{"id":"https://openalex.org/W4390815280","doi":"https://doi.org/10.1109/taslp.2024.3350893","title":"Advanced Long-Content Speech Recognition With Factorized Neural Transducer","display_name":"Advanced Long-Content Speech Recognition With Factorized Neural Transducer","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390815280","doi":"https://doi.org/10.1109/taslp.2024.3350893"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3350893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3350893","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.13423","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086338661","display_name":"Xun Gong","orcid":"https://orcid.org/0000-0002-3364-8407"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Gong","raw_affiliation_strings":["Auditory Cognition and Computational Acoustics Lab, the Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3364-8407","affiliations":[{"raw_affiliation_string":"Auditory Cognition and Computational Acoustics Lab, the Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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 Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5715-3011","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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/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":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1089-9748","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"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":"Shujie Liu","raw_affiliation_strings":["Microsoft Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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/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":"Rui Zhao","raw_affiliation_strings":["Microsoft Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Auditory Cognition and Computational Acoustics Lab, the Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7423-617X","affiliations":[{"raw_affiliation_string":"Auditory Cognition and Computational Acoustics Lab, the Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Auditory Cognition and Computational Acoustics Lab, the Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0314-3790","affiliations":[{"raw_affiliation_string":"Auditory Cognition and Computational Acoustics Lab, the Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9153,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86629346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1803","last_page":"1815"},"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":0.9980000257492065,"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":0.9973999857902527,"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/speech-recognition","display_name":"Speech recognition","score":0.6181430816650391},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.5740104913711548},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.477475643157959},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.47012150287628174},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43743813037872314},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3349120616912842},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32240474224090576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30733728408813477},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2187935709953308},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09159472584724426}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6181430816650391},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.5740104913711548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.477475643157959},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.47012150287628174},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43743813037872314},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3349120616912842},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32240474224090576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30733728408813477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2187935709953308},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09159472584724426},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3350893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3350893","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2403.13423","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.13423","pdf_url":"https://arxiv.org/pdf/2403.13423","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.13423","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.13423","pdf_url":"https://arxiv.org/pdf/2403.13423","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1899722019","display_name":"\u6df1\u5ea6\u5b66\u4e60\u8bed\u97f3\u8bc6\u522b\u4e2d\u7684\u5feb\u901f\u9ad8\u6548\u81ea\u9002\u5e94\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3537961753","display_name":null,"funder_award_id":"62122050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G418946944","display_name":null,"funder_award_id":"2021 SHZDZX0102","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390815280.