{"count":4860,"next":null,"previous":"https://metax.demo.fairdata.fi/v3/datasets?format=json&limit=20&offset=4820","results":[{"id":"c8596ad5-1975-4b50-9634-e1c5f5afd7fd","access_rights":{"id":"fddb6819-0b18-4f7c-ad16-118d13ac5f28","license":[{"id":"edc3e7d1-0e14-490e-a7dd-6ace3dcb3673","url":"http://uri.suomi.fi/codelist/fairdata/license/code/CC0-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Creative Commons CC0 1.0 Universal (CC0 1.0) Public Domain Dedication","fi":"Creative Commons Yleismaailmallinen (CC0 1.0) Public Domain -lausuma"}}],"access_type":{"id":"b41462f7-00bf-4e50-935b-2bf1184453a7","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/open","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Open","fi":"Avoin"}},"restriction_grounds":[]},"actors":[{"id":"5126385c-af7b-4aea-a390-cb9e29cb54da","roles":["creator","rights_holder"],"person":{"id":"ee193871-543c-414a-8831-cd5224a00021","name":"Mietta Lennes","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"b0114513-ca9e-43db-a4c3-a9bc30256483","roles":["creator"],"person":{"id":"681a48e1-e619-4561-befb-3ee7bb2ffe6c","name":"Jussi Piitulainen","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"cefd1004-28f6-46be-a0d6-dcc749684c94","roles":["creator","rights_holder"],"person":{"id":"36d271d7-8d6a-44d2-b794-5cd1d40d0138","name":"Tero Aalto","email":""},"organization":{"id":"477dfdb6-563e-41d9-badc-ec3975f79256","pref_label":{"en":"CSC – IT Center for Science","fi":"CSC - Tieteen tietotekniikan keskus Oy","sv":"CSC – IT Center for Science","und":"CSC - Tieteen tietotekniikan keskus Oy"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/09206320","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"fbbd6ea0-39c1-4af0-a485-165cadb76fa8","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"d41dacd2-a3bb-4cdf-bc9a-6f069d563c26","roles":["curator"],"person":{"id":"9d355f04-67e0-4f39-b492-83542f9365f0","name":"User support at CSC - IT Center for Science Ltd. The Language Bank of Finland","email":""},"organization":{"id":"477dfdb6-563e-41d9-badc-ec3975f79256","pref_label":{"en":"CSC – IT Center for Science","fi":"CSC - Tieteen tietotekniikan keskus Oy","sv":"CSC – IT Center for Science","und":"CSC - Tieteen tietotekniikan keskus Oy"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/09206320","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"06e825dd-9df8-4d1f-a6f7-573025013741","roles":["rights_holder"],"person":{"id":"e2114598-c51b-4e9d-bb65-f6ee6baa55c8","name":"Jussi Piitulainen","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"The resource, which is the Helsinki Korp version of the Route to A wing Corpus, is available in Kielipankki - the Language Bank of Finland at http://urn.fi/urn:nbn:fi:lb-2015050502\n\nFor more information see http://urn.fi/urn:nbn:fi:lb-2014101401"},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2016042614","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"The Helsinki Korp Version of the Route to A wing Corpus","fi":"Reitti A-siipeen -korpuksen Helsinki-Korp-versio"},"created":"2023-04-05T00:00:00Z","modified":"2024-12-04T12:53:57Z","dataset_versions":[{"id":"c8596ad5-1975-4b50-9634-e1c5f5afd7fd","title":{"en":"The Helsinki Korp Version of the Route to A wing Corpus","fi":"Reitti A-siipeen -korpuksen Helsinki-Korp-versio"},"persistent_identifier":"urn:nbn:fi:lb-2016042614","state":"published","created":"2023-04-05T00:00:00Z","version":1}],"published_revision":14,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"d2f2386a-fc21-499d-bafc-9378346a39c1","access_rights":{"id":"baf54dea-3271-4212-a474-e40bba6b5525","license":[{"id":"edc3e7d1-0e14-490e-a7dd-6ace3dcb3673","url":"http://uri.suomi.fi/codelist/fairdata/license/code/CC0-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Creative Commons CC0 1.0 Universal (CC0 1.0) Public Domain Dedication","fi":"Creative Commons Yleismaailmallinen (CC0 1.0) Public Domain -lausuma"}}],"access_type":{"id":"b41462f7-00bf-4e50-935b-2bf1184453a7","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/open","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Open","fi":"Avoin"}},"restriction_grounds":[]},"actors":[{"id":"46a7f148-6725-4785-a406-f73176c89d53","roles":["creator","rights_holder"],"person":{"id":"2655eef4-bb6b-40d7-9689-dbc6c577e554","name":"Mietta Lennes","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"610ed2c8-0aab-4de3-89ac-080cae3fc254","roles":["creator"],"person":{"id":"177756aa-56cd-4a1a-8bd1-278740d6ac2a","name":"Jussi Piitulainen","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"5a186eea-b4e1-42c1-9c55-177a48e9905a","roles":["creator","rights_holder"],"person":{"id":"d690219d-938c-43a3-b7d1-e9536d234138","name":"Tero Aalto","email":""},"organization":{"id":"477dfdb6-563e-41d9-badc-ec3975f79256","pref_label":{"en":"CSC – IT Center for Science","fi":"CSC - Tieteen tietotekniikan keskus Oy","sv":"CSC – IT Center for Science","und":"CSC - Tieteen tietotekniikan keskus Oy"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/09206320","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"7f1599bd-aaa6-4b8f-8068-a93daa619460","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"f2d1e04b-175b-4f83-9e4f-404536fec42c","roles":["curator"],"person":{"id":"0067ec3f-8425-462d-8edb-3bb2a874f324","name":"User support at CSC - IT Center for Science Ltd. The Language Bank of Finland","email":""},"organization":{"id":"477dfdb6-563e-41d9-badc-ec3975f79256","pref_label":{"en":"CSC – IT Center for Science","fi":"CSC - Tieteen tietotekniikan keskus Oy","sv":"CSC – IT Center for Science","und":"CSC - Tieteen tietotekniikan keskus Oy"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/09206320","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"d744a548-a01e-4485-a542-021e2a88c4ed","roles":["rights_holder"],"person":{"id":"06f9c592-8156-4ba5-bfbc-4ce4430850a8","name":"Jussi Piitulainen","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"Until November 2020, this corpus was available via the LAT platform in Kielipankki - the Language Bank of Finland (see Access location).\n\nA downloadable version of the same content is available (see Relations). Further details about the most recent version are available on the info page of this corpus family (https://www.kielipankki.fi/aineistot/reittidemo/, in Finnish).","fi":"Tämä aineisto oli saatavilla Kielipankin LAT-alustan kautta marraskuuhun 2020 saakka (ks. Access location).\n\nAineistosta on saatavilla vastaavan sisältöinen ladattava versio (ks. Relations). Lisätietoja löytyy aineiston tietosivulta Kielipankissa (ks. https://www.kielipankki.fi/aineistot/reittidemo)."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2016042613","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"The Helsinki LAT Version of the Route to A wing Corpus","fi":"Reitti A-siipeen -korpuksen Helsinki-LAT-versio"},"created":"2023-09-09T00:00:00Z","modified":"2024-12-04T12:53:53Z","dataset_versions":[{"id":"d2f2386a-fc21-499d-bafc-9378346a39c1","title":{"en":"The Helsinki LAT Version of the Route to A wing Corpus","fi":"Reitti A-siipeen -korpuksen Helsinki-LAT-versio"},"persistent_identifier":"urn:nbn:fi:lb-2016042613","state":"published","created":"2023-09-09T00:00:00Z","version":1}],"published_revision":14,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"143c69e4-9347-45bb-926d-f16faf47768d","access_rights":{"id":"1bf9d675-1898-4a30-8561-9bae8f3a4655","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","custom_url":"http://urn.fi/urn:nbn:fi:lb-20150304134","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"d7c057cc-0076-4cee-aa60-354a285586c3","roles":["creator","rights_holder"],"organization":{"id":"bdd6cb24-71fe-40e0-9ba0-bfb1ea32b50a","pref_label":{"en":"University of Jyväskylä","fi":"Jyväskylän yliopisto","sv":"Jyväskylä universitet","und":"Jyväskylän yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01906","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"b5317b81-5dd1-4cb0-8df6-17aeed0c4af6","roles":["curator"],"person":{"id":"0d701595-f9da-4a11-a379-70149233765b","name":"User