{"id":"https://openalex.org/W4391021698","doi":"https://doi.org/10.1109/asru57964.2023.10389689","title":"Yodas: Youtube-Oriented Dataset for Audio and Speech","display_name":"Yodas: Youtube-Oriented Dataset for Audio and Speech","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021698","doi":"https://doi.org/10.1109/asru57964.2023.10389689"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinjian Li","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055644612","display_name":"William Chen","orcid":"https://orcid.org/0000-0001-8924-5853"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Chen","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067910092","display_name":"Sayaka Shiota","orcid":"https://orcid.org/0000-0002-2364-068X"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sayaka Shiota","raw_affiliation_strings":["Tokyo Metropolitan University,Japan","Tokyo Metropolitan University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Japan","institution_ids":["https://openalex.org/I69740276"]},{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1416,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94786785,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8479268550872803},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.5843332409858704},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5304645299911499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5128695964813232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.50144362449646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5004880428314209},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.4386335015296936},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.42024940252304077},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4121546447277069},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3128298819065094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8479268550872803},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.5843332409858704},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5304645299911499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5128695964813232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50144362449646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5004880428314209},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.4386335015296936},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.42024940252304077},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4121546447277069},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3128298819065094},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2143612262","https://openalex.org/W2407080277","https://openalex.org/W2520160253","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2937197076","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963979492","https://openalex.org/W2995181338","https://openalex.org/W3015877095","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3043783436","https://openalex.org/W3095410713","https://openalex.org/W3139878283","https://openalex.org/W3197580070","https://openalex.org/W3201357245","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4226502599","https://openalex.org/W4281492411","https://openalex.org/W4319862635","https://openalex.org/W4323066695","https://openalex.org/W4378105483","https://openalex.org/W4388017359","https://openalex.org/W6675365184","https://openalex.org/W6679436768","https://openalex.org/W6696449567","https://openalex.org/W6727336983","https://openalex.org/W6757817989","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6801684963","https://openalex.org/W6810629572","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2036021480","https://openalex.org/W2546377002","https://openalex.org/W22571951","https://openalex.org/W2046541848","https://openalex.org/W4384009753","https://openalex.org/W2791776396","https://openalex.org/W4286531993","https://openalex.org/W2964820744","https://openalex.org/W4247858078","https://openalex.org/W2378944243"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,99,112],"introduce":[4,83],"YODAS":[5,60],"(YouTube-Oriented":[6],"Dataset":[7],"for":[8,56,88],"Audio":[9],"and":[10,33,72],"Speech),":[11],"a":[12,78,101],"large-scale,":[13],"multilingual":[14],"dataset":[15,68,96],"comprising":[16],"currently":[17],"over":[18,118],"500k":[19],"hours":[20],"of":[21,69,104],"speech":[22,36,95,115],"data":[23],"in":[24],"more":[25],"than":[26],"100":[27],"languages,":[28],"sourced":[29],"from":[30],"both":[31],"labeled":[32,39],"unlabeled":[34,52],"YouTube":[35],"datasets.":[37],"The":[38],"subsets,":[40],"including":[41],"manual":[42],"or":[43],"automatic":[44],"subtitles,":[45],"facilitate":[46],"supervised":[47],"model":[48],"training.":[49],"Conversely,":[50],"the":[51,64,84,93,109,114,119],"subsets":[53],"are":[54],"apt":[55],"self-supervised":[57],"learning":[58],"applications.":[59],"is":[61],"distinctive":[62],"as":[63],"first":[65],"publicly":[66],"available":[67],"its":[70],"scale,":[71],"it":[73],"will":[74],"be":[75],"distributed":[76],"under":[77],"Creative":[79],"Commons":[80],"license.":[81],"We":[82],"collection":[85],"methodology":[86],"utilized":[87],"YODAS,":[89],"which":[90],"contributes":[91],"to":[92],"large-scale":[94],"construction.":[97],"Subsequently,":[98],"provide":[100],"comprehensive":[102],"analysis":[103],"speech,":[105],"text":[106],"contained":[107],"within":[108],"dataset.":[110],"Finally,":[111],"describe":[113],"recognition":[116],"baselines":[117],"top-15":[120],"languages.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
