{"id":"https://openalex.org/W4392908892","doi":"https://doi.org/10.1109/icassp48485.2024.10446050","title":"Diarist: Streaming Speech Translation with Speaker Diarization","display_name":"Diarist: Streaming Speech Translation with Speaker Diarization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908892","doi":"https://doi.org/10.1109/icassp48485.2024.10446050"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100530153","display_name":"Mu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mu Yang","raw_affiliation_strings":["University of Texas at Dallas,Center for Robust Speech Systems (CRSS),Richardson,TX,USA","Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Center for Robust Speech Systems (CRSS),Richardson,TX,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","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":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, 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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034556928","display_name":"Junkun Chen","orcid":"https://orcid.org/0000-0003-0193-238X"},"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":"Junkun Chen","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"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":"Peidong Wang","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763213","display_name":"Jian Xue","orcid":"https://orcid.org/0000-0002-9460-802X"},"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 Xue","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, 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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, 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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10866","last_page":"10870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9495999813079834,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9495999813079834,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7845525145530701},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7191768288612366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.606816828250885},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5059294104576111},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38577231764793396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3742259442806244},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.31688928604125977},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.18541553616523743}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7845525145530701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7191768288612366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.606816828250885},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5059294104576111},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38577231764793396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3742259442806244},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31688928604125977},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.18541553616523743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1537859740","https://openalex.org/W1556857061","https://openalex.org/W1558276682","https://openalex.org/W1876378865","https://openalex.org/W1975884129","https://openalex.org/W2113106066","https://openalex.org/W2582956876","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2901607128","https://openalex.org/W2902864383","https://openalex.org/W2963532001","https://openalex.org/W2997419692","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3034625919","https://openalex.org/W3097777922","https://openalex.org/W3105031100","https://openalex.org/W3142516134","https://openalex.org/W3161873870","https://openalex.org/W3167533889","https://openalex.org/W3181056718","https://openalex.org/W3203417382","https://openalex.org/W3204618061","https://openalex.org/W3207834622","https://openalex.org/W3212886388","https://openalex.org/W4224137820","https://openalex.org/W4224925136","https://openalex.org/W4226098957","https://openalex.org/W4226491018","https://openalex.org/W4297161768","https://openalex.org/W4311000453","https://openalex.org/W4372260044","https://openalex.org/W4385822293","https://openalex.org/W4385822321","https://openalex.org/W4385823495","https://openalex.org/W4391021779","https://openalex.org/W4391021781","https://openalex.org/W6639431793","https://openalex.org/W6775053297","https://openalex.org/W6842793246","https://openalex.org/W6847363464","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,25,67],"translation":[2],"(ST)":[3],"for":[4,65,140],"conversation":[5],"recordings":[6],"involves":[7],"several":[8],"under-explored":[9],"challenges":[10],"such":[11],"as":[12],"speaker":[13],"diarization":[14],"(SD)":[15],"without":[16],"accurate":[17],"word":[18],"time":[19],"stamps":[20],"and":[21,40,53,59,106,126,160],"handling":[22],"of":[23,73,92],"overlapping":[24,141],"in":[26,76,147],"a":[27,47,81,123],"streaming":[28,38,50,138],"fashion.":[29],"In":[30],"this":[31,77,148],"work,":[32],"we":[33,79,151],"propose":[34,100],"DiariST,":[35],"the":[36,71,88,93,111,145,153,156,161],"first":[37],"ST":[39,51,112,125],"SD":[41,116,127],"solution.":[42],"It":[43],"is":[44],"built":[45],"upon":[46],"neural":[48],"transducer-based":[49],"system":[52,121],"integrates":[54],"tokenlevel":[55],"serialized":[56],"output":[57],"training":[58],"t-vector,":[60],"which":[61],"were":[62],"originally":[63],"developed":[64],"multi-talker":[66],"recognition.":[68],"Due":[69],"to":[70,109,130],"absence":[72],"evaluation":[74,83,154,162],"benchmarks":[75],"area,":[78],"develop":[80],"new":[82,101,149],"dataset,":[84],"DiariST-AliMeeting,":[85],"by":[86],"translating":[87],"reference":[89],"Chinese":[90],"transcriptions":[91],"AliMeeting":[94],"corpus":[95],"into":[96,118],"English.":[97],"We":[98],"also":[99],"metrics,":[102],"called":[103],"speaker-agnostic":[104],"BLEU":[105],"speaker-attributed":[107],"BLEU,":[108],"measure":[110],"quality":[113],"while":[114,136],"taking":[115],"accuracy":[117],"account.":[119],"Our":[120],"achieves":[122],"strong":[124],"capability":[128],"compared":[129],"offline":[131,157],"systems":[132],"based":[133],"on":[134],"Whisper,":[135],"performing":[137],"inference":[139],"speech.":[142],"To":[143],"facilitate":[144],"research":[146],"direction,":[150],"release":[152],"data,":[155],"baseline":[158],"systems,":[159],"code.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}