support at CSC - IT Center for Science Ltd. The Language Bank of Finland","email":""},"organization":{"id":"477dfdb6-563e-41d9-badc-ec3975f79256","pref_label":{"en":"CSC – IT Center for Science","fi":"CSC - Tieteen tietotekniikan keskus Oy","sv":"CSC – IT Center for Science","und":"CSC - Tieteen tietotekniikan keskus Oy"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/09206320","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"aaf593ee-68c1-45af-bb83-8f3f97709cc7","roles":["curator"],"person":{"id":"ab01fe2b-0d8a-4187-a9e1-ce153b951228","name":"Terho Joutsen","email":""},"organization":{"id":"bdd6cb24-71fe-40e0-9ba0-bfb1ea32b50a","pref_label":{"en":"University of Jyväskylä","fi":"Jyväskylän yliopisto","sv":"Jyväskylä universitet","und":"Jyväskylän yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01906","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"a4c40880-7c92-4b66-b5d3-e499c4d771ac","roles":["publisher"],"organization":{"id":"eac20fd9-c416-494f-a06e-189d8b90c93c","pref_label":{"en":"Multiple publishers, check distribution rights holders in original metadata by following its persistent identifier"}}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"The corpus is available in Kielipankki - the Language Bank of Finland (puhti.csc.fi, access rights instructions: https://www.kielipankki.fi/support/access/). \n\nLicence: https://www.kielipankki.fi/lic/kra/\n\nA digitized corpus for the study of the lexis and syntax of Middle French and for text editions.\n\nThe corpus consists of 14 documents and 430 000 words. The corpus contains prose, novels, plays and lyrical poetry. It can be used to study the Middle French vocabulary and syntax. \n\nLicense information: http://urn.fi/urn:nbn:fi:lb-20150304134\n\nMore information on the corpus:\nhttp://urn.fi/urn:nbn:fi:lb-201406034\n\nThe purpose of the resource use must be outlined in a research plan."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"0974b041-177a-48b6-b3af-0f68e212d27e","url":"http://lexvo.org/id/iso639-3/frm","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Middle French","fi":"keskiranska","sv":"medelfranska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-201403264","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Jyväskylä Corpus of Middle French","fi":"Keskiranskan korpus"},"created":"2023-04-07T00:00:00Z","modified":"2024-12-04T12:51:48Z","dataset_versions":[{"id":"143c69e4-9347-45bb-926d-f16faf47768d","title":{"en":"Jyväskylä Corpus of Middle French","fi":"Keskiranskan korpus"},"persistent_identifier":"urn:nbn:fi:lb-201403264","state":"published","created":"2023-04-07T00:00:00Z","version":1}],"published_revision":15,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"a0c049db-1b5a-43d1-a9ec-5a1a156c0f7e","access_rights":{"id":"2f5c4bcc-b276-4529-b04b-09c386f16101","license":[{"id":"64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9","custom_url":"http://urn.fi/urn:nbn:fi:lb-2024070701","url":"http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Creative Commons Attribution 1.0 Generic (CC BY 1.0)","fi":"Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"}}],"access_type":{"id":"b41462f7-00bf-4e50-935b-2bf1184453a7","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/open","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Open","fi":"Avoin"}},"restriction_grounds":[]},"actors":[{"id":"a7cbe292-e351-4b99-be65-4b140f9f7c73","roles":["creator","curator","rights_holder"],"person":{"id":"5b3c903e-70b9-40cd-b927-8e15ec489415","name":"Lotta Aunio","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"319283d1-cf45-4835-98df-cf2129a082f7","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"The corpus will be available in the Language Bank of Finland via Korp.\n\nThis corpus of spoken Ha language consists of transcripts of various types of natural speech (stories, discussions and elicited materials) collected in the towns of Kibondo, Kasulu and Kigoma and nearby regions in Tanzania during the years 1997, 2000 and 2003. The original transcripts have been pseudonymized.\n\nHa language (ISO 639-3: haq; Great Lakes Bantu language JD66; alternative names Igiha, Giha, Kiha) is spoken in Western Tanzania in the Kigoma region. It is closely related to, for example, Rundi of Burundi and Kinyarwanda of Rwanda. Ha is one of biggest languages in Tanzania with approximately 1,2 million speakers.\n\nThe collection and analysis of the corpus data is described in the following publication:\nHarjula, Lotta 2004. The Ha Language of Tanzania: Grammar, Texts, and Vocabulary. East African Languages and Dialects 13. Cologne: Köppe. ISBN 978-3-89645-027-2.","fi":"Aineisto on tulossa saataville Kielipankin Korp-palvelun kautta.\n\nAineisto sisältää eri tyyppisten puhutun han kielen näytteiden (tarinat, keskustelut ja elisitoidut lauseet) tekstimuotoisia litteraatteja. Näytteet on kerätty Kibondon, Kasulun ja Kigoman kaupungeissa ja niiden ympäristössä Länsi-Tansaniassa vuosina 199, 2000 ja 2003. Alkuperäiset litteraatit on peudonymisoitu.\n\nHan kieltä (ISO 639-3: haq; Suurten järvien bantukieli JD66; vaihtoehtoiset nimet igiha, giha, kiha) puhutaan Länsi-Tansaniassa Kigoman läänissä. Se on läheistä sukua esimerkiksi Burundissa puhuttavalle rundin kielelle ja Ruandan kinyaruandalle. Ha on yksi Tansanian suurimmista kielistä: sitä puhuu noin 1,2 miljoonaa ihmistä.\n\nAineiston keruu ja analyysi on tarkemmin kuvattu seuraavassa han kielioppia ja sanastoa käsittelevässä teoksessa:\nHarjula, Lotta, 2004. The Ha Language of Tanzania: Grammar, Texts, and Vocabulary. East African Languages and Dialects 13. Köln: Köppe. ISBN 978-3-89645-027-2."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"5dd35420-578c-48c1-996a-90c569b3ffd3","url":"http://lexvo.org/id/iso639-3/haq","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Ha"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2017022101","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Ha Language Corpus, Helsinki Korp Version","fi":"Ha-kieliaineiston Helsinki-Korp-versio"},"created":"2023-04-05T00:00:00Z","modified":"2024-07-10T08:40:29Z","dataset_versions":[{"id":"a0c049db-1b5a-43d1-a9ec-5a1a156c0f7e","title":{"en":"Ha Language Corpus, Helsinki Korp Version","fi":"Ha-kieliaineiston Helsinki-Korp-versio"},"persistent_identifier":"urn:nbn:fi:lb-2017022101","state":"published","created":"2023-04-05T00:00:00Z","version":1}],"published_revision":14,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"29f8621f-7fd4-4051-8eb8-8cde86352606","access_rights":{"id":"9e97f9d9-c7f0-4f53-8645-415149ec7069","license":[{"id":"cef12353-9b39-4c92-8a0c-8de977ac8d28","custom_url":"http://urn.fi/urn:nbn:fi:lb-2019121001","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinACA+NC-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN ACA+NC (Academic, Non-Commercial) End-User License 1.0"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"d0da98cd-9cd2-4352-b12a-3e3efcb585fd","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/research","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restriced access for research based on contract","fi":"Saatavuutta rajoitettu sopimuksen perusteella vain tutkimuskäyttöön","sv":"Begränsad åtkomst på bas av kontrakt ändast för forskningsändamål"}}]},"actors":[{"id":"1bd055ec-96c7-4ff4-8a44-8b1dee559dd1","roles":["creator","curator"],"person":{"id":"c46b0104-a12b-45b2-9686-155cd63a972a","name":"Anna Dmitrieva","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"11265d13-1869-45a2-b77d-30949011f810","roles":["creator","rights_holder"],"organization":{"id":"0dcc95ab-5795-4014-af70-29d526b0b396","pref_label":{"en":"Finnish Broadcasting Company (Yle)","fi":"Yleisradio Oy"},"homepage":{"url":"https://yle.fi/"},"email":""}},{"id":"9770abe1-d6ae-4fc9-b5ca-71c5d039ee41","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"This resource will be available via Korp in Kielipankki – the Language Bank of Finland.