{"id":"https://openalex.org/W4372260552","doi":"https://doi.org/10.1109/icassp49357.2023.10095083","title":"Unsupervised Model-Based Speaker Adaptation of End-To-End Lattice-Free MMI Model for Speech Recognition","display_name":"Unsupervised Model-Based Speaker Adaptation of End-To-End Lattice-Free MMI Model for Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260552","doi":"https://doi.org/10.1109/icassp49357.2023.10095083"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095083","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":"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/A5035857878","display_name":"Xurong Xie","orcid":"https://orcid.org/0000-0002-6714-6296"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Institute of Software,Chinese Academy of Sciences,China","Chinese Academy of Sciences, Institute of Software, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210128818"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Software, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114375874","display_name":"Hui Chen","orcid":"https://orcid.org/0000-0002-9840-4876"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Chen","raw_affiliation_strings":["Institute of Software,Chinese Academy of Sciences,China","Chinese Academy of Sciences, Institute of Software, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210128818"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Software, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013118329","display_name":"Hongan Wang","orcid":"https://orcid.org/0000-0002-9320-4920"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongan Wang","raw_affiliation_strings":["Institute of Software,Chinese Academy of Sciences,China","Chinese Academy of Sciences, Institute of Software, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software,Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210128818"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Software, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9891999959945679,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7576178312301636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7059540748596191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6939584612846375},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.55997234582901},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48620742559432983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3592148721218109},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0728892982006073}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7576178312301636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7059540748596191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6939584612846375},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.55997234582901},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48620742559432983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3592148721218109},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0728892982006073},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095083","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/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W70088150","https://openalex.org/W82936479","https://openalex.org/W130324013","https://openalex.org/W854541894","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1567690964","https://openalex.org/W1586532344","https://openalex.org/W1599512239","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2094147890","https://openalex.org/W2106119541","https://openalex.org/W2121981798","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2146871184","https://openalex.org/W2239847623","https://openalex.org/W2276408190","https://openalex.org/W2327501763","https://openalex.org/W2407299475","https://openalex.org/W2514741789","https://openalex.org/W2594610113","https://openalex.org/W2805745502","https://openalex.org/W2808939837","https://openalex.org/W2889282842","https://openalex.org/W2891980359","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2939173691","https://openalex.org/W2962940707","https://openalex.org/W2964182776","https://openalex.org/W2972692349","https://openalex.org/W2972799770","https://openalex.org/W3007550212","https://openalex.org/W3080248383","https://openalex.org/W3094841848","https://openalex.org/W3097747488","https://openalex.org/W3097777922","https://openalex.org/W3113244915","https://openalex.org/W3125118953","https://openalex.org/W3161365423","https://openalex.org/W3194334755","https://openalex.org/W3198654230","https://openalex.org/W4221151563","https://openalex.org/W4224518768","https://openalex.org/W4283654390","https://openalex.org/W4296069265","https://openalex.org/W6605298800","https://openalex.org/W6607114211","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6752334204"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"Modeling":[0],"the":[1,17,62,79,84,94,118,124,133,150,166,175,190],"speaker":[2,28,37,44],"variability":[3],"is":[4,58,110],"a":[5],"key":[6],"challenge":[7],"for":[8,46,112],"automatic":[9],"speech":[10],"recognition":[11],"(ASR)":[12],"systems.":[13,202],"In":[14],"this":[15],"paper,":[16],"learning":[18],"hidden":[19],"unit":[20],"contributions":[21],"(LHUC)":[22],"based":[23,144],"adaptation":[24,45,56,113,137],"techniques":[25],"with":[26],"compact":[27],"dependent":[29],"(SD)":[30],"parameters":[31,64],"are":[32,89,187],"used":[33,111],"to":[34,60,92,116,139,161,189],"facilitate":[35],"both":[36],"adaptive":[38],"training":[39],"(SAT)":[40],"and":[41,70,102,163,169,173,182,198],"unsupervised":[42,54,135],"test-time":[43],"end-to-end":[47],"(E2E)":[48],"lattice-free":[49],"MMI":[50],"(LF-MMI)":[51],"models.":[52,105],"An":[53],"model-based":[55],"framework":[57,138],"proposed":[59,134],"estimate":[61],"SD":[63],"in":[65,132,178],"E2E":[66,99,136,145,201],"paradigm":[67],"using":[68],"LF-MMI":[69,100,146,195],"cross":[71],"entropy":[72],"(CE)":[73],"criterions.":[74],"Various":[75],"regularization":[76],"methods":[77],"of":[78,96,180,192],"standard":[80],"LHUC":[81,86],"adaptation,":[82,88],"e.g.,":[83],"Bayesian":[85],"(BLHUC)":[87],"systematically":[90],"investigated":[91],"mitigate":[93],"risk":[95],"overfitting,":[97],"on":[98,123,165],"CNN-TDNN":[101],"CNN-TDNN-":[103],"BLSTM":[104],"Lattice-based":[106],"confidence":[107],"score":[108],"estimation":[109],"data":[114],"selection":[115],"reduce":[117],"supervision":[119],"label":[120],"uncertainty.":[121],"Experiments":[122],"300-hour":[125],"Switchboard":[126],"task":[127],"suggest":[128],"that,":[129],"applying":[130],"BLHUC":[131],"byte":[140],"pair":[141],"encoding":[142],"(BPE)":[143],"systems":[147,152,197],"consistently":[148],"outperformed":[149],"baseline":[151],"by":[153],"relative":[154],"word":[155],"error":[156],"rate":[157],"(WER)":[158],"reductions":[159],"up":[160],"10.5%":[162],"14.7%":[164],"NIST":[167],"Hub5\u201900":[168],"RT03":[170],"evaluation":[171],"sets,":[172],"achieved":[174],"best":[176],"performance":[177],"WERs":[179],"9.0%":[181],"9.7%,":[183],"respectively.":[184],"These":[185],"results":[186,191],"comparable":[188],"state-of-the-art":[193],"adapted":[194,199],"hybrid":[196],"Conformer-based":[200]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}