{"id":"https://openalex.org/W4408345713","doi":"https://doi.org/10.1109/icassp49660.2025.10890688","title":"Joint Training Framework for Accent and Speech Recognition Based on Conformer Low-Rank Adaptation","display_name":"Joint Training Framework for Accent and Speech Recognition Based on Conformer Low-Rank Adaptation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345713","doi":"https://doi.org/10.1109/icassp49660.2025.10890688"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890688","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/A5044255594","display_name":"Xuyi Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyi Zhuang","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073118994","display_name":"Yukun Qian","orcid":"https://orcid.org/0000-0001-9095-4024"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukun Qian","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086533417","display_name":"Shiyun Xu","orcid":"https://orcid.org/0009-0006-7778-8571"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyun Xu","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009651653","display_name":"Mingjiang Wang","orcid":"https://orcid.org/0000-0002-4706-009X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjiang Wang","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01750598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.6942999958992004,"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":0.6942999958992004,"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":0.599399983882904,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.5662999749183655,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/stress","display_name":"Stress (linguistics)","score":0.7444174289703369},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6878833174705505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6770174503326416},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6691490411758423},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6554275751113892},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5906952619552612},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.551106870174408},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.472040057182312},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44814348220825195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4180833101272583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33388957381248474},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19357722997665405},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1251496970653534},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08901271224021912}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7444174289703369},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6878833174705505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6770174503326416},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6691490411758423},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6554275751113892},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5906952619552612},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.551106870174408},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.472040057182312},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44814348220825195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4180833101272583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33388957381248474},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19357722997665405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1251496970653534},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08901271224021912},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/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/icassp49660.2025.10890688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890688","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2101066392","https://openalex.org/W2194775991","https://openalex.org/W2889494795","https://openalex.org/W2950488390","https://openalex.org/W2964309797","https://openalex.org/W3035422681","https://openalex.org/W3097777922","https://openalex.org/W3160475509","https://openalex.org/W3168867926","https://openalex.org/W3197530164","https://openalex.org/W4283067311","https://openalex.org/W4292387508","https://openalex.org/W4297491209","https://openalex.org/W4319586290","https://openalex.org/W4372266510","https://openalex.org/W4385822407","https://openalex.org/W4388642341","https://openalex.org/W4400903651","https://openalex.org/W4402112032","https://openalex.org/W4402112040","https://openalex.org/W4402112329","https://openalex.org/W6739901393","https://openalex.org/W6790518089","https://openalex.org/W6797037654","https://openalex.org/W6803401863","https://openalex.org/W6856800273","https://openalex.org/W6869749289"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W4213177143","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4252005663","https://openalex.org/W2365914832","https://openalex.org/W2352261042","https://openalex.org/W2314218554"],"abstract_inverted_index":{"In":[0],"real-world":[1],"scenarios,":[2],"accent":[3],"variations":[4,152],"often":[5],"reduce":[6],"Automatic":[7],"Speech":[8,51],"Recognition":[9,21,52],"(ASR)":[10],"accuracy.":[11],"Addressing":[12],"this":[13],"typically":[14],"involves":[15],"a":[16,64],"multi-task":[17],"ASR":[18,36,59,125,144],"and":[19,34,50,60,76,123,131,141,145,153],"Accent":[20,49],"(ASR-AR)":[22],"framework,":[23],"but":[24],"there":[25],"is":[26],"limited":[27],"research":[28],"on":[29,113],"optimizing":[30],"task-specific":[31,85],"feature":[32],"extraction":[33,83],"enhancing":[35],"with":[37,134],"AR":[38,61,120,146],"information.":[39],"This":[40,69],"study":[41],"introduces":[42],"the":[43,73,82,101,114,155],"Conformer":[44],"Low-rank":[45],"Adaptation":[46],"for":[47],"Joint":[48],"(CLAnSR),":[53],"employing":[54],"LoRA":[55],"to":[56,104],"augment":[57],"both":[58,143],"capabilities":[62],"using":[63],"shared":[65],"pre-trained":[66],"base":[67],"encoder.":[68],"approach":[70],"significantly":[71],"reduces":[72,137],"model\u2019s":[74,102],"parameter":[75],"training":[77],"resource":[78],"demands":[79],"while":[80],"facilitating":[81],"of":[84],"features.":[86],"Additionally,":[87],"we":[88],"have":[89],"incorporated":[90],"accent-aware":[91],"multi-channel":[92],"embedding":[93],"layers,":[94],"which":[95],"through":[96],"spatially":[97],"independent":[98],"embeddings,":[99],"enhance":[100],"capacity":[103],"accurately":[105],"represent":[106],"tokens":[107],"across":[108],"diverse":[109],"dialectical":[110],"contexts.":[111],"Tested":[112],"KeSpeech":[115],"dataset,":[116],"CLAnSR":[117],"reaches":[118],"state-of-the-art":[119],"accuracy":[121],"80.41%":[122],"competitive":[124],"CER":[126],"8.39%,":[127],"outperforming":[128],"non-LLM":[129],"systems":[130],"matching":[132],"those":[133],"LLMs.":[135],"It":[136],"parameters":[138],"by":[139],"34.02%":[140],"enhances":[142],"performance,":[147],"effectively":[148],"handling":[149],"speech":[150],"dialect":[151],"advancing":[154],"field.":[156]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}