{"id":"https://openalex.org/W4400033261","doi":"https://doi.org/10.1109/taslp.2024.3419421","title":"Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition","display_name":"Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400033261","doi":"https://doi.org/10.1109/taslp.2024.3419421"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3419421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3419421","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":["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/A5068367173","display_name":"Keqi Deng","orcid":"https://orcid.org/0000-0003-1490-963X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Keqi Deng","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068367173"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.695,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74095999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"32","issue":null,"first_page":"3507","last_page":"3516"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.7610355615615845},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7095518112182617},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.6494737267494202},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6313608288764954},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6010592579841614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5855446457862854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49930572509765625},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4574034512042999},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43312498927116394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34154456853866577},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.159479558467865},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15336862206459045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07837653160095215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610355615615845},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7095518112182617},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.6494737267494202},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6313608288764954},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6010592579841614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5855446457862854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49930572509765625},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4574034512042999},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43312498927116394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34154456853866577},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.159479558467865},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15336862206459045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07837653160095215},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3419421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3419421","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321848","display_name":"Cambridge Trust","ror":"https://ror.org/05sprqy15"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1494198834","https://openalex.org/W1586176709","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2143612262","https://openalex.org/W2144499799","https://openalex.org/W2147768505","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2327501763","https://openalex.org/W2766219058","https://openalex.org/W2888779557","https://openalex.org/W2962780374","https://openalex.org/W2964539095","https://openalex.org/W2972977747","https://openalex.org/W3015686596","https://openalex.org/W3016010032","https://openalex.org/W3016167541","https://openalex.org/W3016234571","https://openalex.org/W3095311338","https://openalex.org/W3096686110","https://openalex.org/W3096702180","https://openalex.org/W3097777922","https://openalex.org/W3122931219","https://openalex.org/W3148654612","https://openalex.org/W3152221657","https://openalex.org/W3155427814","https://openalex.org/W3160475509","https://openalex.org/W3161873870","https://openalex.org/W3162244132","https://openalex.org/W3163560333","https://openalex.org/W3193461931","https://openalex.org/W3198368663","https://openalex.org/W3198439131","https://openalex.org/W3198771897","https://openalex.org/W3202419788","https://openalex.org/W3203453034","https://openalex.org/W3205201903","https://openalex.org/W3205788551","https://openalex.org/W3206573929","https://openalex.org/W3211278025","https://openalex.org/W4210663600","https://openalex.org/W4224663354","https://openalex.org/W4225299129","https://openalex.org/W4226158189","https://openalex.org/W4283031490","https://openalex.org/W4283741996","https://openalex.org/W4312203699","https://openalex.org/W4319862418","https://openalex.org/W4375869444","https://openalex.org/W4383605108","https://openalex.org/W4385245566","https://openalex.org/W4385567350","https://openalex.org/W4385823261","https://openalex.org/W6601894380","https://openalex.org/W6623517193","https://openalex.org/W6691770337","https://openalex.org/W6809946113","https://openalex.org/W6854240803"],"related_works":["https://openalex.org/W2012283803","https://openalex.org/W4384820447","https://openalex.org/W2072454424","https://openalex.org/W2117438306","https://openalex.org/W2185942010","https://openalex.org/W2260725127","https://openalex.org/W2004297762","https://openalex.org/W1992056405","https://openalex.org/W1966826629","https://openalex.org/W767846903"],"abstract_inverted_index":{"Although":[0],"end-to-end":[1],"(E2E)":[2],"automatic":[3],"speech":[4],"recognition":[5,10],"(ASR)":[6],"has":[7],"shown":[8],"state-of-the-art":[9],"accuracy,":[11],"it":[12,56],"tends":[13],"to":[14,40,93,119,132],"be":[15,80,106],"implicitly":[16],"biased":[17],"towards":[18],"the":[19,58,69,95,136],"training":[20],"data":[21,164],"distribution":[22],"which":[23,35,78],"can":[24,79,105],"degrade":[25],"generalisation.":[26],"This":[27],"paper":[28],"proposes":[29],"a":[30,37,50,74,112,140],"label-synchronous":[31],"neural":[32,134],"transducer":[33],"(LS-Transducer),":[34],"provides":[36],"natural":[38],"approach":[39],"domain":[41],"adaptation":[42],"based":[43],"on":[44,158],"text-only":[45,84],"data.":[46,85],"The":[47],"LS-Transducer":[48,138],"extracts":[49],"label-level":[51,96],"encoder":[52,97],"representation":[53,98],"before":[54],"combining":[55],"with":[57,126,165],"prediction":[59,70,168],"network":[60,71],"output.":[61],"Since":[62],"blank":[63],"tokens":[64],"are":[65],"no":[66],"longer":[67],"needed,":[68],"performs":[72],"as":[73,150,152],"standard":[75,133],"language":[76],"model,":[77],"easily":[81],"adapted":[82,167],"using":[83],"An":[86],"Auto-regressive":[87],"Integrate-and-Fire":[88],"(AIF)":[89],"mechanism":[90],"is":[91,117],"proposed":[92,137],"generate":[94],"while":[99,123],"retaining":[100,124],"low":[101],"latency":[102],"operation":[103],"that":[104,130],"used":[107],"for":[108,146],"streaming.":[109],"In":[110],"addition,":[111],"streaming":[113],"joint":[114],"decoding":[115],"method":[116],"designed":[118],"improve":[120],"ASR":[121],"accuracy":[122],"synchronisation":[125],"AIF.":[127],"Experiments":[128],"show":[129],"compared":[131],"transducers,":[135],"gave":[139],"12.9%":[141],"relative":[142,156],"WER":[143],"reduction":[144],"(WERR)":[145],"intra-domain":[147],"LibriSpeech":[148],"data,":[149],"well":[151],"21.4%":[153],"and":[154,162],"24.6%":[155],"WERRs":[157],"cross-domain":[159],"TED-LIUM":[160],"2":[161],"AESRC2020":[163],"an":[166],"network.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}