\n\nThis is a parallel corpus created of the Yle news articles from 2014-2020 by aligning the standard Finnish versions with the easy-language versions. The dataset, created by Anna Dmitrieva and available in CSV format, is aligned on the sentence level. It is based on the two parallel document-level datasets of Yle News articles available on Kielipankki (http://urn.fi/urn:nbn:fi:lb-2022111625 and http://urn.fi/urn:nbn:fi:lb-2024011701). The dataset spans the period from September 2014 to December 2020.\n\nThis dataset is comprised of the following parts:\n1) Sentence alignments: parallel documents from regular and Easy Finnish Yle news articles aligned sentence-by-sentence. Only the \"positive\" documents were taken from the 2019-2020 dataset (http://urn.fi/urn:nbn:fi:lb-2022111625). All but 50 documents were aligned automatically with Vecalign (https://github.com/thompsonb/vecalign) using LASER embeddings (https://github.com/facebookresearch/LASER). Each document has the following columns:\n1.1) pair_id: an id comprised of three parts divided by a double underscore: the id of the regular document, the id of the Easy Finnish document (with a singular underscore), and the sentence pair number.\n1.2) regular_string: a sentence from the regular Finnish article.\n1.3) selko_string: a corresponding sentence from the Easy Finnish article.\n1.4) score: the confidence score given by Vecalign. The lower the score, the more similar the sentences. The \"good\" pairs are estimated to have a score below or equal to 0.65; however, the score is not definitive proof of whether the sentences in the pair truly match in meaning. The zero score is assigned when a sentence has no pair. The scores for all non-zero sentence pairs in manually aligned documents are set to 0.(3).\n2) Golden sentence alignments: 50 documents aligned manually by a human assessor (text). Also available in the ladder format (indexes)."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2024031301","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Parallel Sentence Aligned Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2020, Korp","fi":"Lausetasolla kohdistettu suomi–selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2020, Korp"},"created":"2024-03-27T00:00:00Z","modified":"2024-06-19T08:32:26Z","dataset_versions":[{"id":"29f8621f-7fd4-4051-8eb8-8cde86352606","title":{"en":"Parallel Sentence Aligned Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2020, Korp","fi":"Lausetasolla kohdistettu suomi–selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2020, Korp"},"persistent_identifier":"urn:nbn:fi:lb-2024031301","state":"published","created":"2024-03-27T00:00:00Z","version":1}],"published_revision":12,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"c39baf38-167a-4924-9088-42b098e47f5e","access_rights":{"id":"f2444709-3619-45b5-aaec-b77045662ee0","license":[{"id":"cef12353-9b39-4c92-8a0c-8de977ac8d28","custom_url":"http://urn.fi/urn:nbn:fi:lb-2022050901","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinACA+NC-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN ACA+NC (Academic, Non-Commercial) End-User License 1.0"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"d0da98cd-9cd2-4352-b12a-3e3efcb585fd","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/research","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restriced access for research based on contract","fi":"Saatavuutta rajoitettu sopimuksen perusteella vain tutkimuskäyttöön","sv":"Begränsad åtkomst på bas av kontrakt ändast för forskningsändamål"}}]},"actors":[{"id":"a2c52220-3674-4dc9-9506-3a5673fe79e9","roles":["creator","curator"],"person":{"id":"96f9aea5-f8c2-4041-8586-1b0766052fbf","name":"Anna Dmitrieva","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"2100680b-2823-41fa-b4ac-98edba39627a","roles":["creator","rights_holder"],"organization":{"id":"f4e023be-53b8-4eb7-b502-50958280aa5c","pref_label":{"en":"Finnish Broadcasting Company (Yle)","fi":"Yleisradio Oy"},"homepage":{"url":"https://yle.fi/"},"email":""}},{"id":"863ca0b1-bd7a-4fe9-9c7b-c6e24dc613e2","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"This resource is available for download in Kielipankki – the Language Bank of Finland.\n\nThis is a parallel corpus created of the Yle news articles from 2014-2018 by aligning the standard Finnish versions with the easy-language versions. The dataset, created by Anna Dmitrieva and available in CSV format, is aligned on the document level. The news articles were obtained from the datasets available via Kielipankki (http://urn.fi/urn:nbn:fi:lb-2017070501 and http://urn.fi/urn:nbn:fi:lb-2019050901).\n\nThis dataset extends the previously published Parallel Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2019-2020 (http://urn.fi/urn:nbn:fi:lb-2022111625). Please note that this dataset has not been assessed by a human expert. The articles have been aligned automatically with the Vecalign document alignment algorithm (https://github.com/thompsonb/vecalign) without candidate rescoring, using LASER embeddings (https://github.com/facebookresearch/LASER).\n\nDescription of all columns in the dataset:\n-index_in_selko: This index consists of two parts divided by an underscore. The first (longer) part identifies the entire Easy Finnish article from the original dataset. The second (shorter) part is the number of the paragraph. Since the Yle Selkosuomi articles usually consist of multiple paragraphs, each paragraph describing a separate piece of news, we represent each paragraph as an individual little article in our dataset. Paragraph numbering starts with 0.\n- index_in_regular: The identifier of the regular Finnish article taken from the original dataset.\n- selko_text: A piece of news in Easy Finnish.\n- regular_text: A corresponding piece of news in regular Finnish.\n- distance: The cosine distance between the document vectors. The lower the distance, the more similar the documents are."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2024011701","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Parallel Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2018, source","fi":"Suomi-selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2018, lähdeaineisto"},"created":"2024-02-02T00:00:00Z","modified":"2024-06-19T08:31:00Z","dataset_versions":[{"id":"c39baf38-167a-4924-9088-42b098e47f5e","title":{"en":"Parallel Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2018, source","fi":"Suomi-selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2018, lähdeaineisto"},"persistent_identifier":"urn:nbn:fi:lb-2024011701","state":"published","created":"2024-02-02T00:00:00Z","version":1}],"published_revision":12,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"74a8ede4-89fb-4036-99d0-9cd2967c70cd","access_rights":{"id":"e9d187f1-1a23-4ee9-9a3b-f432432a8b12","license":[{"id":"cef12353-9b39-4c92-8a0c-8de977ac8d28","custom_url":"http://urn.fi/urn:nbn:fi:lb-2022050901","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinACA+NC-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN ACA+NC (Academic, Non-Commercial) End-User License 1.0"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"d0da98cd-9cd2-4352-b12a-3e3efcb585fd","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/research","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restriced access for research based on contract","fi":"Saatavuutta rajoitettu sopimuksen perusteella vain tutkimuskäyttöön","sv":"Begränsad åtkomst på bas av kontrakt ändast för forskningsändamål"}}]},"actors":[{"id":"4c8c751f-5e8a-42d7-b16f-52cc5cd495c5","roles":["creator","curator"],"person":{"id":"b9068701-b790-4f09-b4ef-4134fa03b632","name":"Anna Dmitrieva","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"b194efc6-a0f3-4696-920e-4d08b75dbaef","roles":["creator","rights_holder"],"organization":{"id":"a7aa5c3d-f199-4160-a24f-6ec732b48216","pref_label":{"en":"Finnish Broadcasting Company (Yle)","fi":"Yleisradio Oy"},"homepage":{"url":"https://yle.fi/"},"email":""}},{"id":"4921472c-0b67-4748-9031-ac93225c38a6","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"This resource is available for download in Kielipankki – the Language Bank of Finland.