{"id":"https://openalex.org/W4319586767","doi":"https://doi.org/10.1109/iscslp57327.2022.10037902","title":"Separate-to-Recognize: Joint Multi-target Speech Separation and Speech Recognition for Speaker-attributed ASR","display_name":"Separate-to-Recognize: Joint Multi-target Speech Separation and Speech Recognition for Speaker-attributed ASR","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586767","doi":"https://doi.org/10.1109/iscslp57327.2022.10037902"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037902","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037902","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5022192867","display_name":"Yuxiao Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiao Lin","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["Alibaba Group,Speech Lab,China","Speech Lab, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055433405","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0001-9053-9314"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Alibaba Group,Speech Lab,China","Speech Lab, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Alibaba Group,Speech Lab,China","Speech Lab, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"88","issue":null,"first_page":"150","last_page":"154"},"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":0.9998999834060669,"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":0.9991999864578247,"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":0.8013657927513123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.712165892124176},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5600529313087463},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.558013916015625},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5568368434906006},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5009214878082275},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.49291229248046875},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47454461455345154},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4648973047733307},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4494386613368988},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44415411353111267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4369380474090576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.369838148355484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15972372889518738},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07477611303329468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8013657927513123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.712165892124176},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5600529313087463},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.558013916015625},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5568368434906006},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5009214878082275},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.49291229248046875},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47454461455345154},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4648973047733307},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4494386613368988},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44415411353111267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4369380474090576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.369838148355484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15972372889518738},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07477611303329468},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037902","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037902","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308316","display_name":"Institute for Advanced Study","ror":"https://ror.org/00f809463"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2726515241","https://openalex.org/W2748501745","https://openalex.org/W2760103357","https://openalex.org/W2808631503","https://openalex.org/W2889385246","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2973062255","https://openalex.org/W3008357631","https://openalex.org/W3013139777","https://openalex.org/W3015199127","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3097643313","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3109079702","https://openalex.org/W3163652268","https://openalex.org/W3163793923","https://openalex.org/W3163842642","https://openalex.org/W3212886388","https://openalex.org/W6633847657","https://openalex.org/W6755462816"],"related_works":["https://openalex.org/W2077498359","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805"],"abstract_inverted_index":{"In":[0,52],"this":[1],"paper,":[2],"we":[3,75,132],"propose":[4,107],"a":[5,29,77,108],"joint":[6,103],"framework":[7,19,153],"for":[8,49,102],"speaker-attributed":[9],"automatic":[10],"speech":[11,22,25,36,46,55],"recognition":[12,26],"(SA-ASR)":[13],"task":[14],"named":[15],"Separate-to-Recognize.":[16],"The":[17],"proposed":[18,138],"combines":[20],"multi-target":[21,54,139],"separation":[23,56,72,86,140],"and":[24,38,43,47,106,127,142],"modules":[27,105,117],"into":[28],"single":[30],"end-to-end":[31],"model.":[32,120],"It":[33],"takes":[34],"mixed":[35,58],"utterances":[37],"target-speaker":[39],"embeddings":[40],"as":[41],"input":[42],"predicts":[44],"separated":[45,61],"transcription":[48],"each":[50],"speaker.":[51],"the":[53,63,89,115,134,137],"module,":[57],"speakers":[59],"are":[60],"at":[62],"same":[64],"time,":[65],"which":[66,81],"is":[67],"different":[68,100,124,158],"from":[69,95],"existing":[70],"single-target":[71],"methods.":[73],"Furthermore,":[74],"develop":[76],"dual-path":[78,83,143],"Conformer-based":[79],"separator":[80],"improves":[82],"time":[84],"domain":[85],"by":[87],"utilizing":[88],"modeling":[90],"ability":[91],"of":[92,136],"local":[93],"relationship":[94],"Conformer.":[96],"We":[97],"also":[98,149],"explore":[99],"schemas":[101],"training":[104,109,128],"strategy":[110],"that":[111,151],"can":[112,154],"better":[113],"coordinate":[114],"two":[116],"in":[118,130],"our":[119,152],"By":[121],"comparing":[122],"with":[123],"model":[125],"structures":[126],"strategies":[129],"experiments,":[131],"demonstrate":[133],"effectiveness":[135],"module":[141],"Conformer":[144],"based":[145],"separator.":[146],"Experimental":[147],"results":[148],"show":[150],"be":[155],"generalized":[156],"to":[157],"neural":[159],"network":[160],"architectures.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}