{"id":"https://openalex.org/W3162847598","doi":"https://doi.org/10.1109/icassp39728.2021.9413471","title":"Streaming Multi-Speaker ASR with RNN-T","display_name":"Streaming Multi-Speaker ASR with RNN-T","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162847598","doi":"https://doi.org/10.1109/icassp39728.2021.9413471","mag":"3162847598"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413471","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":"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":"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":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064043969"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":3.2387,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.93108444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6903","last_page":"6907"},"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":0.9998000264167786,"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":0.9991000294685364,"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":0.7892752885818481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7790005207061768},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7188170552253723},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6488758325576782},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6251800060272217},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5514073967933655},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5361374020576477},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5193708539009094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.393681138753891},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3563709855079651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892752885818481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7790005207061768},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7188170552253723},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6488758325576782},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6251800060272217},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5514073967933655},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5361374020576477},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5193708539009094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.393681138753891},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3563709855079651},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413471","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2526425061","https://openalex.org/W2739883972","https://openalex.org/W2890244912","https://openalex.org/W2936774411","https://openalex.org/W2943934118","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963250244","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2963843276","https://openalex.org/W2964121744","https://openalex.org/W2973127116","https://openalex.org/W2995166068","https://openalex.org/W3015746570","https://openalex.org/W3015995734","https://openalex.org/W3094821064","https://openalex.org/W3097643313","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6755552547"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Recent":[0],"research":[1],"shows":[2],"end-to-end":[3],"ASR":[4],"systems":[5],"can":[6],"recognize":[7],"overlapped":[8],"speech":[9,38],"from":[10,104],"multiple":[11],"speakers.":[12],"However,":[13],"all":[14],"published":[15],"works":[16],"have":[17],"assumed":[18],"no":[19],"latency":[20,60],"constraints":[21],"during":[22,124],"inference,":[23],"which":[24,139],"does":[25],"not":[26],"hold":[27],"for":[28,158],"most":[29],"voice":[30],"assistant":[31],"interactions.":[32],"This":[33],"work":[34],"focuses":[35],"on":[36,41,109,134],"multi-speaker":[37,69,112],"recognition":[39,55,62],"based":[40],"a":[42,58,130],"recurrent":[43],"neural":[44],"network":[45],"transducer":[46],"(RNN-T)":[47],"that":[48,84],"has":[49],"been":[50],"shown":[51],"to":[52,68],"provide":[53],"high":[54],"accuracy":[56],"at":[57],"low":[59],"online":[61],"regime.":[63],"We":[64,82],"investigate":[65],"two":[66],"approaches":[67],"model":[70,128,148,153],"training":[71,108],"of":[72,101,122,132],"the":[73,92,96,114,143,151],"RNN-T:":[74],"deterministic":[75],"output-target":[76],"assignment":[77],"and":[78,111],"permutation":[79],"invariant":[80],"training.":[81],"show":[83],"guiding":[85],"separation":[86],"with":[87,106,142],"speaker":[88,98],"order":[89],"labels":[90],"in":[91],"former":[93],"case":[94],"enhances":[95],"high-level":[97],"tracking":[99],"capability":[100],"RNN-T.":[102],"Apart":[103],"that,":[105],"multi-style":[107],"single-":[110],"utterances,":[113],"resulting":[115],"models":[116],"gain":[117],"robustness":[118],"against":[119],"ambiguous":[120],"numbers":[121],"speakers":[123],"inference.":[125],"Our":[126],"best":[127],"achieves":[129],"WER":[131],"10.2%":[133],"simulated":[135],"2-speaker":[136],"LibriSpeech":[137],"data,":[138],"is":[140],"competitive":[141],"previously":[144],"reported":[145],"state-of-the-art":[146],"non-streaming":[147],"(10.3%),":[149],"while":[150],"proposed":[152],"could":[154],"be":[155],"directly":[156],"applied":[157],"streaming":[159],"applications.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}