\n\nThis is a parallel corpus created of the Yle news articles from 2014-2020 by aligning the standard Finnish versions with the easy-language versions. The dataset, created by Anna Dmitrieva and available in CSV format, is aligned on the sentence level. It is based on the two parallel document-level datasets of Yle News articles available on Kielipankki (http://urn.fi/urn:nbn:fi:lb-2022111625 and http://urn.fi/urn:nbn:fi:lb-2024011701). The dataset spans the period from September 2014 to December 2020.\n\nThis dataset is comprised of the following parts:\n1) Sentence alignments: parallel documents from regular and Easy Finnish Yle news articles aligned sentence-by-sentence. Only the \"positive\" documents were taken from the 2019-2020 dataset (http://urn.fi/urn:nbn:fi:lb-2022111625). All but 50 documents were aligned automatically with Vecalign (https://github.com/thompsonb/vecalign) using LASER embeddings (https://github.com/facebookresearch/LASER). Each document has the following columns:\n1.1) pair_id: an id comprised of three parts divided by a double underscore: the id of the regular document, the id of the Easy Finnish document (with a singular underscore), and the sentence pair number.\n1.2) regular_string: a sentence from the regular Finnish article.\n1.3) selko_string: a corresponding sentence from the Easy Finnish article.\n1.4) score: the confidence score given by Vecalign. The lower the score, the more similar the sentences. The \"good\" pairs are estimated to have a score below or equal to 0.65; however, the score is not definitive proof of whether the sentences in the pair truly match in meaning. The zero score is assigned when a sentence has no pair. The scores for all non-zero sentence pairs in manually aligned documents are set to 0.(3).\n2) Golden sentence alignments: 50 documents aligned manually by a human assessor (text). Also available in the ladder format (indexes)."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2024011703","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Parallel Sentence Aligned Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2020, source","fi":"Lausetasolla kohdistettu suomi–selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2020, lähdeaineisto"},"created":"2024-02-09T00:00:00Z","modified":"2024-06-19T08:30:55Z","dataset_versions":[{"id":"74a8ede4-89fb-4036-99d0-9cd2967c70cd","title":{"en":"Parallel Sentence Aligned Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2020, source","fi":"Lausetasolla kohdistettu suomi–selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2020, lähdeaineisto"},"persistent_identifier":"urn:nbn:fi:lb-2024011703","state":"published","created":"2024-02-09T00:00:00Z","version":1}],"published_revision":12,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"73b6c56e-13ee-4ac6-949c-4ae546b27f3e","access_rights":{"id":"1ffff6fd-5111-446b-bc5f-703b68a7c311","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}},{"id":"5a00a777-42a2-41a9-9911-968146f7e53f","url":"http://uri.suomi.fi/codelist/fairdata/license/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Other","fi":"Muu"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"da6d4157-741c-4e00-96aa-4c983a2941ba","roles":["creator","curator"],"person":{"id":"e153d443-2054-4dc8-ad38-0b73b30133b9","name":"Anssi Moisio","email":""},"organization":{"id":"2f9f9011-4061-4a93-96af-768471abada7","pref_label":{"en":"Aalto University","fi":"Aalto-yliopisto","sv":"Aalto-universitetet","und":"Aalto-yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/10076","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"9fbbc378-8a7a-41b5-8f32-c389bfe39e4c","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"This resource is available for download in Kielipankki - The Language Bank of Finland as part of \"Donate Speech: Selected dataset\", http://urn.fi/urn:nbn:fi:lb-2022060127.\n\nThe resource contains a 10-hour subset of speech from the Donate Speech Corpus. This set includes the smaller set puhelahjat-test-mtr, where each recording was transcribed by four different transcribers, but the set was extended by including all recordings by the same 57 speakers (according to the metadata accompanying the original recordings). The multi-transcriber data was used for testing an ASR system at Aalto University.\n\nFor speech technology development purposes, this multi-transcriber speaker dataset can be used together with the smaller puhelahjat-test-mtr set."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2022060125","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Donate Speech Corpus: Test data from multi-transcriber speakers (10h)","fi":"Lahjoita puhetta -aineisto: Testidata useaan kertaan litteroiduilta puhujilta (10h)"},"created":"2023-04-21T00:00:00Z","modified":"2024-06-19T08:26:06Z","dataset_versions":[{"id":"73b6c56e-13ee-4ac6-949c-4ae546b27f3e","title":{"en":"Donate Speech Corpus: Test data from multi-transcriber speakers (10h)","fi":"Lahjoita puhetta -aineisto: Testidata useaan kertaan litteroiduilta puhujilta (10h)"},"persistent_identifier":"urn:nbn:fi:lb-2022060125","state":"published","created":"2023-04-21T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"20c70fe8-07d5-47b6-a823-d3576644facf","access_rights":{"id":"4d207f2c-999a-4127-a75d-fcfc1b5399b7","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","custom_url":"http://urn.fi/urn:nbn:fi:lb-2022062222","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"0e9763b6-a8ee-4ff6-904b-5e389a13b271","roles":["creator","curator"],"person":{"id":"a25f6e2f-6bfd-4a71-bec2-799293abef84","name":"Tuomas Harviainen","email":""},"organization":{"id":"755e6950-1e73-42ac-aa83-70b99783fad0","pref_label":{"en":"Tampere University","fi":"Tampereen yliopisto"},"homepage":{"url":"https://ror.org/033003e23"},"email":""}},{"id":"c103a96d-e0f1-4211-bf09-effaea024141","roles":["publisher","rights_holder"],"organization":{"id":"755e6950-1e73-42ac-aa83-70b99783fad0","pref_label":{"en":"Tampere University","fi":"Tampereen yliopisto"},"homepage":{"url":"https://ror.org/033003e23"},"email":""}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"The resource is available for restricted use via Kielipankki - the Language Bank of Finland. Instructions on applying for access are available on the resource group page (see Documentation).\n\nThis Finnish dataset consists of 3 104 515 messages posted on the Torilauta discussion board operating in the dark web in the years 2017-2020. The data were collected and submitted by the site administrator in order to be archived for research use. The data set was received by the ENNCODE project at the University of Tampere. \n\nIn addition to the message title and text, the posts contain the following metadata: time stamps of sending and deletion, sender's nickname, subject area, and the message and thread identifiers. The data was provided as a JSONLINES text file, each line of which corresponds to one message and its metadata in JSON format. Individual messages have been removed from the data for data protection reasons.","fi":"Tämä aineisto on saatavilla rajoitettuun käyttöön Kielipankin kautta. Ohjeet käyttöoikeuksien hakemiseen löytyvät aineistoryhmän sivulta (ks. Documentation).\n\nTämä suomenkielinen aineisto koostuu 3 104 515 viestistä, jotka on lähetetty pimeässä verkossa toimineelle Torilauta-keskustelupalstalle vuosina 2017–2020. Aineiston keräsi ja luovutti arkistoitavaksi tutkimuskäyttöä varten sivuston ylläpitäjä. Aineiston vastaanotti Tampereen yliopiston ENNCODE-hanke. \n\nViestit sisältävät otsikon ja tekstin lisäksi seuraavat metatiedot: lähetys- ja poistoaikaleima, lähettäjän nimimerkki, aihealue sekä viesti- ja ketjutunniste. Aineisto on toimitettu JSONLINES-tekstitiedostona, jonka jokainen rivi vastaa yhtä viestiä metatietoineen JSON-muodossa. Tietosuojasyistä aineistosta on poistettu henkilö- ja tunnistetietoja ja kokonaisia viestejä."