{"id":"https://openalex.org/W4226098957","doi":"https://doi.org/10.21437/interspeech.2022-253","title":"Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings","display_name":"Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226098957","doi":"https://doi.org/10.21437/interspeech.2022-253"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-253","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-253","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"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":true,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft Cloud+AI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"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":"Jian Wu","raw_affiliation_strings":["Microsoft Cloud+AI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709477","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-5715-3011"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"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":"Xiong Xiao","raw_affiliation_strings":["Microsoft Cloud+AI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"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":"Zhong Meng","raw_affiliation_strings":["Microsoft Cloud+AI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046637354","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0001-5490-5591"},"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":"Xiaofei Wang","raw_affiliation_strings":["Microsoft Cloud+AI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, 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 Cloud+AI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345056","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0001-7799-5163"},"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 Cloud+AI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","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 Cloud+AI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft Cloud+AI, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5016279564"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.8788,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87565591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"521","last_page":"525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9872999787330627,"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":0.9749000072479248,"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":0.7935956120491028},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7832729816436768},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5472348928451538},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42238712310791016},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.37532493472099304},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2197159230709076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935956120491028},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7832729816436768},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5472348928451538},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42238712310791016},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.37532493472099304},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2197159230709076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-253","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-253","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1876378865","https://openalex.org/W2046056978","https://openalex.org/W2125336414","https://openalex.org/W2133564696","https://openalex.org/W2746574320","https://openalex.org/W2884797218","https://openalex.org/W2928165649","https://openalex.org/W2939690918","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2973127116","https://openalex.org/W2973730722","https://openalex.org/W3008283340","https://openalex.org/W3008762051","https://openalex.org/W3016010032","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3094831814","https://openalex.org/W3095822285","https://openalex.org/W3097643313","https://openalex.org/W3105031100","https://openalex.org/W3137249133","https://openalex.org/W3140315487","https://openalex.org/W3143843080","https://openalex.org/W3154262773","https://openalex.org/W3161873870","https://openalex.org/W3162347631","https://openalex.org/W3163842642","https://openalex.org/W3212886388","https://openalex.org/W4226305408","https://openalex.org/W4226491018","https://openalex.org/W4285666843","https://openalex.org/W4287240341","https://openalex.org/W4287240843","https://openalex.org/W4288083483","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2118860825","https://openalex.org/W2161543916"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,45,63,116,136],"streaming":[4,46,138],"speaker-attributed":[5],"automatic":[6],"speech":[7,43,74],"recognition":[8],"(SA-ASR)":[9],"model":[10,27,114,130,139],"that":[11,60],"can":[12,61],"recognize":[13,49],"\"who":[14],"spoke":[15],"what\"":[16],"with":[17,88,104,108],"low":[18,109],"latency":[19],"even":[20,145],"when":[21],"multiple":[22],"people":[23],"are":[24],"speaking":[25],"simultaneously.Our":[26],"is":[28,85],"based":[29,56],"on":[30],"token-level":[31],"serialized":[32],"output":[33],"training":[34],"(t-SOT)":[35],"which":[36],"was":[37],"recently":[38],"proposed":[39,80,113,129],"to":[40,148],"transcribe":[41],"multi-talker":[42,106],"in":[44],"fashion.To":[47],"further":[48],"speaker":[50,57,64,81,97,101],"identities,":[51],"we":[52],"propose":[53],"an":[54],"encoderdecoder":[55],"embedding":[58],"extractor":[59],"estimate":[62],"representation":[65],"for":[66,115],"each":[67],"recognized":[68],"token":[69],"not":[70],"only":[71],"from":[72,77],"non-overlapping":[73],"but":[75],"also":[76],"overlapping":[78],"speech.The":[79],"embedding,":[82],"named":[83],"t-vector,":[84],"extracted":[86],"synchronously":[87],"the":[89,105,112,149],"t-SOT":[90],"ASR":[91,120],"model,":[92],"enabling":[93],"joint":[94,117],"execution":[95],"of":[96,119],"identification":[98],"(SID)":[99],"or":[100,143],"diarization":[102],"(SD)":[103],"transcription":[107],"latency.We":[110],"evaluate":[111],"task":[118],"and":[121,126,140],"SID/SD":[122],"by":[123],"using":[124],"LibriSpeechMix":[125],"LibriCSS":[127],"corpora.The":[128],"achieves":[131],"substantially":[132],"better":[133],"accuracy":[134],"than":[135],"prior":[137],"shows":[141],"comparable":[142],"sometimes":[144],"superior":[146],"results":[147],"state-of-the-art":[150],"offline":[151],"SA-ASR":[152],"model.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}