{"id":"https://openalex.org/W4372342485","doi":"https://doi.org/10.1109/icassp49357.2023.10097139","title":"Adapting Self-Supervised Models to Multi-Talker Speech Recognition Using Speaker Embeddings","display_name":"Adapting Self-Supervised Models to Multi-Talker Speech Recognition Using Speaker Embeddings","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372342485","doi":"https://doi.org/10.1109/icassp49357.2023.10097139"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101619225","display_name":"Zili Huang","orcid":"https://orcid.org/0000-0003-1238-8017"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zili Huang","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA","Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004777817","display_name":"Desh Raj","orcid":"https://orcid.org/0000-0002-5038-9400"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Desh Raj","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA","Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paola Garc\u00eda","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA","Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA","Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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":0.8184365034103394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7040390968322754},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5242507457733154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5204761028289795},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4575539827346802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.453662246465683},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4307454228401184},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4298713207244873},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4277578294277191},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4196305274963379},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41913938522338867},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.41008222103118896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3971225619316101},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.373362272977829}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184365034103394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7040390968322754},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5242507457733154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5204761028289795},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4575539827346802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453662246465683},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4307454228401184},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4298713207244873},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4277578294277191},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4196305274963379},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41913938522338867},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.41008222103118896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3971225619316101},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.373362272977829},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W2125336414","https://openalex.org/W2127141656","https://openalex.org/W2150769028","https://openalex.org/W2294798173","https://openalex.org/W2402146185","https://openalex.org/W2460742184","https://openalex.org/W2726515241","https://openalex.org/W2760103357","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2891833136","https://openalex.org/W2951130829","https://openalex.org/W2963420686","https://openalex.org/W2973062255","https://openalex.org/W2995181338","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3027008958","https://openalex.org/W3035725276","https://openalex.org/W3036601975","https://openalex.org/W3087148478","https://openalex.org/W3119308075","https://openalex.org/W3175898847","https://openalex.org/W3181056718","https://openalex.org/W3197580070","https://openalex.org/W3198275944","https://openalex.org/W3198694222","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226390724","https://openalex.org/W4281492411","https://openalex.org/W6678809451","https://openalex.org/W6682600690","https://openalex.org/W6775537894","https://openalex.org/W6777776875","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6782990278"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W1521049138","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"methods":[3],"which":[4,40,108],"learn":[5],"representations":[6],"of":[7,55,135,154],"data":[8],"without":[9],"explicit":[10],"supervision":[11],"have":[12,26],"gained":[13],"popularity":[14],"in":[15,114],"speech-processing":[16],"tasks,":[17],"particularly":[18],"for":[19,29,45,96,142,157],"single-talker":[20],"applications.":[21,47],"However,":[22],"these":[23],"models":[24,58,156,170],"often":[25],"degraded":[27],"performance":[28],"multi-talker":[30,61],"scenarios":[31],"\u2014":[32,39],"possibly":[33],"due":[34],"to":[35,59,92],"the":[36,53,60,115,143,152,164],"domain":[37],"mismatch":[38],"severely":[41],"limits":[42],"their":[43,118],"use":[44],"such":[46],"In":[48],"this":[49],"paper,":[50],"we":[51,76,99,125],"investigate":[52],"adaptation":[54],"upstream":[56],"SSL":[57],"automatic":[62],"speech":[63],"recognition":[64],"(ASR)":[65],"task":[66],"under":[67],"two":[68],"conditions.":[69],"First,":[70],"when":[71],"segmented":[72,144],"utterances":[73],"are":[74,171],"given,":[75],"show":[77,126],"that":[78,127],"adding":[79],"a":[80,101],"target":[81],"speaker":[82,104,129],"extraction":[83],"(TSE)":[84],"module":[85],"based":[86],"on":[87,123,163,173],"enrollment":[88],"embeddings":[89,130],"is":[90],"complementary":[91],"mixture-aware":[93],"pre-training.":[94],"Second,":[95],"unsegmented":[97,146],"mixtures,":[98],"propose":[100],"novel":[102],"joint":[103],"modeling":[105],"(JSM)":[106],"approach,":[107],"aggregates":[109],"information":[110],"from":[111],"all":[112],"speakers":[113],"mixture":[116],"through":[117,161],"embeddings.":[119],"With":[120],"controlled":[121],"experiments":[122,162],"Libri2Mix,":[124],"using":[128],"provides":[131],"relative":[132],"WER":[133],"improvements":[134],"9.1%":[136],"and":[137,145,169],"42.1%":[138],"over":[139],"strong":[140],"baselines":[141],"cases,":[147],"respectively.":[148],"We":[149],"also":[150],"demonstrate":[151],"effectiveness":[153],"our":[155],"real":[158],"conversational":[159],"mixtures":[160],"AMI":[165],"dataset.":[166],"Our":[167],"code":[168],"open-sourced":[172],"https://github.com/HuangZiliAndy/SSL_for_multitalker.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}