{"id":"https://openalex.org/W4415433581","doi":"https://doi.org/10.21437/interspeech.2025-720","title":"Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use","display_name":"Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433581","doi":"https://doi.org/10.21437/interspeech.2025-720"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-720","doi":"https://doi.org/10.21437/interspeech.2025-720","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-720","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.21578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089505434","display_name":"Titouan Parcollet","orcid":"https://orcid.org/0000-0003-0672-1346","observed_orcids":["https://orcid.org/0000-0003-0672-1346"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Titouan Parcollet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088360278","display_name":"Yuan Tseng","orcid":"https://orcid.org/0009-0003-7719-363X","observed_orcids":["https://orcid.org/0009-0003-7719-363X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Tseng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003030422","display_name":"Shucong Zhang","orcid":"https://orcid.org/0009-0000-8299-8481","observed_orcids":["https://orcid.org/0009-0000-8299-8481"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shucong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024696072","display_name":"Rogier C. van Dalen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rogier C. van Dalen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8993,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86991477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4053","last_page":"4057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00039999998989515007,"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/T12031","display_name":"Speech and dialogue systems","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8259999752044678},{"id":"https://openalex.org/keywords/english-speech","display_name":"English speech","score":0.5600000023841858},{"id":"https://openalex.org/keywords/speech-transcription","display_name":"speech transcription","score":0.4830000102519989},{"id":"https://openalex.org/keywords/conversational-speech","display_name":"conversational speech","score":0.6439999938011169},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"speech corpus","score":0.5910000205039978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5777999758720398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5213000178337097},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4586000144481659},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-720","doi":"https://doi.org/10.21437/interspeech.2025-720","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-720","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.21578","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.21578","pdf_url":"https://arxiv.org/pdf/2505.21578","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2505.21578","doi":"https://doi.org/10.48550/arxiv.2505.21578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.21578","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.21578","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.21578","pdf_url":"https://arxiv.org/pdf/2505.21578","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3184414142","https://openalex.org/W7117151587","https://openalex.org/W2405083174","https://openalex.org/W7161737243","https://openalex.org/W3095410713","https://openalex.org/W4402111220","https://openalex.org/W2250319793","https://openalex.org/W4372341945","https://openalex.org/W4220810509","https://openalex.org/W4408355549"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,114],"recognition":[2],"(ASR)":[3],"research":[4],"is":[5,31,124],"driven":[6],"by":[7,34],"the":[8,70,80,88,121,133],"availability":[9],"of":[10,82,95,102,104,113],"common":[11],"datasets":[12],"between":[13],"industrial":[14],"researchers":[15,68,131],"and":[16,20,37,109,130],"academics,":[17],"encouraging":[18],"comparisons":[19],"evaluations.":[21],"LibriSpeech,":[22],"despite":[23],"its":[24,35],"long":[25],"success":[26],"as":[27],"an":[28],"ASR":[29,137],"benchmark,":[30],"now":[32],"limited":[33],"size":[36],"focus":[38],"on":[39],"clean,":[40,119],"read":[41],"speech,":[42],"leading":[43],"to":[44,126,135],"near-zero":[45],"word":[46],"error":[47],"rates.":[48],"More":[49],"recent":[50],"datasets,":[51],"including":[52,65],"MOSEL,":[53],"YODAS,":[54],"Gigaspeech,":[55],"OWSM,":[56],"Libriheavy":[57],"or":[58,79],"People's":[59],"Speech":[60],"suffer":[61],"from":[62],"major":[63],"limitations":[64],"licenses":[66],"that":[67],"in":[69,132,139],"industry":[71,134],"cannot":[72],"use,":[73],"unreliable":[74],"transcriptions,":[75],"incorrect":[76],"audio":[77],"data,":[78],"lack":[81],"evaluation":[83],"sets.":[84],"This":[85],"work":[86,127],"presents":[87],"Loquacious":[89,122],"Set,":[90],"a":[91,110],"25,000-hour":[92],"curated":[93],"collection":[94],"commercially":[96],"usable":[97],"English":[98],"speech.":[99],"Featuring":[100],"hundreds":[101],"thousands":[103],"speakers":[105],"with":[106],"diverse":[107],"accents":[108],"wide":[111],"range":[112],"types":[115],"(read,":[116],"spontaneous,":[117],"talks,":[118],"noisy),":[120],"Set":[123],"designed":[125],"for":[128],"academics":[129],"build":[136],"systems":[138],"real-world":[140],"scenarios.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-24T00:00:00"}