{"id":"https://openalex.org/W4372260432","doi":"https://doi.org/10.1109/icassp49357.2023.10096900","title":"LongFNT: Long-Form Speech Recognition with Factorized Neural Transducer","display_name":"LongFNT: Long-Form Speech Recognition with Factorized Neural Transducer","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260432","doi":"https://doi.org/10.1109/icassp49357.2023.10096900"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/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"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Xun Gong","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","Microsoft","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University","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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684043","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0003-2993-2023"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0009-0004-4458-0753"},"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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University","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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5086338661"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":1.9231,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88403016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.7785534858703613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7481281161308289},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7368881106376648},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6433892250061035},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6306453943252563},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6290227174758911},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5694133639335632},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.568436861038208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5647451281547546},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4866279065608978},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4522772431373596},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43556737899780273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41746607422828674},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3689790964126587},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3231637477874756},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10138645768165588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785534858703613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7481281161308289},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7368881106376648},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6433892250061035},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6306453943252563},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6290227174758911},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5694133639335632},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.568436861038208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5647451281547546},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4866279065608978},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4522772431373596},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43556737899780273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41746607422828674},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3689790964126587},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3231637477874756},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10138645768165588},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1999965501","https://openalex.org/W2127141656","https://openalex.org/W2739883972","https://openalex.org/W2886025712","https://openalex.org/W2936774411","https://openalex.org/W2963250244","https://openalex.org/W2965373594","https://openalex.org/W3007776460","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3015686596","https://openalex.org/W3016010032","https://openalex.org/W3096798607","https://openalex.org/W3097777922","https://openalex.org/W3161873870","https://openalex.org/W3163463193","https://openalex.org/W3197898596","https://openalex.org/W3197976839","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/W4288088457","https://openalex.org/W4375869444","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6739901393","https://openalex.org/W6766673545","https://openalex.org/W6769806307","https://openalex.org/W6774538274","https://openalex.org/W6791650154","https://openalex.org/W6847047051"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W2126322296"],"abstract_inverted_index":{"Traditional":[0],"automatic":[1],"speech":[2,14,123,127],"recognition":[3],"(ASR)":[4],"systems":[5],"usually":[6],"focus":[7],"on":[8,142],"individual":[9],"utterances,":[10],"without":[11],"considering":[12],"long-form":[13,82,96,122],"with":[15,85,102,147],"useful":[16],"historical":[17],"information,":[18],"which":[19,78],"is":[20,49,140],"more":[21],"practical":[22],"in":[23,41],"real":[24,67],"scenarios.":[25],"Simply":[26],"attending":[27],"longer":[28],"transcription":[29],"history":[30],"for":[31],"a":[32,51,66,103],"vanilla":[33],"neural":[34,62],"transducer":[35,63],"model":[36],"shows":[37],"no":[38],"much":[39],"gain":[40],"our":[42,137],"preliminary":[43],"experiments,":[44],"since":[45],"the":[46,60,70,75,80,86,89,99,111,116,121,125,131],"prediction":[47],"network":[48],"not":[50],"pure":[52],"language":[53,68],"model.":[54],"This":[55],"motivates":[56],"us":[57],"to":[58,108,124],"leverage":[59],"factorized":[61],"structure,":[64],"containing":[65],"model,":[69],"vocabulary":[71,90,100],"predictor.":[72],"We":[73],"propose":[74,115],"LongFNT-Text":[76],"architecture,":[77],"fuses":[79],"sentence-level":[81],"features":[83,97],"directly":[84],"output":[87],"of":[88,136],"predictor":[91],"and":[92,129,144,149],"then":[93],"embeds":[94],"token-level":[95],"inside":[98],"predictor,":[101],"pre-trained":[104],"contextual":[105],"encoder":[106],"RoBERTa":[107],"further":[109],"boost":[110],"performance.":[112,133],"Moreover,":[113],"we":[114],"LongFNT":[117,138],"architecture":[118],"by":[119],"extending":[120],"original":[126],"input":[128],"achieve":[130],"best":[132],"The":[134],"effectiveness":[135],"approach":[139],"validated":[141],"LibriSpeech":[143],"GigaSpeech":[145],"corpora":[146],"19%":[148],"12%":[150],"relative":[151],"word":[152],"error":[153],"rate":[154],"(WER)":[155],"reduction,":[156],"respectively.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}