{"id":"https://openalex.org/W4408354843","doi":"https://doi.org/10.1109/icassp49660.2025.10889979","title":"Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition","display_name":"Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354843","doi":"https://doi.org/10.1109/icassp49660.2025.10889979"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889979","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":"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/A5006997733","display_name":"Chien-Chun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Chun Wang","raw_affiliation_strings":["National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625784","display_name":"Liwei Chen","orcid":"https://orcid.org/0000-0002-9858-0765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li-Wei Chen","raw_affiliation_strings":["United-Link Co., Ltd,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"United-Link Co., Ltd,Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng-Kang Chou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng-Kang Chou","raw_affiliation_strings":["United-Link Co., Ltd,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"United-Link Co., Ltd,Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["United-Link Co., Ltd,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"United-Link Co., Ltd,Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048512827","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica,Institute of Computer Science,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Institute of Computer Science,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5234,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93676055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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":0.9728999733924866,"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":0.7902207970619202},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7107059359550476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6456434726715088},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5256946086883545},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4681307077407837},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4239780306816101},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4123944938182831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33749136328697205},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.29369068145751953},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.17164140939712524},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05596175789833069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902207970619202},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7107059359550476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6456434726715088},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5256946086883545},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4681307077407837},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4239780306816101},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4123944938182831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33749136328697205},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.29369068145751953},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.17164140939712524},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05596175789833069},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889979","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":28,"referenced_works":["https://openalex.org/W2760103357","https://openalex.org/W2889326414","https://openalex.org/W2891138528","https://openalex.org/W2902772991","https://openalex.org/W3026041220","https://openalex.org/W3095838132","https://openalex.org/W3097777922","https://openalex.org/W3106784978","https://openalex.org/W3108316907","https://openalex.org/W3160525311","https://openalex.org/W3196667132","https://openalex.org/W3196733780","https://openalex.org/W3197507772","https://openalex.org/W4221154745","https://openalex.org/W4221156109","https://openalex.org/W4226189894","https://openalex.org/W4313225456","https://openalex.org/W4375868977","https://openalex.org/W4393406219","https://openalex.org/W4402111962","https://openalex.org/W4405440098","https://openalex.org/W6631190155","https://openalex.org/W6756568514","https://openalex.org/W6780218876","https://openalex.org/W6791904447","https://openalex.org/W6838276489","https://openalex.org/W6846618144","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501"],"abstract_inverted_index":{"While":[0],"pre-trained":[1],"automatic":[2],"speech":[3,93,98],"recognition":[4],"(ASR)":[5],"systems":[6],"demonstrate":[7],"impressive":[8],"performance":[9,14],"on":[10,121],"matched":[11],"domains,":[12],"their":[13],"often":[15],"degrades":[16],"when":[17],"confronted":[18],"with":[19],"channel":[20,63,76,111],"mismatch":[21],"stemming":[22],"from":[23,69],"unseen":[24],"recording":[25],"environments":[26],"and":[27,54,87,128,143,167],"conditions.":[28],"To":[29],"mitigate":[30],"this":[31],"issue,":[32],"we":[33],"propose":[34],"a":[35,62,81,91],"novel":[36],"channel-aware":[37,157],"data":[38,86,158],"simulation":[39,159],"method":[40,46,120,160],"for":[41,161],"robust":[42],"ASR":[43],"training.":[44],"Our":[45],"harnesses":[47],"the":[48,102,106,110,114,122,148,153,163],"synergistic":[49],"power":[50],"of":[51,66,74,84,105,113,141,155],"channel-extractive":[52],"techniques":[53],"generative":[55],"adversarial":[56],"networks":[57],"(GANs).":[58],"We":[59,117],"first":[60],"train":[61],"encoder":[64],"capable":[65],"extracting":[67],"embeddings":[68,77],"arbitrary":[70],"audio.":[71],"On":[72],"top":[73],"this,":[75],"are":[78],"extracted":[79],"using":[80],"minimal":[82],"amount":[83],"target-domain":[85,168],"used":[88],"to":[89,147],"guide":[90],"GAN-based":[92],"synthesizer.":[94],"This":[95],"synthesizer":[96],"generates":[97],"that":[99],"faithfully":[100],"preserves":[101],"phonetic":[103],"content":[104],"input":[107],"while":[108],"mimicking":[109],"characteristics":[112],"target":[115],"domain.":[116],"evaluate":[118],"our":[119,156],"challenging":[123],"Hakka":[124],"Across":[125,130],"Taiwan":[126,131],"(HAT)":[127],"Taiwanese":[129],"(TAT)":[132],"corpora,":[133],"achieving":[134],"relative":[135],"character":[136],"error":[137],"rate":[138],"(CER)":[139],"reductions":[140],"20.02%":[142],"9.64%,":[144],"respectively,":[145],"compared":[146],"baselines.":[149],"These":[150],"results":[151],"highlight":[152],"efficacy":[154],"bridging":[162],"gap":[164],"between":[165],"source-":[166],"acoustics.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
