{"id":"https://openalex.org/W3200955206","doi":"https://doi.org/10.1109/icassp43922.2022.9746574","title":"Continuous Streaming Multi-Talker ASR with Dual-Path Transducers","display_name":"Continuous Streaming Multi-Talker ASR with Dual-Path Transducers","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3200955206","doi":"https://doi.org/10.1109/icassp43922.2022.9746574","mag":"3200955206"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746574","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5004777817","display_name":"Desh Raj","orcid":"https://orcid.org/0000-0002-5038-9400"},"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":true,"raw_author_name":"Desh Raj","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"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":"Liang Lu","raw_affiliation_strings":["Microsoft Corp.,USA","Microsoft Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345062","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0001-9991-6892"},"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":"Zhuo Chen","raw_affiliation_strings":["Microsoft Corp.,USA","Microsoft Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","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":"Yashesh Gaur","raw_affiliation_strings":["Microsoft Corp.,USA","Microsoft Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","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 Corp.,USA","Microsoft Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004777817"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.6649,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85492647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7317","last_page":"7321"},"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":0.9998000264167786,"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":0.9976000189781189,"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":0.826439619064331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5617769360542297},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5194387435913086},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4399242699146271},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.43235665559768677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41503196954727173},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12768065929412842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826439619064331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5617769360542297},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5194387435913086},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4399242699146271},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.43235665559768677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41503196954727173},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12768065929412842},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/icassp43922.2022.9746574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746574","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1558276682","https://openalex.org/W1828163288","https://openalex.org/W1989314204","https://openalex.org/W2125336414","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2222512263","https://openalex.org/W2289394825","https://openalex.org/W2608712415","https://openalex.org/W2759071281","https://openalex.org/W2890244912","https://openalex.org/W2940744433","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963574857","https://openalex.org/W2964391865","https://openalex.org/W2998108143","https://openalex.org/W3007227084","https://openalex.org/W3013139777","https://openalex.org/W3015199127","https://openalex.org/W3015746570","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3094821064","https://openalex.org/W3095189764","https://openalex.org/W3096893582","https://openalex.org/W3106009088","https://openalex.org/W3106298483","https://openalex.org/W3109079702","https://openalex.org/W3162847598","https://openalex.org/W3163842642","https://openalex.org/W3196194966","https://openalex.org/W3211278025","https://openalex.org/W4323654151","https://openalex.org/W6623517193","https://openalex.org/W6633191483","https://openalex.org/W6638749077","https://openalex.org/W6678809451","https://openalex.org/W6687566353","https://openalex.org/W6761628794","https://openalex.org/W6772853553","https://openalex.org/W6775489429","https://openalex.org/W6776048756","https://openalex.org/W6779728549","https://openalex.org/W6781260015","https://openalex.org/W6792630565","https://openalex.org/W6804209468"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036","https://openalex.org/W2124470186"],"abstract_inverted_index":{"Streaming":[0,29],"recognition":[1],"of":[2],"multi-talker":[3],"conversations":[4],"has":[5],"so":[6],"far":[7],"been":[8],"evaluated":[9],"only":[10],"for":[11,21,64,104],"2-speaker":[12],"single-turn":[13,42],"sessions.":[14],"In":[15],"this":[16,45],"paper,":[17],"we":[18,55,115],"investigate":[19],"it":[20],"multi-turn":[22],"meetings":[23],"containing":[24],"multiple":[25],"speakers":[26],"using":[27],"the":[28,41,57,120],"Unmixing":[30],"and":[31,36,72,77,101,107],"Recognition":[32],"Transducer":[33],"(SURT)":[34],"model,":[35],"show":[37,78],"that":[38,79],"naively":[39],"extending":[40],"model":[43],"to":[44],"harder":[46],"setting":[47],"incurs":[48],"a":[49,53],"performance":[50,86],"penalty.":[51],"As":[52],"solution,":[54],"propose":[56],"dual-path":[58],"(DP)":[59],"modeling":[60],"strategy":[61],"first":[62],"used":[63],"time-domain":[65],"speech":[66],"separation.":[67],"We":[68,91],"experiment":[69],"with":[70,128],"LSTM":[71],"Transformer":[73],"based":[74],"DP":[75],"models,":[76,106],"they":[80,125],"improve":[81],"word":[82],"error":[83],"rate":[84],"(WER)":[85],"while":[87],"yielding":[88],"faster":[89],"convergence.":[90],"also":[92],"explore":[93],"training":[94],"strategies":[95],"such":[96],"as":[97],"chunk":[98],"width":[99],"randomization":[100],"curriculum":[102],"learning":[103],"these":[105],"demonstrate":[108],"their":[109],"importance":[110],"through":[111],"ablation":[112],"studies.":[113],"Finally,":[114],"evaluate":[116],"our":[117],"models":[118],"on":[119],"LibriCSS":[121],"meeting":[122],"data,":[123],"where":[124],"perform":[126],"competitively":[127],"offline":[129],"separation-based":[130],"methods.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}