{"id":"https://openalex.org/W4408352970","doi":"https://doi.org/10.1109/icassp49660.2025.10887883","title":"A Domain Adaptation Framework for Speech Recognition Systems with Only Synthetic data","display_name":"A Domain Adaptation Framework for Speech Recognition Systems with Only Synthetic data","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352970","doi":"https://doi.org/10.1109/icassp49660.2025.10887883"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5103277708","display_name":"Minh Tran","orcid":"https://orcid.org/0009-0004-2391-3563"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minh Tran","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846108","display_name":"Yutong Pang","orcid":"https://orcid.org/0000-0003-4829-4741"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutong Pang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075310174","display_name":"Debjyoti Paul","orcid":"https://orcid.org/0000-0001-8057-399X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debjyoti Paul","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111196070","display_name":"Laxmi Pandey","orcid":"https://orcid.org/0000-0002-4751-0660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laxmi Pandey","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kevin Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Jiang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103232491","display_name":"Jinxi Guo","orcid":"https://orcid.org/0000-0001-9563-7351"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinxi Guo","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317809","display_name":"Lian Li","orcid":"https://orcid.org/0000-0003-4700-1134"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100415451","display_name":"Shun Zhang","orcid":"https://orcid.org/0009-0004-3319-6596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shun Zhang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646177","display_name":"Xuedong Zhang","orcid":"https://orcid.org/0000-0003-2456-2342"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuedong Zhang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101736394","display_name":"Xin Lei","orcid":"https://orcid.org/0000-0001-6488-3875"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Lei","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5103277708"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"],"apc_list":null,"apc_paid":null,"fwci":9.8967,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97548078,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"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":0.9955000281333923,"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":0.9955000281333923,"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":0.9347000122070312,"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":0.7867552042007446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6892880201339722},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6360720992088318},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5244731903076172},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4502876400947571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3803214728832245},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33941054344177246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867552042007446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6892880201339722},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6360720992088318},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5244731903076172},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4502876400947571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3803214728832245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33941054344177246},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2587088898","https://openalex.org/W2889423969","https://openalex.org/W2912668608","https://openalex.org/W2963364041","https://openalex.org/W3008008574","https://openalex.org/W3162244132","https://openalex.org/W3198004110","https://openalex.org/W4392904112","https://openalex.org/W4401042743","https://openalex.org/W6639480849","https://openalex.org/W6738045163","https://openalex.org/W6739901393","https://openalex.org/W6796581206","https://openalex.org/W6847363464","https://openalex.org/W6853432749","https://openalex.org/W6858704499","https://openalex.org/W6859083102","https://openalex.org/W6863792614"],"related_works":["https://openalex.org/W4394775207","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W3203792196","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W2955455867","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"We":[0,73,130],"introduce":[1,74],"DAS":[2,32,134],"(Domain":[3],"Adaptation":[4],"with":[5,60,118,156],"Synthetic":[6],"data),":[7],"a":[8,75],"novel":[9,76],"domain":[10],"adaptation":[11],"framework":[12],"for":[13,64],"pre-trained":[14],"ASR":[15],"model,":[16,117],"designed":[17],"to":[18,21,39,47,57,107,114,150],"efficiently":[19,87,136],"adapt":[20],"various":[22],"language-defined":[23],"domains":[24,66,112],"without":[25],"requiring":[26],"any":[27],"real":[28],"data.":[29],"In":[30],"particular,":[31],"first":[33],"prompts":[34],"large":[35],"language":[36],"models":[37],"(LLMs)":[38],"generate":[40],"domain-specific":[41],"texts":[42,46],"before":[43],"converting":[44],"these":[45],"speech":[48],"via":[49],"text-to-speech":[50],"technology.":[51],"The":[52],"synthetic":[53],"data":[54],"is":[55],"used":[56],"finetune":[58],"Whisper":[59],"Low-Rank":[61],"Adapters":[62],"(LoRAs)":[63],"targeted":[65],"such":[67],"as":[68],"music,":[69],"weather,":[70],"and":[71],"sports.":[72],"one-pass":[77],"decoding":[78],"strategy":[79],"that":[80,133],"merges":[81],"predictions":[82],"from":[83],"multiple":[84],"LoRA":[85,158],"adapters":[86],"during":[88,137],"the":[89,100,115,151],"auto-regressive":[90],"text":[91],"generation":[92],"process.":[93],"Experimental":[94],"results":[95],"show":[96],"significant":[97],"improvements,":[98],"reducing":[99],"Word":[101],"Error":[102],"Rate":[103],"(WER)":[104],"by":[105],"10%":[106],"17%":[108],"across":[109],"all":[110],"target":[111],"compared":[113,149],"original":[116,152],"minimal":[119],"performance":[120],"regression":[121],"in":[122,144],"out-of-domain":[123],"settings":[124],"\u22121%":[125],"on":[126],"Librispeech":[127],"test":[128],"sets.":[129],"also":[131],"demonstrate":[132],"operates":[135],"inference,":[138],"introducing":[139],"an":[140],"additional":[141],"9%":[142],"increase":[143],"Real":[145],"Time":[146],"Factor":[147],"(RTF)":[148],"model":[153],"when":[154],"inferring":[155],"three":[157],"adapters.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-05-15T08:27:34.491423","created_date":"2025-10-10T00:00:00"}