{"id":"https://openalex.org/W4375869413","doi":"https://doi.org/10.1109/icassp49357.2023.10096876","title":"Speech Separation with Large-Scale Self-Supervised Learning","display_name":"Speech Separation with Large-Scale Self-Supervised Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869413","doi":"https://doi.org/10.1109/icassp49357.2023.10096876"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096876","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/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":true,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft,Redmond,USA","Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, 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,Redmond,USA","Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, 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,Redmond,USA","Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324098","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-1680-8253"},"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":"Yu Wu","raw_affiliation_strings":["Microsoft,Redmond,USA","Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363470","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-7223-1030"},"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,Redmond,USA","Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, 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,Redmond,USA","Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, 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,Redmond,USA","Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113968312","display_name":"Sunit Sivasankaran","orcid":null},"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":"Sunit Sivasankaran","raw_affiliation_strings":["Microsoft,Redmond,USA","Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"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":"Sefik Emre Eskimez","raw_affiliation_strings":["Microsoft,Redmond,USA","Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100345092"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.7379,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87307785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.7838314771652222},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5916458368301392},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5401737689971924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5200138092041016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4844672679901123},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4696711003780365},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45788490772247314},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4513784646987915},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4246673583984375},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.421461820602417},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4177761673927307},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41365569829940796},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37003397941589355},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36958348751068115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.361184298992157},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14645031094551086},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07065293192863464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838314771652222},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5916458368301392},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5401737689971924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5200138092041016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4844672679901123},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4696711003780365},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45788490772247314},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4513784646987915},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4246673583984375},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.421461820602417},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4177761673927307},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41365569829940796},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37003397941589355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36958348751068115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.361184298992157},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14645031094551086},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07065293192863464},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096876","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":0.5099999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1591607137","https://openalex.org/W2117678320","https://openalex.org/W2125336414","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2726515241","https://openalex.org/W2757672955","https://openalex.org/W2803322398","https://openalex.org/W2808631503","https://openalex.org/W2889503488","https://openalex.org/W2939246703","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W3008283340","https://openalex.org/W3015199127","https://openalex.org/W3030437843","https://openalex.org/W3093839391","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W3175898847","https://openalex.org/W3178203035","https://openalex.org/W3181056718","https://openalex.org/W3194687854","https://openalex.org/W3206116612","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224933800","https://openalex.org/W4225096077","https://openalex.org/W4225632569","https://openalex.org/W4285250921","https://openalex.org/W4292969786","https://openalex.org/W4372271367","https://openalex.org/W4385245566","https://openalex.org/W6678809451","https://openalex.org/W6739901393","https://openalex.org/W6744711567","https://openalex.org/W6771467084","https://openalex.org/W6771611251","https://openalex.org/W6784499681","https://openalex.org/W6797992114","https://openalex.org/W6842384739","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2032826752","https://openalex.org/W2142815029","https://openalex.org/W1999699871","https://openalex.org/W2145230572","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2146197305","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2166312020"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"methods":[3],"such":[4],"as":[5],"WavLM":[6],"have":[7],"shown":[8],"promising":[9],"speech":[10,128,141],"separation":[11],"(SS)":[12],"results":[13],"in":[14],"small-scale":[15],"simulation-based":[16],"experiments.":[17],"In":[18],"this":[19],"work,":[20],"we":[21],"extend":[22],"the":[23,26,34,54,58,81,84,93,102,143,155,168],"exploration":[24],"of":[25,83,116,150],"SSL-based":[27],"SS":[28,59,95],"by":[29,171],"massively":[30],"scaling":[31],"up":[32],"both":[33],"pre-training":[35],"data":[36,43],"(more":[37],"than":[38],"300K":[39],"hours)":[40],"and":[41,75,92,114,148,161],"fine-tuning":[42,77],"(10K":[44],"hours).":[45],"We":[46],"also":[47],"investigate":[48],"various":[49],"techniques":[50],"to":[51],"efficiently":[52],"integrate":[53],"pre-trained":[55,85],"model":[56,72,96,111,145],"with":[57,88,101],"network":[60],"under":[61],"a":[62,67,76,89,125],"limited":[63],"computation":[64],"budget,":[65],"including":[66],"low":[68],"frame":[69],"rate":[70,120],"SSL":[71],"training":[73],"setup":[74],"scheme":[78],"using":[79,97,139],"only":[80],"part":[82],"model.":[86],"Compared":[87],"supervised":[90,157],"baseline":[91,158],"WavLM-based":[94],"feature":[98],"embeddings":[99],"obtained":[100],"previously":[103],"released":[104],"94K":[105],"hours":[106],"trained":[107],"WavLM,":[108],"our":[109],"proposed":[110,144],"obtains":[112],"15.9%":[113],"11.2%":[115],"relative":[117,151],"word":[118],"error":[119],"(WER)":[121],"reductions,":[122],"respectively,":[123,165],"for":[124],"simulated":[126],"far-field":[127],"mixture":[129],"test":[130],"set.":[131],"For":[132],"conversation":[133],"transcription":[134],"on":[135,159],"real":[136],"meeting":[137],"recordings":[138],"continuous":[140],"separation,":[142],"achieves":[146],"6.8%":[147],"10.6%":[149],"WER":[152],"reductions":[153],"over":[154],"purely":[156],"AMI":[160],"ICSI":[162],"evaluation":[163],"sets,":[164],"while":[166],"reducing":[167],"computational":[169],"cost":[170],"38%.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}