{"id":"https://openalex.org/W4226418945","doi":"https://doi.org/10.21437/interspeech.2022-11210","title":"A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings","display_name":"A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226418945","doi":"https://doi.org/10.21437/interspeech.2022-11210"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11210","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11210","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 2022","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/A5100346632","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0003-3147-7269"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777589","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0001-7795-437X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"ShiLiang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019233731","display_name":"Yuxiao Lin","orcid":"https://orcid.org/0000-0002-4194-9525"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxiao Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","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":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"560","last_page":"564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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/T12031","display_name":"Speech and dialogue systems","score":0.9966999888420105,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9775000214576721,"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/computer-science","display_name":"Computer science","score":0.8213450312614441},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8141943216323853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7412114143371582},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5513125658035278},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.5134804844856262},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4758586287498474},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.47209733724594116},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4466271698474884},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43203532695770264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3715443015098572},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34388014674186707},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06792056560516357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213450312614441},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8141943216323853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7412114143371582},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5513125658035278},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.5134804844856262},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4758586287498474},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47209733724594116},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4466271698474884},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43203532695770264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3715443015098572},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34388014674186707},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06792056560516357},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11210","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11210","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W1992908141","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"In":[0,176],"this":[1,34],"paper,":[2],"we":[3,90,121],"conduct":[4],"a":[5,19,42,50,102,129,149],"comparative":[6],"study":[7],"on":[8,148,164],"speaker-attributed":[9,57],"automatic":[10],"speech":[11],"recognition":[12],"(SA-ASR)":[13],"in":[14,24,33],"the":[15,63,81,86,92,118,123,157,173,178,183],"multi-party":[16],"meeting":[17,25,151],"scenario,":[18],"topic":[20],"with":[21,172],"increasing":[22],"attention":[23],"rich":[26],"transcription.":[27],"Specifically,":[28],"three":[29],"approaches":[30],"are":[31,59],"evaluated":[32],"study.":[35],"The":[36,56],"first":[37],"approach,":[38,94,125,145],"FD-SOT,":[39],"consists":[40],"of":[41,110],"frame-level":[43],"diarization":[44,64,104],"model":[45,87],"to":[46,53,80,96],"identify":[47],"speakers":[48],"and":[49,66,133,186],"multi-talker":[51],"ASR":[52,135],"recognize":[54],"utterances.":[55],"transcriptions":[58],"obtained":[60],"by":[61,100],"aligning":[62],"results":[65,147],"recognized":[67],"hypotheses.":[68],"However,":[69],"such":[70,111],"an":[71,134],"alignment":[72,98,113,119],"strategy":[73],"may":[74],"suffer":[75],"from":[76],"erroneous":[77],"timestamps":[78],"due":[79],"modular":[82],"independence,":[83],"severely":[84],"hindering":[85],"performance.":[88],"Therefore,":[89],"propose":[91,122],"second":[93],"WD-SOT,":[95],"address":[97],"errors":[99],"introducing":[101],"word-level":[103],"model,":[105],"which":[106,127],"can":[107],"get":[108],"rid":[109],"timestamp":[112],"dependency.":[114],"To":[115],"further":[116],"mitigate":[117],"issues,":[120],"third":[124],"TS-ASR,":[126],"trains":[128],"target-speaker":[130],"separation":[131],"module":[132,136],"jointly.":[137],"By":[138],"comparing":[139],"various":[140],"strategies":[141],"for":[142],"each":[143],"SA-ASR":[144],"experimental":[146],"real":[150],"scenario":[152],"corpus,":[153],"AliMeeting,":[154],"reveal":[155],"that":[156],"WD-SOT":[158],"approach":[159,180,185],"achieves":[160],"10.7%":[161],"relative":[162,189],"reduction":[163],"averaged":[165],"speaker-dependent":[166],"character":[167],"error":[168],"rate":[169],"(SD-CER),":[170],"compared":[171],"FD-SOT":[174,184],"approach.":[175],"addition,":[177],"TS-ASR":[179],"also":[181],"outperforms":[182],"brings":[187],"16.5%":[188],"average":[190],"SD-CER":[191],"reduction.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}