{"id":"https://openalex.org/W4226391469","doi":"https://doi.org/10.1007/s10579-022-09606-3","title":"Lahjoita puhetta: a large-scale corpus of spoken Finnish with some benchmarks","display_name":"Lahjoita puhetta: a large-scale corpus of spoken Finnish with some benchmarks","publication_year":2022,"publication_date":"2022-08-09","ids":{"openalex":"https://openalex.org/W4226391469","doi":"https://doi.org/10.1007/s10579-022-09606-3","pmid":"https://pubmed.ncbi.nlm.nih.gov/35965738"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-022-09606-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-022-09606-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-022-09606-3.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-022-09606-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000562801","display_name":"Anssi Moisio","orcid":"https://orcid.org/0000-0002-2018-3524"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Anssi Moisio","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-2018-3524","affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052292328","display_name":"Dejan Porjazovski","orcid":"https://orcid.org/0000-0002-7219-9042"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Dejan Porjazovski","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045737992","display_name":"Aku Rouhe","orcid":"https://orcid.org/0009-0000-0977-609X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Aku Rouhe","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082953089","display_name":"Yaroslav Getman","orcid":"https://orcid.org/0000-0003-4680-8294"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yaroslav Getman","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087875674","display_name":"Anja Virkkunen","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Anja Virkkunen","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ragheb AlGhezi","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ragheb AlGhezi","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mietta Lennes","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mietta Lennes","raw_affiliation_strings":["Department of Digital Humanities, University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Digital Humanities, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058277119","display_name":"Tam\u00e1s Gr\u00f3sz","orcid":"https://orcid.org/0000-0001-7918-9579"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s Gr\u00f3sz","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001408607","display_name":"Krister Lind\u00e9n","orcid":"https://orcid.org/0000-0003-2337-303X"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Krister Lind\u00e9n","raw_affiliation_strings":["Department of Digital Humanities, University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Digital Humanities, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5000562801"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.1387,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52446208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"57","issue":"3","first_page":"1295","last_page":"1327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2320999950170517,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2320999950170517,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.17839999496936798,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.09809999912977219,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8694137930870056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7440137267112732},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.698521077632904},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5638362765312195},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5457266569137573},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5254582166671753},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.44556134939193726},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.44450071454048157},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43373996019363403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38845106959342957},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3577015995979309},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3387588858604431},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32695460319519043},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.12498492002487183},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08690187335014343}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8694137930870056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440137267112732},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.698521077632904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5638362765312195},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5457266569137573},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5254582166671753},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.44556134939193726},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.44450071454048157},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43373996019363403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38845106959342957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3577015995979309},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3387588858604431},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32695460319519043},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.12498492002487183},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08690187335014343},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/s10579-022-09606-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-022-09606-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-022-09606-3.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmid:35965738","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35965738","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language resources and evaluation","raw_type":null},{"id":"pmh:oai:arXiv.org:2203.12906","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.12906","pdf_url":"https://arxiv.org/pdf/2203.12906","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/116866","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/859ff3a4-d919-4e9d-a5aa-1da0d49094e5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},{"id":"pmh:oai:pubmedcentral.nih.gov:9362968","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9362968","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lang Resour Eval","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2203.12906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.12906","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10579-022-09606-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-022-09606-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-022-09606-3.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1536121294","display_name":"Common Language Resources and Technology Infrastructure","funder_award_id":"337073","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G3490526257","display_name":null,"funder_award_id":"337073","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G5721256034","display_name":null,"funder_award_id":"329267","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G7154773589","display_name":null,"funder_award_id":"345790","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G796713724","display_name":null,"funder_award_id":"322625","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G8267031437","display_name":"Understanding speech and scene with ears and eyes","funder_award_id":"345790","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320321394","display_name":"Aalto-Yliopisto","ror":"https://ror.org/020hwjq30"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226391469.pdf","grobid_xml":"https://content.openalex.org/works/W4226391469.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1631260214","https://openalex.org/W1877570817","https://openalex.org/W2053306448","https://openalex.org/W2064675550","https://openalex.org/W2069712814","https://openalex.org/W2115002762","https://openalex.org/W2117621558","https://openalex.org/W2117671523","https://openalex.org/W2120487507","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2166637769","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2402261002","https://openalex.org/W2511234952","https://openalex.org/W2526425061","https://openalex.org/W2735949438","https://openalex.org/W2800045928","https://openalex.org/W2802248956","https://openalex.org/W2890964092","https://openalex.org/W2953412414","https://openalex.org/W2962826786","https://openalex.org/W2962990575","https://openalex.org/W2963341956","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3119308075","https://openalex.org/W3157512577","https://openalex.org/W3186528847","https://openalex.org/W3209059054","https://openalex.org/W3212767696","https://openalex.org/W4304206733","https://openalex.org/W6631362777","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W155019","https://openalex.org/W140362","https://openalex.org/W442490","https://openalex.org/W17150818","https://openalex.org/W2308727","https://openalex.org/W8738421","https://openalex.org/W2195354","https://openalex.org/W8558777","https://openalex.org/W10763016","https://openalex.org/W667520"],"abstract_inverted_index":{"The":[0,25,43,92],"Donate":[1],"Speech":[2],"campaign":[3],"has":[4],"so":[5],"far":[6],"succeeded":[7],"in":[8,143],"gathering":[9],"approximately":[10],"3600":[11],"h":[12],"of":[13,36,46,66,100,104,157],"ordinary,":[14],"colloquial":[15],"Finnish":[16,60],"speech":[17,98],"into":[18],"the":[19,34,47,64,77,81,117,138,155,158],"<i>Lahjoita":[20],"puhetta</i>":[21],"(<i>Donate":[22],"Speech</i>)":[23],"corpus.":[24],"corpus":[26,145,159],"includes":[27],"over":[28],"twenty":[29],"thousand":[30],"speakers":[31],"from":[32,39],"all":[33,40],"regions":[35],"Finland":[37],"and":[38,61,69,80,84,108,110,140,147,152],"age":[41],"brackets.":[42],"primary":[44],"goals":[45],"collection":[48,78],"were":[49],"to":[50,56,62,136,148],"create":[51],"a":[52],"representative,":[53],"large-scale":[54],"resource":[55],"study":[57],"spontaneous":[58,101],"spoken":[59],"accelerate":[63],"development":[65],"language":[67],"technology":[68],"speech-based":[70],"services.":[71],"In":[72],"this":[73,144],"paper,":[74],"we":[75],"present":[76],"process":[79],"collected":[82],"corpus,":[83],"showcase":[85],"its":[86],"versatility":[87],"through":[88],"multiple":[89],"use":[90,94,118,133],"cases.":[91],"evaluated":[93],"cases":[95],"include:":[96],"automatic":[97],"recognition":[99],"speech,":[102],"detection":[103],"age,":[105],"gender,":[106],"dialect":[107],"topic":[109],"metadata":[111,139,151],"analysis.":[112],"We":[113],"provide":[114],"benchmarks":[115],"for":[116,129,154],"cases,":[119],"as":[120],"well":[121],"downloadable,":[122],"trained":[123],"baseline":[124],"systems":[125],"with":[126],"open-source":[127],"code":[128],"reproducibility.":[130],"One":[131],"further":[132],"case":[134],"is":[135,162],"verify":[137],"transcripts":[141,153],"given":[142],"itself,":[146],"suggest":[149],"artificial":[150],"part":[156],"where":[160],"it":[161],"missing.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2022-05-05T00:00:00"}
