{"id":"https://openalex.org/W4386763469","doi":"https://doi.org/10.1109/waspaa58266.2023.10248096","title":"Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation","display_name":"Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386763469","doi":"https://doi.org/10.1109/waspaa58266.2023.10248096"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5042385500","display_name":"Yoshiki Masuyama","orcid":"https://orcid.org/0000-0002-5881-0474"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yoshiki Masuyama","raw_affiliation_strings":["Tokyo Metropolitan University,Japan","Tokyo Metropolitan University, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Japan","institution_ids":["https://openalex.org/I69740276"]},{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Samuele Cornell","raw_affiliation_strings":["Università Politecnica Delle Marche,Italy"],"affiliations":[{"raw_affiliation_string":"Università Politecnica Delle Marche,Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Tokyo Metropolitan University,Japan","Tokyo Metropolitan University, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Japan","institution_ids":["https://openalex.org/I69740276"]},{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5042385500"],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":1.6213,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84795395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.998199999332428,"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":0.7826094627380371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7537034153938293},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5375573039054871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5003938674926758},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49677830934524536},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.49471065402030945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45493704080581665},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4327498972415924},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.43182235956192017},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4209045469760895},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42046549916267395},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.31291577219963074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09566736221313477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826094627380371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7537034153938293},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5375573039054871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5003938674926758},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49677830934524536},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.49471065402030945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45493704080581665},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4327498972415924},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.43182235956192017},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4209045469760895},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42046549916267395},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.31291577219963074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09566736221313477},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/waspaa58266.2023.10248096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2127851351","https://openalex.org/W2130361043","https://openalex.org/W2221409856","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2506203739","https://openalex.org/W2517616541","https://openalex.org/W2526425061","https://openalex.org/W2568308529","https://openalex.org/W2622203030","https://openalex.org/W2640112133","https://openalex.org/W2803322398","https://openalex.org/W2891616026","https://openalex.org/W2892163332","https://openalex.org/W2921496354","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2995166068","https://openalex.org/W3008762051","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3032969657","https://openalex.org/W3094821064","https://openalex.org/W3094831814","https://openalex.org/W3096073522","https://openalex.org/W3099330747","https://openalex.org/W3126427729","https://openalex.org/W3163217847","https://openalex.org/W3163652268","https://openalex.org/W3197580070","https://openalex.org/W3207558756","https://openalex.org/W3209059054","https://openalex.org/W3209490467","https://openalex.org/W3209984917","https://openalex.org/W4210402803","https://openalex.org/W4224936432","https://openalex.org/W4225310539","https://openalex.org/W4226390724","https://openalex.org/W4285250921","https://openalex.org/W4297841651","https://openalex.org/W4312356750","https://openalex.org/W4319862214","https://openalex.org/W4385756463","https://openalex.org/W6735168207","https://openalex.org/W6780218876","https://openalex.org/W6786197189"],"related_works":["https://openalex.org/W2963170046","https://openalex.org/W2186375278","https://openalex.org/W2499802997","https://openalex.org/W4255044973","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2464377622","https://openalex.org/W2914064142","https://openalex.org/W2394963835"],"abstract_inverted_index":{"Neural":[0],"speech":[1,12,30,104],"separation":[2,31,46,105],"has":[3],"made":[4],"remarkable":[5],"progress":[6],"and":[7,34,50,78,106,118,139],"its":[8],"integration":[9,112,141],"with":[10,86,108],"automatic":[11],"recognition":[13,81,93,107],"(ASR)":[14],"is":[15],"an":[16,26,38,134],"important":[17],"direction":[18],"towards":[19],"realizing":[20],"multi-speaker":[21,92],"ASR.":[22],"This":[23],"work":[24],"provides":[25],"insightful":[27],"investigation":[28],"of":[29],"in":[32,62,127],"reverberant":[33,128],"noisy-reverberant":[35],"scenarios":[36],"as":[37,54,56,75],"ASR":[39,64],"front-end.":[40],"In":[41],"detail,":[42],"we":[43,95],"explore":[44],"multi-channel":[45],"methods,":[47],"mask-based":[48,136],"beamforming":[49,138],"complex":[51,115],"spectral":[52,116],"mapping,":[53],"well":[55],"the":[57,63,69,80,84],"best":[58],"features":[59],"to":[60],"use":[61],"back-end":[65],"model.":[66],"We":[67],"employ":[68],"recent":[70],"self-supervised":[71],"learning":[72],"representation":[73],"(SSLR)":[74],"a":[76,97,122],"feature":[77],"improve":[79,91],"performance":[82],"from":[83],"case":[85],"filterbank":[87,140],"features.":[88],"To":[89],"further":[90],"performance,":[94],"present":[96],"carefully":[98],"designed":[99],"training":[100],"strategy":[101],"for":[102],"integrating":[103],"SSLR.":[109],"The":[110],"proposed":[111],"using":[113],"TF-GridNet-based":[114],"mapping":[117],"WavLM-based":[119],"SSLR":[120],"achieves":[121],"2.5%":[123],"word":[124],"error":[125],"rate":[126],"WHAMR!":[129],"test":[130],"set,":[131],"significantly":[132],"outperforming":[133],"existing":[135],"MVDR":[137],"(28.9%).":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}