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2022062221","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Finnish Dark Web Marketplace Corpus","fi":"Suomenkielisen pimeän verkon kauppapaikka-aineisto"},"created":"2024-04-03T00:00:00Z","modified":"2024-06-19T08:24:56Z","dataset_versions":[{"id":"20c70fe8-07d5-47b6-a823-d3576644facf","title":{"en":"Finnish Dark Web Marketplace Corpus","fi":"Suomenkielisen pimeän verkon kauppapaikka-aineisto"},"persistent_identifier":"urn:nbn:fi:lb-2022062221","state":"published","created":"2024-04-03T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"6692df1f-1f0d-4f43-b713-e3e3b36b78ff","access_rights":{"id":"6f6cc8cb-9d01-40e0-8117-950f10624194","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}},{"id":"5a00a777-42a2-41a9-9911-968146f7e53f","url":"http://uri.suomi.fi/codelist/fairdata/license/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Other","fi":"Muu"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"adb3e890-3592-4053-920f-0827d606f789","roles":["creator","curator"],"person":{"id":"bb778074-de00-4152-bafb-06963597a2a3","name":"Anssi Moisio","email":""},"organization":{"id":"2f9f9011-4061-4a93-96af-768471abada7","pref_label":{"en":"Aalto University","fi":"Aalto-yliopisto","sv":"Aalto-universitetet","und":"Aalto-yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/10076","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"98a7ef5c-43c3-44e9-927e-627fc49a9676","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"This resource is available for download in Kielipankki - The Language Bank of Finland as part of \"Donate Speech: Selected dataset\", http://urn.fi/urn:nbn:fi:lb-2022060127.\n\nThe resource contains a subset of 10 hours of transcribed speech that was selected from the Donate Speech Corpus and used for testing an ASR system at Aalto University.\n\nThe test data includes at least ten minutes of speech for each metadata class in each of the five metadata domains (age, dialect, gender, native/non-native and theme). The set contains speech from 103 different speakers (according to the metadata accompanying the original recordings). The gender ratio has been debiased, so that the set includes over 40% male speakers (similarly to the puhelahjat-dev set, while the puhelahjat-train set has just over 20% of male speakers). \n\nFor speech technology development purposes, the test dataset can be used together with the puhelahjat-dev and puhelahjat-train datasets. There is no overlap of speakers between these three sets."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2022060122","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Donate Speech Corpus: Test data (10h)","fi":"Lahjoita puhetta -aineisto: Testidata (10h)"},"created":"2023-04-21T00:00:00Z","modified":"2024-06-19T08:24:24Z","dataset_versions":[{"id":"6692df1f-1f0d-4f43-b713-e3e3b36b78ff","title":{"en":"Donate Speech Corpus: Test data (10h)","fi":"Lahjoita puhetta -aineisto: Testidata (10h)"},"persistent_identifier":"urn:nbn:fi:lb-2022060122","state":"published","created":"2023-04-21T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"212653f4-5a1a-4443-bbe5-7c48c7db799c","access_rights":{"id":"2ee56bf8-c6fc-48ef-b866-ed875e9fcbc7","license":[{"id":"edc3e7d1-0e14-490e-a7dd-6ace3dcb3673","custom_url":"http://urn.fi/urn:nbn:fi:lb-2022041923","url":"http://uri.suomi.fi/codelist/fairdata/license/code/CC0-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Creative Commons CC0 1.0 Universal (CC0 1.0) Public Domain Dedication","fi":"Creative Commons Yleismaailmallinen (CC0 1.0) Public Domain -lausuma"}}],"access_type":{"id":"b41462f7-00bf-4e50-935b-2bf1184453a7","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/open","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Open","fi":"Avoin"}},"restriction_grounds":[]},"actors":[{"id":"17ac405b-5f80-4922-8a73-f750900a2f49","roles":["creator","curator","rights_holder"],"person":{"id":"62975232-da4c-4482-b0fe-e916179b8d2d","name":"Frankie R. Robertson","email":""},"organization":{"id":"bdd6cb24-71fe-40e0-9ba0-bfb1ea32b50a","pref_label":{"en":"University of Jyväskylä","fi":"Jyväskylän yliopisto","sv":"Jyväskylä universitet","und":"Jyväskylän yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01906","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"99d21861-6d47-44b0-8a6d-196031697c26","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"The TallVocabL2Fi dataset comprises of responses from 15 participants to a \"tall\" 12000 word 5-point scale self-rating response task and a 100 word confirmatory word translation response task. The 15 participants were split by native language, 5 English, 4 Hungarian and 6 Russian, and self-reported CEFR reading level, 5 B1, 4 B2, 5 C1 and 2 C2. The data was gathered through a website from paid participants resident in Finland over a period of 3 months from September and November 2021. In total there are 180 thousand word knowledge self-rating responses and 1.5 thousand word translation responses.\n\nThe dataset is unique in its combination of the tall data collection set up, where responses are collected for many words, the varied backgrounds of the learners, the use of Finnish prompt words, and the triangulation with a word translation test. The dataset can be used for vocabulary acquisition research in general, but it is particularly suited to evaluation of the task of Vocabulary Inventory Prediction (VIP) including techniques based on Computer-Adaptive Testing (CAT).\n\nThe dataset is relational/tabular. It is distributed as a series of TSV files along with a SQL schema exported from DuckDB. \n\nThe TallVocabL2Fi dataset is available for download via Kielipankki – The Language Bank of Finland.\n\nFurther information about the schema and the collection process is available in the readme included with the data, and in the accompanying publication: \n\nRobertson, F., Chang & L., Söyrinki, S. (2022). TallVocabL2Fi: An Extensive Mapping of 15 Finnish L2 Learners' Vocabulary. In Language Resources and Evaluation Conference (LREC 2022)."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2022041921","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"TallVocabL2Fi: Measurements of 15 L2 Finnish learners' vocabularies","fi":"TallVocabL2Fi: Mitat 15 S2-opiskelijan sanavarastosta"},"created":"2023-04-05T00:00:00Z","modified":"2024-06-19T08:23:20Z","dataset_versions":[{"id":"212653f4-5a1a-4443-bbe5-7c48c7db799c","title":{"en":"TallVocabL2Fi: Measurements of 15 L2 Finnish learners' vocabularies","fi":"TallVocabL2Fi: Mitat 15 S2-opiskelijan sanavarastosta"},"persistent_identifier":"urn:nbn:fi:lb-2022041921","state":"published","created":"2023-04-05T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"df695ee8-c5f8-495a-b8a5-2658085d0894","access_rights":{"id":"a473a449-f834-48b1-bf1e-89f290cf979f","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}},{"id":"5a00a777-42a2-41a9-9911-968146f7e53f","url":"http://uri.suomi.fi/codelist/fairdata/license/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Other","fi":"Muu"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"f786e469-71ea-459c-9cdf-5eb4ee60d54b","roles":["creator","curator"],"person":{"id":"775cb394-61fa-451f-8cf1-6d21b62cb9a9","name":"Anssi Moisio","email":""},"organization":{"id":"2f9f9011-4061-4a93-96af-768471abada7","pref_label":{"en":"Aalto University","fi":"Aalto-yliopisto","sv":"Aalto-universitetet","und":"Aalto-yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/10076","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"52ea557b-003a-4027-88ee-ec72d279e961","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"This resource is available for download in Kielipankki - The Language Bank of Finland as part of \"Donate Speech: Selected dataset\", http://urn.fi/urn:nbn:fi:lb-2022060127.\n\nThe resource contains a subset of 100 hours of transcribed speech that was selected from the Donate Speech Corpus and used for training an ASR system at Aalto University.\n\nThe training data includes speech from 1129 different speakers (according to the metadata accompanying the original recordings). Note that the training dataset has just over 20% of male speakers, whereas the puhelahjat-test and puhelahjat-dev sets contain 40% of male speakers.