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1999965501","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2251849926","https://openalex.org/W2327501763","https://openalex.org/W2472672021","https://openalex.org/W2508661145","https://openalex.org/W2573537087","https://openalex.org/W2739883972","https://openalex.org/W2766219058","https://openalex.org/W2886025712","https://openalex.org/W2891176389","https://openalex.org/W2936774411","https://openalex.org/W2937649809","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963250244","https://openalex.org/W2963414781","https://openalex.org/W2963827914","https://openalex.org/W2965373594","https://openalex.org/W2972818416","https://openalex.org/W3007073761","https://openalex.org/W3007328579","https://openalex.org/W3007776460","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3015194534","https://openalex.org/W3016234571","https://openalex.org/W3028545098","https://openalex.org/W3093502359","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3096798607","https://openalex.org/W3097777922","https://openalex.org/W3161873870","https://openalex.org/W3162665866","https://openalex.org/W3163463193","https://openalex.org/W3197242296","https://openalex.org/W3197654132","https://openalex.org/W3197898596","https://openalex.org/W3198413388","https://openalex.org/W3198694222","https://openalex.org/W3200895333","https://openalex.org/W3202419788","https://openalex.org/W3211278025","https://openalex.org/W4221144554","https://openalex.org/W4283826357","https://openalex.org/W4283835659","https://openalex.org/W4297841866","https://openalex.org/W4319862418","https://openalex.org/W4319862683","https://openalex.org/W4372260432","https://openalex.org/W4375869444","https://openalex.org/W4385245566","https://openalex.org/W4388017359","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6747158283","https://openalex.org/W6766673545","https://openalex.org/W6784312278"],"related_works":["https://openalex.org/W2012283803","https://openalex.org/W4384820447","https://openalex.org/W2383068986","https://openalex.org/W2090275562","https://openalex.org/W3152005513","https://openalex.org/W2020960496","https://openalex.org/W1266100159","https://openalex.org/W2088920587","https://openalex.org/W2034887142","https://openalex.org/W2046074924"],"abstract_inverted_index":{"Long-form":[0],"automatic":[1],"speech":[2,130,203,242,252],"recognition":[3,253],"(ASR)":[4],"has":[5],"obtained":[6],"increasing":[7],"interest":[8],"in":[9,46,110,125],"recent":[10],"years,":[11],"as":[12,100],"it":[13],"captures":[14],"the":[15,23,39,66,76,92,120,153,182,186,208,231,237],"relationship":[16],"among":[17],"consecutive":[18],"historical":[19],"sentences":[20],"while":[21,224],"decoding":[22],"current":[24],"sentence.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,115,180],"propose":[30,116],"two":[31],"novel":[32],"approaches,":[33],"which":[34,189],"integrate":[35],"long-form":[36,62,87,112,123,200,241],"information":[37,124],"into":[38],"factorized":[40],"neural":[41],"transducer":[42,69],"(FNT)":[43],"based":[44],"architecture":[45],"both":[47,126,248],"non-streaming":[48,249],"(referred":[49,54],"to":[50,55,91,142,152,185,198,230],"asLongFNT)":[51],"and":[52,118,129,135,165,168,172,195,202,215,221,243,250],"streaming":[53,187,251],"asSLongFNT)":[56],"scenarios.":[57],"We":[58],"first":[59],"investigate":[60],"whether":[61],"transcriptions":[63],"can":[64],"improve":[65],"vanilla":[67,77],"conformer":[68],"(C-T)":[70],"models.":[71],"Our":[72],"experiments":[73],"indicate":[74],"that":[75,207],"C-T":[78,96],"models":[79,97,137],"do":[80],"not":[81,98],"exhibit":[82],"improved":[83],"performance":[84],"when":[85],"utilizing":[86,111],"transcriptions,":[88],"possibly":[89],"due":[90],"predictor":[93],"network":[94],"of":[95,122,157,193,239],"functioning":[99],"a":[101,226],"pure":[102],"language":[103],"model.":[104,154],"Instead,":[105],"FNT":[106,232],"shows":[107],"its":[108],"potential":[109],"information,":[113],"where":[114],"theLongFNTmodel":[117],"explore":[119],"impact":[121],"text":[127,201],"(LongFNT-Text)":[128],"(LongFNT-Speech).":[131],"The":[132,155],"proposed":[133,209],"LongFNT-Text":[134],"LongFNT-Speech":[136],"further":[138],"complement":[139],"each":[140],"other":[141],"achieve":[143],"better":[144],"performance,":[145],"with":[146],"transcription":[147,244],"history":[148],"proving":[149],"more":[150],"valuable":[151],"effectiveness":[156],"our":[158,235],"LongFNT":[159,183],"approach":[160],"is":[161,190],"evaluated":[162],"on":[163,219],"LibriSpeech":[164,220],"GigaSpeech":[166,222],"corpora,":[167],"obtains":[169],"relative":[170,213],"19%":[171],"12%":[173],"word":[174],"error":[175],"rate":[176],"reduction,":[177],"respectively.":[178],"Furthermore,":[179],"extend":[181],"model":[184,211],"scenario,":[188],"namedSLongFNT,":[191],"consisting":[192],"SLongFNT-Text":[194],"SLongFNT-Speech":[196],"approaches":[197],"utilize":[199],"information.":[204],"Experiments":[205],"show":[206],"SLongFNT":[210],"achieves":[212],"26%":[214],"17%":[216],"WER":[217],"reduction":[218],"respectively":[223],"keeping":[225],"good":[227],"latency,":[228],"compared":[229],"baseline.":[233],"Overall,":[234],"proposedLongFNTandSLongFNThighlight":[236],"significance":[238],"considering":[240],"knowledge":[245],"for":[246],"improving":[247],"systems.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}