{"id":"https://openalex.org/W4409819205","doi":"https://doi.org/10.1186/s13636-025-00406-5","title":"Parameter-efficient adaptation with multi-channel adversarial training for far-field speech recognition","display_name":"Parameter-efficient adaptation with multi-channel adversarial training for far-field speech recognition","publication_year":2025,"publication_date":"2025-04-25","ids":{"openalex":"https://openalex.org/W4409819205","doi":"https://doi.org/10.1186/s13636-025-00406-5"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00406-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00406-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00406-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00406-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101583906","display_name":"Tong Niu","orcid":"https://orcid.org/0009-0007-3453-0738"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Tong Niu","raw_affiliation_strings":["Information Engineering University, Zhengzhou, 450000, China","Laboratory for Advanced Computing and Intelligence Engineering, Wuxi, 214000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Engineering University, Zhengzhou, 450000, China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"Laboratory for Advanced Computing and Intelligence Engineering, Wuxi, 214000, China","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101560152","display_name":"Yaqi Chen","orcid":"https://orcid.org/0000-0001-6301-802X"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqi Chen","raw_affiliation_strings":["Information Engineering University, Zhengzhou, 450000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Engineering University, Zhengzhou, 450000, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001488518","display_name":"Dan Qu","orcid":"https://orcid.org/0000-0001-9917-7794"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Dan Qu","raw_affiliation_strings":["Information Engineering University, Zhengzhou, 450000, China","Laboratory for Advanced Computing and Intelligence Engineering, Wuxi, 214000, China"],"raw_orcid":"https://orcid.org/0000-0001-9917-7794","affiliations":[{"raw_affiliation_string":"Information Engineering University, Zhengzhou, 450000, China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"Laboratory for Advanced Computing and Intelligence Engineering, Wuxi, 214000, China","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066809438","display_name":"Hengbo Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153896","display_name":"Zhengzhou Institute of Machinery","ror":"https://ror.org/04r3bvt56","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210153896"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengbo Hu","raw_affiliation_strings":["Research and Development Department, Zhengzhou Xinda Institute of Advanced Technology, Zhengzhou, 450000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Department, Zhengzhou Xinda Institute of Advanced Technology, Zhengzhou, 450000, China","institution_ids":["https://openalex.org/I4210153896"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071560660","display_name":"ChengRan Liu","orcid":"https://orcid.org/0000-0002-5672-2841"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ChengRan Liu","raw_affiliation_strings":["Information Engineering University, Zhengzhou, 450000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Engineering University, Zhengzhou, 450000, China","institution_ids":["https://openalex.org/I169689159"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08884688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8987982273101807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7084773778915405},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6608415246009827},{"id":"https://openalex.org/keywords/near-and-far-field","display_name":"Near and far field","score":0.6126208901405334},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6122381091117859},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6010242700576782},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.569013237953186},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42843446135520935},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41454771161079407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3144903779029846},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.26388922333717346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8987982273101807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7084773778915405},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6608415246009827},{"id":"https://openalex.org/C25227671","wikidata":"https://www.wikidata.org/wiki/Q13405516","display_name":"Near and far field","level":2,"score":0.6126208901405334},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6122381091117859},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6010242700576782},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.569013237953186},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42843446135520935},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41454771161079407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3144903779029846},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.26388922333717346},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00406-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00406-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00406-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:90451b9debca48df993afb097ae99dfb","is_oa":true,"landing_page_url":"https://doaj.org/article/90451b9debca48df993afb097ae99dfb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-10 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00406-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00406-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00406-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2727895085","display_name":null,"funder_award_id":"232300421240","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"},{"id":"https://openalex.org/G4912337242","display_name":null,"funder_award_id":"No.232300421240","funder_id":"https://openalex.org/F4320322866","funder_display_name":"Natural Science Foundation of Hainan Province"},{"id":"https://openalex.org/G7804056170","display_name":null,"funder_award_id":"62171470","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8396178784","display_name":null,"funder_award_id":"No.62171470","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322866","display_name":"Natural Science Foundation of Hainan Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323845","display_name":"Natural Science Foundation of Henan Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409819205.pdf","grobid_xml":"https://content.openalex.org/works/W4409819205.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2148613904","https://openalex.org/W2510867321","https://openalex.org/W2593768305","https://openalex.org/W2900212944","https://openalex.org/W2962780374","https://openalex.org/W3020336359","https://openalex.org/W3086154751","https://openalex.org/W3097263872","https://openalex.org/W4205991051","https://openalex.org/W4225274946","https://openalex.org/W4285247752","https://openalex.org/W4382319414","https://openalex.org/W4385822890","https://openalex.org/W4385987638","https://openalex.org/W4391021530","https://openalex.org/W4391021545","https://openalex.org/W4392904451","https://openalex.org/W6600103761","https://openalex.org/W6910527551"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W4394050964","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Despite":[0],"notable":[1],"advancements":[2],"in":[3,112,120],"automatic":[4],"speech":[5,24,56,123,131],"recognition":[6,25],"(ASR)":[7],"technologies,":[8],"issues":[9],"such":[10],"as":[11],"background":[12],"noise,":[13],"reverberation,":[14],"and":[15,44,158],"speaker":[16],"distance":[17],"still":[18],"degrade":[19],"the":[20,66,83,93,118],"performance":[21],"of":[22,46,79,97,141,156],"far-field":[23],"(FSR).":[26],"Although":[27],"large-scale":[28],"pre-trained":[29],"models":[30],"have":[31],"shown":[32],"promise,":[33],"their":[34],"adaptation":[35],"to":[36,76,116],"FSR":[37,61,89],"is":[38],"hampered":[39],"by":[40,136],"high":[41],"training":[42,104,149],"costs":[43],"risks":[45],"overfitting.":[47],"To":[48,91],"overcome":[49,92],"these":[50],"problems,":[51],"we":[52,99],"introduce":[53],"a":[54,101,109,137],"parameter-efficient":[55],"prefix":[57,132],"tuning":[58,133],"(SPT)":[59],"for":[60,65,86],"based":[62],"on":[63,127],"Whisper":[64],"first":[67],"time.":[68],"This":[69],"method":[70],"uses":[71],"fixed-length":[72],"vector":[73],"sequences":[74],"appended":[75],"input":[77],"features":[78],"each":[80],"layer,":[81],"enhancing":[82],"model\u2019s":[84],"capability":[85],"handling":[87],"complex":[88],"tasks.":[90],"channel":[94,110,177],"interference":[95],"problem":[96],"FSR,":[98],"propose":[100],"multi-channel":[102,147],"adversarial":[103,114,148],"(MCAT)":[105],"approach,":[106],"which":[107],"incorporates":[108],"recognizer":[111],"an":[113,152],"manner":[115],"guide":[117],"model":[119],"learning":[121],"channel-invariant":[122],"representations.":[124],"Experimental":[125],"results":[126],"multiple":[128],"datasets":[129],"demonstrate":[130],"surpasses":[134],"LoRA":[135],"degradation":[138,155],"relative":[139],"WER":[140,154],"5.76%":[142],"with":[143],"fewer":[144],"parameters.":[145],"Moreover,":[146],"further":[150],"achieves":[151],"additional":[153],"3.92%":[157],"3.71%.":[159],"The":[160],"t-SNE":[161],"visualization":[162],"indicates":[163],"that":[164],"MCAT":[165],"clusters":[166],"more":[167],"samples":[168],"from":[169],"different":[170],"channels":[171],"into":[172],"similar":[173],"representations,":[174],"effectively":[175],"reducing":[176],"interference.":[178]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}