{"id":"https://openalex.org/W4392903212","doi":"https://doi.org/10.1109/icassp48485.2024.10447904","title":"T-SOT FNT: Streaming Multi-Talker ASR with Text-Only Domain Adaptation Capability","display_name":"T-SOT FNT: Streaming Multi-Talker ASR with Text-Only Domain Adaptation Capability","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903212","doi":"https://doi.org/10.1109/icassp48485.2024.10447904"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447904","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":"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/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":true,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"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/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"],"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/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"],"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/A5101987526","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9699-9984"},"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":"Rui Zhao","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"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/A5108961732","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0007-3882-3810"},"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, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"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/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"],"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":6,"corresponding_author_ids":["https://openalex.org/A5101674460"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.7301,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73128851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"11531","last_page":"11535"},"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":0.9994999766349792,"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":0.9987000226974487,"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/security-token","display_name":"Security token","score":0.9370877742767334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7850085496902466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7003989219665527},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.656679093837738},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6443081498146057},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5625527501106262},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.517695426940918},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4864489734172821},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4348711669445038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39953410625457764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.334962397813797},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3254340887069702},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08487272262573242},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06247261166572571}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.9370877742767334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850085496902466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7003989219665527},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.656679093837738},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6443081498146057},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5625527501106262},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.517695426940918},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4864489734172821},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4348711669445038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39953410625457764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.334962397813797},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3254340887069702},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08487272262573242},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06247261166572571},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447904","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1591607137","https://openalex.org/W2125336414","https://openalex.org/W2144499799","https://openalex.org/W2803322398","https://openalex.org/W2884797218","https://openalex.org/W2963240019","https://openalex.org/W2972492143","https://openalex.org/W2972794451","https://openalex.org/W3008037978","https://openalex.org/W3016010032","https://openalex.org/W3016232124","https://openalex.org/W3016234571","https://openalex.org/W3094821064","https://openalex.org/W3094831814","https://openalex.org/W3097777922","https://openalex.org/W3109079702","https://openalex.org/W3152221657","https://openalex.org/W3161873870","https://openalex.org/W3162847598","https://openalex.org/W3163842642","https://openalex.org/W3194687854","https://openalex.org/W3200955206","https://openalex.org/W3202419788","https://openalex.org/W3211278025","https://openalex.org/W4224920409","https://openalex.org/W4226491018","https://openalex.org/W4375868938","https://openalex.org/W4375869444","https://openalex.org/W4385245566","https://openalex.org/W6744711567"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2944691285","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Token-level":[0],"serialized":[1],"output":[2],"training":[3],"(t-SOT)":[4],"was":[5],"recently":[6],"proposed":[7,74,120],"to":[8,127,136],"address":[9],"the":[10,38,66,82,87,93,113,117,128,134],"challenge":[11],"of":[12,40,68,95,112],"streaming":[13],"multi-talker":[14,26,146],"automatic":[15],"speech":[16,23],"recognition":[17],"(ASR).":[18],"T-SOT":[19],"effectively":[20],"handles":[21,86],"overlapped":[22],"by":[24,103],"representing":[25],"transcriptions":[27],"as":[28],"a":[29,41,59,77],"single":[30,144],"token":[31,89],"stream":[32],"with":[33],"\u27e8cc\u27e9":[34,96,114],"symbols":[35,97],"interspersed.":[36],"However,":[37],"use":[39,94],"naive":[42],"neural":[43,70],"transducer":[44],"architecture":[45],"significantly":[46],"constrained":[47],"its":[48],"applicability":[49],"for":[50],"text-only":[51,149],"adaptation.":[52,150],"To":[53],"overcome":[54],"this":[55,102],"limitation,":[56],"we":[57],"propose":[58],"novel":[60],"t-SOT":[61,121,130],"model":[62,79,123,131],"structure":[63],"that":[64],"incorporates":[65],"idea":[67],"factorized":[69],"transducers":[71],"(FNT).":[72],"The":[73,119],"method":[75],"separates":[76],"language":[78],"(LM)":[80],"from":[81,92],"transducer\u2019s":[83],"predictor":[84],"and":[85,108,145],"unnatural":[88],"order":[90],"resulting":[91],"in":[98],"t-SOT.":[99],"We":[100],"achieve":[101],"maintaining":[104],"multiple":[105],"hidden":[106],"states":[107],"introducing":[109],"special":[110],"handling":[111],"tokens":[115],"within":[116],"LM.":[118],"FNT":[122],"achieves":[124],"comparable":[125],"performance":[126],"original":[129],"while":[132],"retaining":[133],"ability":[135],"reduce":[137],"word":[138],"error":[139],"rate":[140],"(WER)":[141],"on":[142],"both":[143],"datasets":[147],"through":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}