{"id":"https://openalex.org/W4392910813","doi":"https://doi.org/10.1109/icassp48485.2024.10446365","title":"Accent-Specific Vector Quantization for Joint Unsupervised and Supervised Training in Accent Robust Speech Recognition","display_name":"Accent-Specific Vector Quantization for Joint Unsupervised and Supervised Training in Accent Robust Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910813","doi":"https://doi.org/10.1109/icassp48485.2024.10446365"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5106407830","display_name":"Li Li","orcid":"https://orcid.org/0000-0003-2990-1614"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,Shanghai,China","Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,Shanghai,China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039983089","display_name":"Yijie Li","orcid":"https://orcid.org/0009-0004-3636-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijie Li","raw_affiliation_strings":["Unisound AI Technology Co., Ltd.,Beijing,China","Unisound AI Technology Co., Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072265807","display_name":"Dongxing Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongxing Xu","raw_affiliation_strings":["Unisound AI Technology Co., Ltd.,Beijing,China","Unisound AI Technology Co., Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019789898","display_name":"Haoran Wei","orcid":"https://orcid.org/0000-0002-0666-5551"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoran Wei","raw_affiliation_strings":["University of Texas at Dallas,Department of ECE,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Department of ECE,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,Shanghai,China","Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,Shanghai,China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10201","last_page":"10205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9814000129699707,"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":0.9814000129699707,"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":0.9611999988555908,"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/stress","display_name":"Stress (linguistics)","score":0.7528414726257324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.702330470085144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.680378794670105},{"id":"https://openalex.org/keywords/learning-vector-quantization","display_name":"Learning vector quantization","score":0.6412683725357056},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6141660213470459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6040703058242798},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5800430774688721},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4815285801887512},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46017590165138245},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4414482116699219},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08865711092948914}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7528414726257324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.702330470085144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680378794670105},{"id":"https://openalex.org/C40567965","wikidata":"https://www.wikidata.org/wiki/Q1820283","display_name":"Learning vector quantization","level":3,"score":0.6412683725357056},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6141660213470459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6040703058242798},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5800430774688721},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4815285801887512},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46017590165138245},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4414482116699219},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08865711092948914},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G514874842","display_name":"\u4f4e\u8d44\u6e90\u6761\u4ef6\u4e0b\u7684\u91cd\u53e3\u97f3\u9c81\u68d2\u6027\u58f0\u5b66\u5efa\u6a21\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62071302","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1902237438","https://openalex.org/W2127141656","https://openalex.org/W2183341477","https://openalex.org/W2889494795","https://openalex.org/W2936774411","https://openalex.org/W2938374794","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2962893195","https://openalex.org/W2973094925","https://openalex.org/W3044481399","https://openalex.org/W3095311338","https://openalex.org/W3096686110","https://openalex.org/W3097777922","https://openalex.org/W3104215796","https://openalex.org/W3160235762","https://openalex.org/W3160987270","https://openalex.org/W3162812479","https://openalex.org/W3163152557","https://openalex.org/W3186596101","https://openalex.org/W3197561413","https://openalex.org/W3212799896","https://openalex.org/W4210663600","https://openalex.org/W4292387508","https://openalex.org/W4372260408","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6788335241","https://openalex.org/W6799245484","https://openalex.org/W6802472062"],"related_works":["https://openalex.org/W2100968651","https://openalex.org/W4243803532","https://openalex.org/W2142248489","https://openalex.org/W2352648934","https://openalex.org/W4230688072","https://openalex.org/W1915693853","https://openalex.org/W1530525041","https://openalex.org/W2378212145","https://openalex.org/W2798892016","https://openalex.org/W2202992072"],"abstract_inverted_index":{"How":[0],"to":[1,8,36,59,102],"effectively":[2],"use":[3],"limited":[4],"supervised":[5,29],"accent":[6],"data":[7],"improve":[9],"the":[10,61,70,91,95],"accented":[11,73,82,109],"ASR":[12,34,74,86],"is":[13],"of":[14,32,43,72],"paramount":[15],"importance.":[16],"In":[17],"this":[18,38],"work,":[19],"we":[20],"propose":[21],"an":[22],"accent-specific":[23],"quantization":[24],"for":[25],"joint":[26],"unsupervised":[27],"and":[28,49,56,63,84],"training":[30,57],"(AQ-JUST)":[31],"end-to-end":[33],"models":[35],"address":[37],"issue.":[39],"Specifically,":[40],"two":[41],"variants":[42],"AQ-JUST":[44],"are":[45,78],"investigated,":[46],"namely":[47],"BAQ-JUST":[48],"SAQ-JUST,":[50],"by":[51,99],"employing":[52],"different":[53],"model":[54],"structures":[55],"methods":[58,93],"capture":[60],"distinctiveness":[62],"commonalities":[64],"between":[65],"diverse":[66],"accents,":[67],"thus":[68],"enhancing":[69],"performance":[71],"systems.":[75],"Our":[76],"experiments":[77],"performed":[79],"on":[80,108],"both":[81],"English":[83],"Mandarin":[85],"tasks.":[87],"Results":[88],"show":[89],"that":[90],"proposed":[92],"outperform":[94],"strong":[96],"JUST":[97],"baseline":[98],"relative":[100],"3.9%":[101],"9.4%":[103],"word/character":[104],"error":[105],"rate":[106],"reductions":[107],"test":[110],"sets.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}