{"id":"https://openalex.org/W4372270200","doi":"https://doi.org/10.1109/icassp49357.2023.10096577","title":"Adaptive Multi-Corpora Language Model Training for Speech Recognition","display_name":"Adaptive Multi-Corpora Language Model Training for Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372270200","doi":"https://doi.org/10.1109/icassp49357.2023.10096577"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096577","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/A5103207430","display_name":"Yingyi Ma","orcid":"https://orcid.org/0000-0002-0205-0197"},"institutions":[{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yingyi Ma","raw_affiliation_strings":["Meta AI,Menlo Park,CA,USA","Meta AI, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,Menlo Park,CA,USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462347","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0001-8578-2635"},"institutions":[{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["Meta AI,Menlo Park,CA,USA","Meta AI, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,Menlo Park,CA,USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100646177","display_name":"Xuedong Zhang","orcid":"https://orcid.org/0000-0003-2456-2342"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuedong Zhang","raw_affiliation_strings":["Meta AI,Menlo Park,CA,USA","Meta AI, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,Menlo Park,CA,USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103207430"],"corresponding_institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63063273,"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":"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":0.9986000061035156,"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":0.9958000183105469,"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":0.8824572563171387},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6227490901947021},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6093970537185669},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6046572327613831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5796025991439819},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5598562359809875},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5547213554382324},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5488609671592712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5441648960113525},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5287085771560669},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5108451247215271},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48074841499328613},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47402575612068176},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47385314106941223},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4184044897556305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4109848141670227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8824572563171387},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6227490901947021},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6093970537185669},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6046572327613831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5796025991439819},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5598562359809875},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5547213554382324},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5488609671592712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5441648960113525},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5287085771560669},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5108451247215271},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48074841499328613},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47402575612068176},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47385314106941223},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4184044897556305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4109848141670227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096577","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":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1494108583","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2020073413","https://openalex.org/W2026149468","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2397868525","https://openalex.org/W2437096199","https://openalex.org/W2795282075","https://openalex.org/W2802201485","https://openalex.org/W2802422770","https://openalex.org/W2885771996","https://openalex.org/W2891244534","https://openalex.org/W2903732155","https://openalex.org/W2943845043","https://openalex.org/W2947380870","https://openalex.org/W2963240019","https://openalex.org/W2963854351","https://openalex.org/W2972320704","https://openalex.org/W3015484572","https://openalex.org/W3034938700","https://openalex.org/W3097714942","https://openalex.org/W3123350987","https://openalex.org/W3155915517","https://openalex.org/W3162072286","https://openalex.org/W3162193499","https://openalex.org/W3162639446","https://openalex.org/W3162665866","https://openalex.org/W3206965164","https://openalex.org/W4205411913","https://openalex.org/W4284663685","https://openalex.org/W6638749077","https://openalex.org/W6750523955","https://openalex.org/W6763430915","https://openalex.org/W6803334173"],"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":{"Neural":[0],"network":[1],"language":[2],"model":[3],"(NNLM)":[4],"plays":[5],"an":[6,26],"essential":[7],"role":[8],"in":[9,16],"automatic":[10],"speech":[11],"recognition":[12],"(ASR)":[13],"systems,":[14],"especially":[15],"adaptation":[17,49,137],"tasks":[18],"when":[19],"text-only":[20],"data":[21,35,42],"is":[22,28,45,100],"available.":[23],"In":[24,72],"practice,":[25],"NNLM":[27,69],"typically":[29],"trained":[30],"on":[31,55,133],"a":[32,77],"combination":[33],"of":[34,91],"sampled":[36],"from":[37],"multiple":[38],"corpora.":[39],"Thus,":[40],"the":[41,48,88,95,114],"sampling":[43,58,89,111],"strategy":[44,112],"important":[46],"to":[47,102,123],"performance.":[50],"Most":[51],"existing":[52],"works":[53],"focus":[54],"designing":[56],"static":[57,110],"strategies.":[59],"However,":[60],"each":[61,92],"corpus":[62,93],"may":[63],"show":[64],"varying":[65],"impacts":[66],"at":[67],"different":[68],"training":[70,81,96],"stages.":[71],"this":[73],"paper,":[74],"we":[75],"introduce":[76],"novel":[78],"adaptive":[79],"multi-corpora":[80],"algorithm":[82,99],"that":[83],"dynamically":[84],"learns":[85],"and":[86,105,126,135],"adjusts":[87],"probability":[90],"along":[94],"process.":[97],"The":[98],"robust":[101],"corpora":[103],"sizes":[104],"domain":[106],"relevance.":[107],"Compared":[108],"with":[109],"baselines,":[113],"proposed":[115],"approach":[116],"yields":[117],"remarkable":[118],"improvement":[119],"by":[120],"achieving":[121],"up":[122],"relative":[124],"7%":[125],"9%":[127],"word":[128],"error":[129],"rate":[130],"(WER)":[131],"reductions":[132],"in-domain":[134],"out-of-domain":[136],"tasks,":[138],"respectively.":[139]},"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"}