\n\nFor speech technology development purposes, the training dataset can be used together with the puhelahjat-test and puhelahjat-dev datasets. There is no overlap of speakers between these three sets."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2022060123","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Donate Speech Corpus: Training data (100h)","fi":"Lahjoita puhetta -aineisto: Opetusdata (100h)"},"created":"2023-04-21T00:00:00Z","modified":"2024-06-19T08:21:24Z","dataset_versions":[{"id":"df695ee8-c5f8-495a-b8a5-2658085d0894","title":{"en":"Donate Speech Corpus: Training data (100h)","fi":"Lahjoita puhetta -aineisto: Opetusdata (100h)"},"persistent_identifier":"urn:nbn:fi:lb-2022060123","state":"published","created":"2023-04-21T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"24da85be-f979-464f-b5ee-6a1755d18fea","access_rights":{"id":"9c449a2d-da8c-41d7-961d-043b370c9ce9","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}},{"id":"5a00a777-42a2-41a9-9911-968146f7e53f","url":"http://uri.suomi.fi/codelist/fairdata/license/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Other","fi":"Muu"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"a4cc9f3d-158b-4f55-ac84-477f404baf44","roles":["creator","curator"],"person":{"id":"e2a3c815-96f0-4df5-b6cd-f8ad417a4d23","name":"Anssi Moisio","email":""},"organization":{"id":"2f9f9011-4061-4a93-96af-768471abada7","pref_label":{"en":"Aalto University","fi":"Aalto-yliopisto","sv":"Aalto-universitetet","und":"Aalto-yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/10076","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"720a2c4e-cdfd-4dc4-af1b-f7eb32709b3e","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"This resource is available for download in Kielipankki - The Language Bank of Finland as part of \"Donate Speech: Selected dataset\", http://urn.fi/urn:nbn:fi:lb-2022060127.\n\nThe resource contains a 1-hour subset of speech from the Donate Speech Corpus. In this set, each recording was transcribed by four different transcribers. The multi-transcriber data was used for testing an ASR system at Aalto University.\n\nThe set contains speech from 57 different speakers (according to the metadata accompanying the original recordings).\n\nFor speech technology development purposes, this multi-transcriber test dataset can be used together with the puhelahjat-test-mtrs set that was extended by adding all recordings by the same speakers to the current puhelahjat-test-mtr dataset."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2022060124","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Donate Speech Corpus: Multi-transcriber test data (1h)","fi":"Lahjoita puhetta -aineisto: Usean litteroijan testidata (1h)"},"created":"2023-04-21T00:00:00Z","modified":"2024-06-19T08:21:19Z","dataset_versions":[{"id":"24da85be-f979-464f-b5ee-6a1755d18fea","title":{"en":"Donate Speech Corpus: Multi-transcriber test data (1h)","fi":"Lahjoita puhetta -aineisto: Usean litteroijan testidata (1h)"},"persistent_identifier":"urn:nbn:fi:lb-2022060124","state":"published","created":"2023-04-21T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"99a59be7-6780-4144-a33f-2a6537bd05b8","access_rights":{"id":"c1a448a1-de7b-4ba0-aa53-ffc271c2eda6","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}},{"id":"5a00a777-42a2-41a9-9911-968146f7e53f","url":"http://uri.suomi.fi/codelist/fairdata/license/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Other","fi":"Muu"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"05181b83-d8fb-4749-bcd9-41b86da4e65f","roles":["creator","curator"],"person":{"id":"cb8a4107-f503-48da-ad85-9390ee770571","name":"Anssi Moisio","email":""},"organization":{"id":"2f9f9011-4061-4a93-96af-768471abada7","pref_label":{"en":"Aalto University","fi":"Aalto-yliopisto","sv":"Aalto-universitetet","und":"Aalto-yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/10076","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"9be84a39-ce6f-4015-93b8-4be8b819f63b","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"This resource is available for download in Kielipankki - The Language Bank of Finland as part of \"Donate Speech: Selected dataset\", http://urn.fi/urn:nbn:fi:lb-2022060127.\n\nThe resource contains a subset of 10 hours of transcribed speech that was selected from the Donate Speech Corpus and used for developing an ASR system at Aalto University.\n\nThe development data includes at least ten minutes of speech for each metadata class in each of the five metadata domains (age, dialect, gender, native/non-native and theme). The set contains speech from 103 different speakers (according to the metadata accompanying the original recordings). The gender ratio has been debiased, so that the set includes over 40% male speakers (similarly to the puhelahjat-test set, while the puhelahjat-train set has just over 20% of male speakers). \n\nFor speech technology development purposes, the development dataset can be used together with the puhelahjat-test and puhelahjat-train datasets. There is no overlap of speakers between these three sets."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2022060121","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Donate Speech Corpus: Development data (10h)","fi":"Lahjoita puhetta -aineisto: Kehitysdata (10h)"},"created":"2023-04-21T00:00:00Z","modified":"2024-06-19T08:19:50Z","dataset_versions":[{"id":"99a59be7-6780-4144-a33f-2a6537bd05b8","title":{"en":"Donate Speech Corpus: Development data (10h)","fi":"Lahjoita puhetta -aineisto: Kehitysdata (10h)"},"persistent_identifier":"urn:nbn:fi:lb-2022060121","state":"published","created":"2023-04-21T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"a3837165-7d27-4f84-9a90-3348595ae786","access_rights":{"id":"1938e07a-a117-426e-afab-5cf0cf7b76b1","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"e00b157d-185c-422b-bfea-f6e15716ace2","roles":["creator","curator","rights_holder"],"person":{"id":"bc8673b5-92c7-4b11-865d-1d7d24eaae5c","name":"Mikko Ojanen","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"51ab8bf8-711f-4b3a-b3ac-569b56d2c267","roles":["publisher","rights_holder"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"fi":"FinEARS-aineisto sisältää suomalaisen elektroakustisen musiikin historiaan liittyviä teemahaastatteluja, joita on tehty vuodesta 2004 alkaen. Aineisto on suomenkielistä. Haastatteluissa käsitellään suomalaisen elektroakustisen musiikin historiaa 1960- ja 1970-luvuilla. Aineisto sisältää muistitietoa ja muistelupuhetta.\n\nAineisto on tulossa saataville Kielipankkiin."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2020030421","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Finnish electroacoustic music interviews","fi":"Suomalaisen elektroakustisen musiikin haastatteluaineisto"},"created":"2024-03-09T00:00:00Z","modified":"2024-06-19T08:19:02Z","dataset_versions":[{"id":"a3837165-7d27-4f84-9a90-3348595ae786","title":{"en":"Finnish electroacoustic music interviews","fi":"Suomalaisen elektroakustisen musiikin haastatteluaineisto"},"persistent_identifier":"urn:nbn:fi:lb-2020030421","state":"published","created":"2024-03-09T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"b6054f95-a86e-45d9-8d27-9cc1d79c3e23","access_rights":{"id":"e3c8f784-c513-4817-bd37-9437d49c4359","license":[{"id":"0f835a1d-e5e0-4465-911c-aae0749610f1","url":"http://uri.suomi.fi/codelist/fairdata/license/code/undernegotiation","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Under negotiation","fi":"Neuvottelut kesken"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"b3fd29a9-985a-4555-8b51-6cc28402e7e2","roles":["creator","publisher","rights_holder"],"organization":{"id":"4599eee9-5e9d-446e-9d4d-449b1819cff4","pref_label":{"en":"University of Eastern Finland","fi":"Itä-Suomen yliopisto","sv":"Östra Finlands universitet","und":"Itä-Suomen yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/10088","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"405f5e6a-94b8-424e-90a2-4e7d6e4a4cbc","roles":["curator"],"person":{"id":"8d2265c6-27ca-4eb4-a6e9-e03a3ff6aacf","name":"Marjatta Palander","email":""},"organization":{"id":"4599eee9-5e9d-446e-9d4d-449b1819cff4","pref_label":{"en":"University of Eastern Finland","fi":"Itä-Suomen yliopisto","sv":"Östra Finlands universitet","und":"Itä-Suomen yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/10088","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"7abd6102-1f88-4797-8243-911625a07641","roles":["curator"],"person":{"id":"5a477019-12df-4052-a79d-9b69d9e9c3c4","name":"Helka Riionheimo","email":""},"organization":{"id":"4599eee9-5e9d-446e-9d4d-449b1819cff4","pref_label":{"en":"University of Eastern Finland","fi":"Itä-Suomen yliopisto","sv":"Östra Finlands universitet","und":"Itä-Suomen yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/10088","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"The corpus of Ingrian Finnish dialects was collected by the University of Joensuu (the predecessor of the University of Eastern Finland). The corpus contains about 100 hours of audio files and transcripts of the interviews of Ingrian Finnish speakers in the territory of Ingria (Russia) and in Estonia.\n\nThe recordings in Russia (about 70 hours) were performed in 1993-1997, and those in Estonia (about 30 hours in total) took place in 1990-1996. The interviewees are middle-aged or elderly speakers of Ingrian that were born in the 1900s-1940s.\n\nThe corpus is not yet available, since it is currently being constructed and reviewed by researchers at the University of Eastern Finland. The material will be made available later at https://lat.csc.fi/."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"fdb49b54-7d28-419b-b86a-e56a3a769365","url":"http://lexvo.org/id/iso639-3/est","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Estonian","fi":"viro","sv":"estniska"}},{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}},{"id":"afcd3a6b-e6cb-4d2b-b31a-6579301f203f","url":"http://lexvo.org/id/iso639-3/rus","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Russian","fi":"venäjä","sv":"ryska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2014073032","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"The Corpus of Ingrian Finnish","fi":"Inkerin murteiden korpus"},"created":"2023-04-05T00:00:00Z","modified":"2024-06-19T08:16:42Z","dataset_versions":[{"id":"b6054f95-a86e-45d9-8d27-9cc1d79c3e23","title":{"en":"The Corpus of Ingrian Finnish","fi":"Inkerin murteiden korpus"},"persistent_identifier":"urn:nbn:fi:lb-2014073032","state":"published","created":"2023-04-05T00:00:00Z","version":1}],"published_revision":14,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"f2f69e2f-3785-4c59-af2f-4efd122bc649","access_rights":{"id":"188418ce-81d4-4462-8255-483ec74ed36d","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"37b26209-be5c-4a02-ab99-6aa9eb06e5f2","roles":["creator","curator","publisher","rights_holder"],"person":{"id":"a39b9d79-fec8-4713-a4f9-eff4124a90ed","name":"Mietta Lennes","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"9dd0f16f-db1d-4adc-89c9-2da93aac8d47","roles":["rights_holder"],"organization":{"id":"6ad641d6-1456-4072-8970-8d1935e6cecc","pref_label":{"en":"Faculty of Behavioural Sciences, University of Helsinki"},"homepage":{"url":"http://www.helsinki.fi/behav"},"email":""}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"The FinDialogue corpus is a subcorpus of FinINTAS. FinDialogue consists of ten spontaneous dialogues between friends, duration 45-55 minutes each. The corpus includes audio files (WAV) and phonetic annotation files (Praat TextGrid). FinDialogue will be made available at http://lat.csc.fi in the near future, along with FinRead.\n\nThe dialogues are numbered from D1 to D12. (The original recordings of D3 and D5 have been excluded due to ethical and technical reasons.)\n\nThe speakers were native Finns from the capital city region in Finland. Ten speakers were 20 to 30 years of age (D1, D2, D4, D6, D7), whereas the rest of the speakers (D8-D12) were between 45-65 years. The speakers are the same as in FinRead, the other subcorpus of FinINTAS.\n\nThe recordings were performed in an anechoic room for dialogues D1-D7 and in a professional recording studio for dialogues D8-D12. In both cases, the speakers were sitting a few meters apart, facing opposite directions, with headphone-microphone combos on their heads. Thus, the situation resembled a telephone conversation. Even though the anechoic room was a somewhat strange environment, it was found that the speakers usually relaxed after a few minutes and started to chat quite casually. In order to encourage ordinary conversation, the person responsible of the recording left the speakers alone and did not monitor them during the session. The recording person interrupted the conversation only a couple times during each recording session in order to see that all was well and to provide the speakers with a new topic to discuss (first school, then movies/films, and finally travel). However, the speakers were instructed not to stick to the given topic in case they found something else to talk about, which thay often did.\n\nThe FinDialogue corpus of spontaneous Finnish speech will be made available at http://lat.csc.fi."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2016041421","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"FinDialogue Corpus of Spontaneous Finnish Speech","fi":"FinDialogue - spontaanin suomenkielisen puheen korpus"},"created":"2023-04-05T00:00:00Z","modified":"2024-06-19T08:08:34Z","dataset_versions":[{"id":"f2f69e2f-3785-4c59-af2f-4efd122bc649","title":{"en":"FinDialogue Corpus of Spontaneous Finnish Speech","fi":"FinDialogue - spontaanin suomenkielisen puheen korpus"},"persistent_identifier":"urn:nbn:fi:lb-2016041421","state":"published","created":"2023-04-05T00:00:00Z","version":1}],"published_revision":14,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"70565792-e787-4bf0-9356-2a47b364a647","access_rights":{"id":"b349408c-1b42-4a45-971d-53d76f782bbc","license":[{"id":"dfdfe068-168e-4647-8a45-9c1d8236f117","url":"http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-NC-SA-4.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)","fi":"Creative Commons Nimeä-EiKaupallinen-JaaSamoin 4.0 Kansainvälinen (CC BY-NC-SA 4.0) "}},{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"83931d0c-0068-466b-ad3d-9072dfdd8300","roles":["creator"],"organization":{"id":"eb5ed7fa-f806-4bd8-b1e7-5f8b856cc687","pref_label":{"fi":"Jyväskylän yliopisto"},"homepage":{"url":"https://www.jyu.fi/hytk/fi/laitokset/kivi/opiskelu/oppiaineet/viittomakieli"},"email":""}},{"id":"a48966dd-0ead-4779-9ec6-bc961e06c734","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"92abb1e4-2f3b-435f-8c39-7c4b61c12c2d","roles":["curator"],"person":{"id":"6e40f7d6-e39a-4609-a167-57cb711bb569","name":"Tommi Jantunen","email":""},"organization":{"id":"bdd6cb24-71fe-40e0-9ba0-bfb1ea32b50a","pref_label":{"en":"University of Jyväskylä","fi":"Jyväskylän yliopisto","sv":"Jyväskylä universitet","und":"Jyväskylän yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01906","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"8b7f2b58-cabb-444c-b359-d62f1a61fbba","roles":["rights_holder"],"organization":{"id":"bdd6cb24-71fe-40e0-9ba0-bfb1ea32b50a","pref_label":{"en":"University of Jyväskylä","fi":"Jyväskylän yliopisto","sv":"Jyväskylä universitet","und":"Jyväskylän yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01906","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"Finnish Sign Language material collected in the CFINSL project. The material consists of video files and the annotations of the videos in ELAN format as well as the metadata about the signers and the content and format of the videos. \n\nThe material comprises conversations and elicited narratives from 21 Finnish Sign Language signers who belong to different age groups and live in different parts of Finland. The signers perform seven fixed tasks which are: 1) introductions, 2) discussing work/hobbies, 3) narrating about short cartoon strips, 4) narrating about a video, 5) narrating a story from a picture book The Snowman or Frog, Where are you?, 6) discussing a topic related to the deaf world, and 7) free discussion (e.g. on travel, sports). All of the video data (15,25 hours x six camera angles) has been annotated for signs and translations.