{"id":"https://openalex.org/W4224920409","doi":"https://doi.org/10.1109/icassp43922.2022.9746074","title":"Multi-Turn RNN-T for Streaming Recognition of Multi-Party Speech","display_name":"Multi-Turn RNN-T for Streaming Recognition of Multi-Party Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920409","doi":"https://doi.org/10.1109/icassp43922.2022.9746074"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746074","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/A5064043969","display_name":"Ilya Sklyar","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ilya Sklyar","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079151774","display_name":"Anna Piunova","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Piunova","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"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":["University of Cambridge"],"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100768704","display_name":"Yulan Liu","orcid":"https://orcid.org/0000-0003-3320-2381"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulan Liu","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064043969"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":1.8787,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87507288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8402","last_page":"8406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9984999895095825,"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":0.8587555289268494},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7386046648025513},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7100499868392944},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5435826778411865},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5285928249359131},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4970417320728302},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4603443443775177},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.45820263028144836},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4427882730960846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38500291109085083},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36403584480285645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8587555289268494},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7386046648025513},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7100499868392944},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5435826778411865},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5285928249359131},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4970417320728302},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4603443443775177},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.45820263028144836},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4427882730960846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38500291109085083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36403584480285645},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746074","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":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1560013842","https://openalex.org/W1578856370","https://openalex.org/W1828163288","https://openalex.org/W2027499299","https://openalex.org/W2404199887","https://openalex.org/W2460742184","https://openalex.org/W2507946458","https://openalex.org/W2884797218","https://openalex.org/W2890244912","https://openalex.org/W2936774411","https://openalex.org/W2943934118","https://openalex.org/W2962715207","https://openalex.org/W2963250244","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2963843276","https://openalex.org/W2995166068","https://openalex.org/W3013139777","https://openalex.org/W3015746570","https://openalex.org/W3015995734","https://openalex.org/W3016232124","https://openalex.org/W3032969657","https://openalex.org/W3097643313","https://openalex.org/W3109079702","https://openalex.org/W3143843080","https://openalex.org/W3162847598","https://openalex.org/W3181056718","https://openalex.org/W3186652349","https://openalex.org/W3187990717","https://openalex.org/W3196194966","https://openalex.org/W4226305408","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6775489429","https://openalex.org/W6779505821","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W2145230572","https://openalex.org/W2166312020","https://openalex.org/W2150750161","https://openalex.org/W4384389756","https://openalex.org/W2914064142","https://openalex.org/W3136989387","https://openalex.org/W3082335021"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,87],"recognition":[2,33,172],"(ASR)":[3],"of":[4,13,124,136,140,175,186],"single":[5],"channel":[6],"far-field":[7],"recordings":[8],"with":[9,112,165],"an":[10,113,121,179],"unknown":[11],"number":[12,123,139],"speakers":[14,125,141],"is":[15],"traditionally":[16],"tackled":[17],"by":[18],"cascaded":[19],"modules.":[20],"Recent":[21],"research":[22,195],"shows":[23],"that":[24,118],"end-to-end":[25],"(E2E)":[26],"multi-speaker":[27,76],"ASR":[28],"models":[29,41],"can":[30],"achieve":[31],"superior":[32],"accuracy":[34],"compared":[35],"to":[36,48,120],"modular":[37],"systems.":[38],"However,":[39],"these":[40],"do":[42],"not":[43],"ensure":[44],"real-time":[45,58],"applicability":[46,59],"due":[47],"their":[49],"dependency":[50],"on":[51,75,99,145,148],"full":[52],"audio":[53],"context.":[54],"This":[55],"work":[56,74],"takes":[57],"as":[60,190,192],"the":[61,129,134,137,159,187],"first":[62],"priority":[63],"in":[64,72,128],"model":[65,111,130],"design":[66],"and":[67,152,173],"addresses":[68],"a":[69,106,166],"few":[70],"challenges":[71],"previous":[73],"recurrent":[77],"neural":[78],"network":[79],"transducer":[80],"(MS-RNN-T).":[81],"First,":[82],"we":[83,104,163,182],"introduce":[84],"on-the-fly":[85],"overlapping":[86],"simulation":[88],"during":[89,143],"training,":[90],"yielding":[91],"14%":[92],"relative":[93,155],"word":[94],"error":[95],"rate":[96],"(WER)":[97],"improvement":[98,157],"LibriSpeechMix":[100],"test":[101,150],"set.":[102],"Second,":[103],"propose":[105],"novel":[107],"multi-turn":[108],"RNN-T":[109],"(MT-RNN-T)":[110],"overlap-based":[114],"target":[115],"arrangement":[116],"strategy":[117,169],"generalizes":[119],"arbitrary":[122],"without":[126],"changes":[127],"architecture.":[131],"We":[132],"investigate":[133],"impact":[135],"maximum":[138],"seen":[142],"training":[144],"MT-RNN-T":[146],"performance":[147],"LibriCSS":[149],"set,":[151],"report":[153],"28%":[154],"WER":[156],"over":[158],"two-speaker":[160],"MS-RNN-T.":[161],"Third,":[162],"experiment":[164],"rich":[167],"transcription":[168],"for":[170],"joint":[171],"segmentation":[174],"multi-party":[176],"speech.":[177],"Through":[178],"in-depth":[180],"analysis,":[181],"discuss":[183],"potential":[184],"pitfalls":[185],"proposed":[188],"system":[189],"well":[191],"promising":[193],"future":[194],"directions.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2025-10-10T00:00:00"}