{"id":"https://openalex.org/W4372348115","doi":"https://doi.org/10.1109/icassp49357.2023.10094787","title":"Self-Supervised Learning with Bi-Label Masked Speech Prediction for Streaming Multi-Talker Speech Recognition","display_name":"Self-Supervised Learning with Bi-Label Masked Speech Prediction for Streaming Multi-Talker Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348115","doi":"https://doi.org/10.1109/icassp49357.2023.10094787"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094787","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":"article","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":true,"raw_author_name":"Zili Huang","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377935","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0002-5932-4371"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005333910","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-8482-6138"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peidong Wang","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101619225"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.6952,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74727876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.8402202129364014},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7123009562492371},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5302726030349731},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.509369969367981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4840035140514374},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4827539324760437},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.455305278301239},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4103754758834839},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3944155275821686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402202129364014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7123009562492371},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5302726030349731},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.509369969367981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4840035140514374},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4827539324760437},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.455305278301239},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4103754758834839},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3944155275821686},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094787","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W2460742184","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W3000358149","https://openalex.org/W3016010032","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3094821064","https://openalex.org/W3112034174","https://openalex.org/W3116025434","https://openalex.org/W3161873870","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3198275944","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211278025","https://openalex.org/W4226491018","https://openalex.org/W4281492411","https://openalex.org/W4283324001","https://openalex.org/W4297808394","https://openalex.org/W6718827390","https://openalex.org/W6775489429","https://openalex.org/W6780218876","https://openalex.org/W6784418856","https://openalex.org/W6786669483"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2081671587","https://openalex.org/W1151175420","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL),":[2],"which":[3,53,100],"utilizes":[4],"the":[5,24,79,115,135],"input":[6],"data":[7,119],"itself":[8],"for":[9,16,39,48],"representation":[10,81],"learning,":[11],"has":[12],"achieved":[13],"state-of-the-art":[14],"results":[15],"various":[17,112],"downstream":[18],"speech":[19,51,98],"tasks.":[20],"However,":[21],"most":[22],"of":[23,56,82,104,114],"previous":[25],"studies":[26],"focused":[27],"on":[28,74,134],"offline":[29],"single-talker":[30],"applications,":[31],"with":[32],"limited":[33],"investigations":[34],"in":[35,59,107],"multi-talker":[36,50],"cases,":[37],"especially":[38],"streaming":[40,49,61],"scenarios.":[41],"In":[42],"this":[43,75],"paper,":[44],"we":[45,64],"investigate":[46,111],"SSL":[47,68,90,126],"recognition,":[52],"generates":[54],"transcriptions":[55],"overlapping":[57,83,108],"speakers":[58,106],"a":[60,88],"fashion.":[62],"Firstly,":[63],"observe":[65],"that":[66],"conventional":[67],"techniques":[69],"do":[70],"not":[71],"work":[72],"well":[73],"task":[76],"due":[77],"to":[78,94],"poor":[80],"speech.":[84,109],"We":[85,110],"then":[86],"propose":[87],"novel":[89],"training":[91],"objective,":[92],"referred":[93],"as":[95],"bi-label":[96],"masked":[97],"prediction,":[99],"explicitly":[101],"preserves":[102],"representations":[103],"all":[105],"aspects":[113],"proposed":[116,125],"system,":[117],"including":[118],"configuration":[120],"and":[121],"quantizer":[122],"selection.":[123],"The":[124],"setup":[127],"achieves":[128],"substantially":[129],"better":[130],"word":[131],"error":[132],"rates":[133],"LibriSpeechMix":[136],"dataset.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}