\n\nAccording to the tasks performed by the signers, the corpus has been divided into two subcorpora: one that contains the elicited narratives, and another that contains the conversations. Note that both subcorpora are also available for download. For information on the subcorpora, see Related resources.","fi":"Suomalaisen viittomakielen materiaali, joka on kerätty projektissa CFINSL (Suomen viittomakielten korpukset). Materiaali sisältää videotiedostoja, niiden ELAN-ohjelmalla tuotettuja annotaatiotiedostoja ja metadataa viittojista sekä materiaalin sisällöstä ja muodosta."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"ac272ecd-a881-40b2-a9ef-d421676da946","url":"http://lexvo.org/id/iso639-3/fse","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish Sign Language","fi":"Suomalainen viittomakieli"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2019012321","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Corpus of Finnish Sign Language","fi":"Suomalaisen viittomakielen korpus"},"created":"2023-04-05T00:00:00Z","modified":"2024-06-19T07:54:00Z","dataset_versions":[{"id":"70565792-e787-4bf0-9356-2a47b364a647","title":{"en":"Corpus of Finnish Sign Language","fi":"Suomalaisen viittomakielen korpus"},"persistent_identifier":"urn:nbn:fi:lb-2019012321","state":"published","created":"2023-04-05T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"03613a46-3cce-45a6-b6f6-9056285c2ff1","access_rights":{"id":"3168c8d9-a9f4-4a58-8139-066d41883a6e","license":[{"id":"fc8a7008-cf5e-4df1-9e05-0145d445c80e","custom_url":"http://urn.fi/urn:nbn:fi:lb-2017030602","url":"http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"CLARIN RES (Restricted) End-User License 1.0"}}],"access_type":{"id":"6311561d-0b53-460b-9fb9-1852ce0761eb","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Restricted use","fi":"Saatavuutta rajoitettu"}},"restriction_grounds":[{"id":"41b4ff93-e15e-4829-8553-49e4ef079d69","url":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other","in_scheme":"http://uri.suomi.fi/codelist/fairdata/restriction_grounds","pref_label":{"en":"Restricted access due to other reasons","fi":"Saatavuutta rajoitettu muulla perusteella","sv":"Begränsad åtkomst av övriga skäl"}}]},"actors":[{"id":"42007ff3-fae8-4ed8-88c6-c900cd9fba93","roles":["creator"],"person":{"id":"9fb2e96b-74a2-452e-9321-cdd567ccaf6d","name":"Pentti Leino","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"8c128b56-a0d1-4281-8c8d-56406b5d81c4","roles":["publisher"],"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"a2eb16d1-8327-4c95-bd0c-368d612150fa","roles":["curator"],"person":{"id":"f9c4864b-4206-474a-87ca-b8372f5852be","name":"Mari Siiroinen","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}},{"id":"8f18ceab-4669-4478-b388-2f1c6b797a62","roles":["rights_holder"],"organization":{"id":"073fe51f-5b84-4291-961b-27ac0dc9eeed","pref_label":{"en":"The Matriculation Examination Board"},"homepage":{"url":"https://www.ylioppilastutkinto.fi/fi/english"},"email":""}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"en":"The corpus, containing Finnish essays written by the students of the 1994, 1999 and 2004 matriculation examinations, is available at korp.csc.fi. \n\nLicense information: http://urn.fi/urn:nbn:fi:lb-2017030602 (in Finnish: http://urn.fi/urn:nbn:fi:lb-2017030601)."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2017030301","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Corpus of Finnish Matriculation Examination Essays from 1994, 1999 and 2004","fi":"1994, 1999 ja 2004 äidinkielen ylioppilaskokeiden esseitä sisältävä korpus"},"created":"2022-11-17T00:00:00Z","modified":"2024-06-19T07:53:21Z","dataset_versions":[{"id":"03613a46-3cce-45a6-b6f6-9056285c2ff1","title":{"en":"Corpus of Finnish Matriculation Examination Essays from 1994, 1999 and 2004","fi":"1994, 1999 ja 2004 äidinkielen ylioppilaskokeiden esseitä sisältävä korpus"},"persistent_identifier":"urn:nbn:fi:lb-2017030301","state":"published","created":"2022-11-17T00:00:00Z","version":1}],"published_revision":13,"version":1,"api_version":3,"metadata_repository":"Fairdata"},{"id":"7361f52f-4dd0-4e6c-b5b6-56266ab281f7","access_rights":{"id":"e011b2f1-bc40-4af4-8bc3-25b75fda80e1","license":[{"id":"64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9","url":"http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0","in_scheme":"http://uri.suomi.fi/codelist/fairdata/license","pref_label":{"en":"Creative Commons Attribution 1.0 Generic (CC BY 1.0)","fi":"Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"}}],"access_type":{"id":"b41462f7-00bf-4e50-935b-2bf1184453a7","url":"http://uri.suomi.fi/codelist/fairdata/access_type/code/open","in_scheme":"http://uri.suomi.fi/codelist/fairdata/access_type","pref_label":{"en":"Open","fi":"Avoin"}},"restriction_grounds":[]},"actors":[{"id":"2e0d9a06-6387-47b1-bbfb-400b8647aca9","roles":["creator","curator","publisher","rights_holder"],"person":{"id":"1564b4d6-88c9-47a7-9a84-fa344c4411c1","name":"Mietta Lennes","email":""},"organization":{"id":"a5f4935c-4c0e-44f6-a7d6-71b946913649","pref_label":{"en":"University of Helsinki","fi":"Helsingin yliopisto","sv":"Helsingfors universitet","und":"Helsingin yliopisto"},"url":"http://uri.suomi.fi/codelist/fairdata/organization/code/01901","in_scheme":"http://uri.suomi.fi/codelist/fairdata/organization"}}],"cumulative_state":0,"data_catalog":"urn:nbn:fi:att:data-catalog-harvest-kielipankki","description":{"fi":"Aineisto sisältää puheen analyysimenetelmien opiskeluun ja harjoitteluun tarkoitettua suomenkielistä äänimateriaalia: ääneen luettuja sanoja, lauseita ja tarinoita. Aineisto on äänitetty ja valmisteltavana Kielipankin latauspalvelua varten. Yksittäisiä aineistoon kuuluvia osia on julkaistu Kielipankin verkkosivuilla ja puheen analyysin oppimateriaalien yhteydessä (sekä Kielipankin käytöstä poistuneessa LAT-palvelussa sijaintitunnisteella http://urn.fi/urn:nbn:fi:lb-100110018959). \n\nKoko aineisto tulee myöhemmin Kielipankin kautta saataville Creative Commons Nimeä -lisenssin uusimmalla versiolla. Aineistoa tai sen osia käytettäessä pitää mainita aineiston nimi ja pysyvä tunniste."},"field_of_science":[{"id":"f7ee5ba6-f6af-48d0-bb0f-ea26851256d2","url":"http://www.yso.fi/onto/okm-tieteenala/ta6121","in_scheme":"http://www.yso.fi/onto/okm-tieteenala/conceptscheme","pref_label":{"en":"Languages","fi":"Kielitieteet","sv":"Språkvetenskaper"}}],"infrastructure":[],"keyword":[],"language":[{"id":"b0c7eada-5b22-48b8-86c2-16e996ca2681","url":"http://lexvo.org/id/iso639-3/fin","in_scheme":"http://lexvo.org/id/","pref_label":{"en":"Finnish","fi":"suomi","sv":"finska"}}],"metadata_owner":{"id":"003e43bb-cfd5-43a5-92c8-1a6cbec7f76c","organization":"service_kielipankki"},"other_identifiers":[],"persistent_identifier":"urn:nbn:fi:lb-2016022401","pid_generated_by_fairdata":false,"projects":[],"provenance":[],"relation":[],"remote_resources":[],"spatial":[],"state":"published","temporal":[],"theme":[],"title":{"en":"Learning material for speech analysis: Sample recordings","fi":"Puheen analyysin oppimateriaalin näytetallenteet"},"created":"2023-04-05T00:00:00Z","modified":"2024-06-19T07:42:57Z","dataset_versions":[{"id":"7361f52f-4dd0-4e6c-b5b6-56266ab281f7","title":{"en":"Learning material for speech analysis: Sample recordings","fi":"Puheen analyysin oppimateriaalin näytetallenteet"},"persistent_identifier":"urn:nbn:fi:lb-2016022401","state":"published","created":"2023-04-05T00:00:00Z","version":1}],"published_revision":14,"version":1,"api_version":3,"metadata_repository":"Fairdata"}]}