{"id":"https://openalex.org/W3161201807","doi":"https://doi.org/10.1109/icassp39728.2021.9414127","title":"Dual-Path Modeling for Long Recording Speech Separation in Meetings","display_name":"Dual-Path Modeling for Long Recording Speech Separation in Meetings","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161201807","doi":"https://doi.org/10.1109/icassp39728.2021.9414127","mag":"3161201807"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"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":"Chenda Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab","MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108961732","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0007-3882-3810"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070114472","display_name":"Cong Han","orcid":"https://orcid.org/0000-0003-2121-000X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Han","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103218426","display_name":"Tianyan Zhou","orcid":"https://orcid.org/0000-0003-3238-2982"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tianyan Zhou","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","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,MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab","MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5739","last_page":"5743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9987999796867371,"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":0.7460455894470215},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6017436981201172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5569811463356018},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.511816680431366},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5068197846412659},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49687817692756653},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4877668023109436},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29838037490844727},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10064226388931274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460455894470215},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6017436981201172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5569811463356018},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.511816680431366},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5068197846412659},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49687817692756653},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4877668023109436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29838037490844727},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10064226388931274},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/icassp39728.2021.9414127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2117678320","https://openalex.org/W2221409856","https://openalex.org/W2302255633","https://openalex.org/W2460742184","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2890244912","https://openalex.org/W2891405874","https://openalex.org/W2891833136","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963403868","https://openalex.org/W2963773971","https://openalex.org/W2964121744","https://openalex.org/W2972818416","https://openalex.org/W2973062255","https://openalex.org/W3000358149","https://openalex.org/W3007328579","https://openalex.org/W3008003372","https://openalex.org/W3008283340","https://openalex.org/W3008762051","https://openalex.org/W3008880747","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3016232124","https://openalex.org/W3017474798","https://openalex.org/W3032969657","https://openalex.org/W3096893582","https://openalex.org/W3097445713","https://openalex.org/W3099330747","https://openalex.org/W3105928222","https://openalex.org/W3124972797","https://openalex.org/W3133834828","https://openalex.org/W3143843080","https://openalex.org/W3151851237","https://openalex.org/W3185109982","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6698183232","https://openalex.org/W6729728456","https://openalex.org/W6739901393","https://openalex.org/W6774687970","https://openalex.org/W6780226713","https://openalex.org/W6782161367","https://openalex.org/W6785331785","https://openalex.org/W6790988731"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3016124757","https://openalex.org/W3034520363","https://openalex.org/W2183638083","https://openalex.org/W2119138398","https://openalex.org/W2306351532","https://openalex.org/W2598979711","https://openalex.org/W2037384153"],"abstract_inverted_index":{"The":[0,71,123],"continuous":[1],"speech":[2,11,32,64],"separation":[3,33],"(CSS)":[4],"is":[5,38,114,157],"a":[6,14,21,45,78,130,150],"task":[7,37],"to":[8,34,39,58,68,80,84,128,186],"separate":[9],"the":[10,35,41,60,90,94,103,143,162,172,187],"sources":[12],"from":[13],"long,":[15],"partially":[16],"overlapped":[17],"recording,":[18],"which":[19,116,179],"involves":[20],"varying":[22],"number":[23],"of":[24,29],"speakers.":[25],"A":[26,110],"straightforward":[27],"extension":[28,56],"conventional":[30],"utterance-level":[31],"CSS":[36,108],"segment":[40],"long":[42,61],"recording":[43],"with":[44,154,167],"size-fixed":[46],"window":[47,51],"and":[48,65,93,135],"process":[49],"each":[50],"separately.":[52],"Though":[53],"effective,":[54],"this":[55,81,98],"fails":[57],"model":[59],"dependency":[62,92],"in":[63,87,142],"thus":[66],"leads":[67],"sub-optimum":[69],"performance.":[70],"recent":[72],"proposed":[73,124],"dual-path":[74,104,112,151,175],"modeling":[75,89,105],"could":[76],"be":[77,140],"remedy":[79],"problem,":[82],"thanks":[83],"its":[85],"capability":[86],"jointly":[88],"cross-window":[91],"local-window":[95],"processing.":[96],"In":[97],"work,":[99],"we":[100],"further":[101],"extend":[102],"framework":[106],"for":[107,120,146],"task.":[109],"transformer-based":[111],"system":[113],"proposed,":[115],"integrates":[117],"transform":[118],"layers":[119,156],"global":[121],"modeling.":[122],"models":[125,176],"are":[126,177],"applied":[127],"LibriCSS,":[129],"real":[131],"recorded":[132],"multi-talk":[133],"dataset,":[134],"consistent":[136],"WER":[137,169,183],"reduction":[138,184],"can":[139],"observed":[141],"ASR":[144],"evaluation":[145],"separated":[147],"speech.":[148],"Also,":[149],"transformer":[152],"equipped":[153],"convolutional":[155],"proposed.":[158],"It":[159],"significantly":[160],"reduces":[161],"computation":[163],"amount":[164],"by":[165],"30%":[166],"better":[168],"evaluation.":[170],"Furthermore,":[171],"online":[173],"processing":[174],"investigated,":[178],"shows":[180],"10%":[181],"relative":[182],"compared":[185],"baseline.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}