{"id":"https://openalex.org/W4372267974","doi":"https://doi.org/10.1109/icassp49357.2023.10094606","title":"Self-Supervised Learning-Based Source Separation for Meeting Data","display_name":"Self-Supervised Learning-Based Source Separation for Meeting Data","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267974","doi":"https://doi.org/10.1109/icassp49357.2023.10094606"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094606","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094606","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/A5032504077","display_name":"Yuang Li","orcid":"https://orcid.org/0000-0002-2244-0184"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuang Li","raw_affiliation_strings":["Cambridge University Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013736436","display_name":"Xianrui Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xianrui Zheng","raw_affiliation_strings":["Cambridge University Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":["Cambridge University Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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/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":0.9994000196456909,"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":0.8043792247772217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6463296413421631},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5349491834640503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5276429057121277},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5214906930923462},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5122696757316589},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5072309970855713},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.449990451335907},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4143044352531433},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0820985734462738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043792247772217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6463296413421631},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5349491834640503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5276429057121277},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5214906930923462},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5122696757316589},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5072309970855713},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.449990451335907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4143044352531433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0820985734462738},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094606","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094606","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W2030486566","https://openalex.org/W2117678320","https://openalex.org/W2166637769","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2891833136","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2972541922","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3016232124","https://openalex.org/W3027008958","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3093839391","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3143367551","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W3197580070","https://openalex.org/W3198771897","https://openalex.org/W3206116612","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224933800","https://openalex.org/W4224951806","https://openalex.org/W4285044984","https://openalex.org/W6777776875","https://openalex.org/W6780218876","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W2594778474","https://openalex.org/W2944183083","https://openalex.org/W3104453097","https://openalex.org/W200981350","https://openalex.org/W4386907265","https://openalex.org/W2058752985","https://openalex.org/W2293740626","https://openalex.org/W2763412546","https://openalex.org/W1499712254","https://openalex.org/W2915347927"],"abstract_inverted_index":{"Source":[0],"separation":[1,96],"can":[2],"improve":[3,73],"automatic":[4,62],"speech":[5],"recognition":[6],"(ASR)":[7],"under":[8],"multi-party":[9],"meeting":[10],"scenarios":[11],"by":[12],"extracting":[13],"single-speaker":[14],"signals":[15],"from":[16],"overlapped":[17],"speech.":[18],"Despite":[19],"the":[20,56,84,91,129],"success":[21],"of":[22,109,123],"self-supervised":[23],"learning":[24],"models":[25,42],"in":[26,90,113],"single-channel":[27],"source":[28,69,95],"separation,":[29],"most":[30],"studies":[31],"have":[32],"focused":[33],"on":[34,45,104,128],"simulated":[35,47],"setups.":[36],"In":[37],"this":[38],"paper,":[39],"seven":[40],"SSL":[41],"were":[43,126],"compared":[44],"both":[46],"and":[48,111,132],"real-world":[49,74],"corpora.":[50],"Then,":[51],"we":[52],"propose":[53],"to":[54,83],"integrate":[55],"best-performing":[57],"model":[58,102],"WavLM":[59],"into":[60],"an":[61,100,120],"transcription":[63,92],"system":[64,93],"through":[65],"a":[66],"novel":[67],"iterative":[68],"selection":[70],"method.":[71],"To":[72],"performance,":[75],"time-domain":[76],"unsupervised":[77],"mixture":[78],"invariant":[79],"training":[80],"was":[81,97],"adapted":[82],"time-frequency":[85],"domain.":[86],"Experiments":[87],"showed":[88],"that":[89],"when":[94],"inserted":[98],"before":[99],"ASR":[101],"fine-tuned":[103],"separated":[105],"speech,":[106],"absolute":[107],"reductions":[108],"1.9%":[110],"1.5%":[112],"concatenated":[114],"minimum-permutation":[115],"word":[116],"error":[117],"rate":[118],"for":[119],"unknown":[121],"number":[122],"speakers":[124],"(cpWER-us)":[125],"observed":[127],"AMI":[130],"dev":[131],"test":[133],"sets.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}