{"id":"https://openalex.org/W3143843080","doi":"https://doi.org/10.1109/slt48900.2021.9383600","title":"Investigation of End-to-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings","display_name":"Investigation of End-to-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3143843080","doi":"https://doi.org/10.1109/slt48900.2021.9383600","mag":"3143843080"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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 Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"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":"Xuankai Chang","raw_affiliation_strings":["Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363489","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0009-0004-6683-3969"},"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 Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., 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 Corp., USA"],"affiliations":[{"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"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., 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 Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5016279564"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":5.167,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96153345,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"809","last_page":"816"},"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":0.9993000030517578,"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":0.9991999864578247,"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/monaural","display_name":"Monaural","score":0.8157387971878052},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8056838512420654},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7830628752708435},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7628717422485352},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6828171014785767},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5090989470481873},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.440518856048584},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.425048828125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4002630114555359}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8157387971878052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8056838512420654},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7830628752708435},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7628717422485352},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6828171014785767},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5090989470481873},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.440518856048584},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.425048828125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4002630114555359},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1591607137","https://openalex.org/W1876378865","https://openalex.org/W2030486566","https://openalex.org/W2046056978","https://openalex.org/W2125336414","https://openalex.org/W2132914434","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2569324142","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2884797218","https://openalex.org/W2900440209","https://openalex.org/W2902864383","https://openalex.org/W2939690918","https://openalex.org/W2952752702","https://openalex.org/W2957946919","https://openalex.org/W2963227667","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2963979492","https://openalex.org/W2972449503","https://openalex.org/W2972492143","https://openalex.org/W2972949456","https://openalex.org/W2973127116","https://openalex.org/W2997419692","https://openalex.org/W2999547272","https://openalex.org/W3000358149","https://openalex.org/W3007946293","https://openalex.org/W3008283340","https://openalex.org/W3008357631","https://openalex.org/W3008762051","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3016244460","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3094821064","https://openalex.org/W3094831814","https://openalex.org/W3095822285","https://openalex.org/W3097643313","https://openalex.org/W3105031100","https://openalex.org/W3131736947","https://openalex.org/W3154262773","https://openalex.org/W3208240190","https://openalex.org/W4237168004","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6639431793","https://openalex.org/W6662018943","https://openalex.org/W6678809451","https://openalex.org/W6775537894","https://openalex.org/W6784900337","https://openalex.org/W6791127467","https://openalex.org/W6802591457"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4318225096","https://openalex.org/W2126085626","https://openalex.org/W2545131480","https://openalex.org/W2087341511","https://openalex.org/W1521049138","https://openalex.org/W4247736853","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"Recently,":[0],"an":[1],"end-to-end":[2],"(E2E)":[3],"speaker-attributed":[4],"automatic":[5],"speech":[6,19,34],"recognition":[7,20],"(SA-ASR)":[8],"model":[9,15,44,98,188],"was":[10],"proposed":[11,148,166],"as":[12],"a":[13,117,138,169],"joint":[14],"of":[16,37,40,48,60,94,103,124,141,197],"speaker":[17,22,49,53,77,84,92,112,163,175],"counting,":[18],"and":[21,86,146,194],"identification":[23],"for":[24,32],"monaural":[25,152],"overlapped":[26],"speech.":[27],"It":[28],"showed":[29],"promising":[30],"results":[31],"simulated":[33],"mixtures":[35],"consisting":[36],"various":[38],"numbers":[39],"speakers.":[41],"However,":[42],"the":[43,58,61,68,73,90,95,101,104,111,121,125,142,147,151,157,165,181,185,192,198],"required":[45],"prior":[46,69,174],"knowledge":[47],"profiles":[50,107],"to":[51,99,120,156],"perform":[52,83],"identification,":[54],"which":[55,129],"significantly":[56],"limited":[57],"application":[59],"model.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,82],"extend":[67],"work":[70],"by":[71,88],"addressing":[72],"case":[74],"where":[75],"no":[76],"profile":[78],"is":[79],"available.":[80],"Specifically,":[81],"counting":[85],"clustering":[87],"using":[89],"internal":[91],"representations":[93],"E2E":[96,126,144,159,186],"SA-ASR":[97,127,145,160,187],"diarize":[100],"utterances":[102],"speakers":[105],"whose":[106],"are":[108],"missing":[109],"from":[110],"inventory.":[113],"We":[114,136,177],"also":[115,178],"propose":[116],"simple":[118],"modification":[119],"reference":[122],"labels":[123],"training":[128],"helps":[130],"handle":[131],"continuous":[132],"multi-talker":[133],"recordings":[134],"well.":[135],"conduct":[137],"comprehensive":[139],"investigation":[140],"original":[143,158],"method":[149,167],"on":[150],"LibriCSS":[153],"dataset.":[154],"Compared":[155],"with":[161],"relevant":[162],"profiles,":[164],"achieves":[168],"close":[170],"performance":[171],"without":[172],"any":[173],"knowledge.":[176],"show":[179],"that":[180],"source-target":[182],"attention":[183],"in":[184],"provides":[189],"information":[190],"about":[191],"start":[193],"end":[195],"times":[196],"hypotheses.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}