{"id":"https://openalex.org/W4402351683","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650455","title":"Decoupling-Enhanced Vietnamese Speech Recognition Accent Adaptation Supervised by Prosodic Domain Information","display_name":"Decoupling-Enhanced Vietnamese Speech Recognition Accent Adaptation Supervised by Prosodic Domain Information","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351683","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650455"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650455","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5104111230","display_name":"Yanwen Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwen Fang","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107954117","display_name":"Wenjun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Wang","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068973438","display_name":"Ling Dong","orcid":"https://orcid.org/0000-0003-1612-6671"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Dong","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017471172","display_name":"Shengxiang Gao","orcid":"https://orcid.org/0000-0002-2980-8420"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Gao","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101002499","display_name":"Hua Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Lai","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108312981","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-9525-9060"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China","institution_ids":["https://openalex.org/I10660446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10660446"],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54292459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8057346343994141},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7686543464660645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314000725746155},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.7247080206871033},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6598930954933167},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5829527378082275},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5357237458229065},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.5129448771476746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4748813509941101},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4328674077987671},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4296095371246338},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.3738211393356323},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21835395693778992},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15966546535491943},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11227753758430481}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8057346343994141},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7686543464660645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314000725746155},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.7247080206871033},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6598930954933167},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5829527378082275},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5357237458229065},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.5129448771476746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4748813509941101},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4328674077987671},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4296095371246338},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.3738211393356323},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21835395693778992},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15966546535491943},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11227753758430481},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650455","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2327501763","https://openalex.org/W2889494795","https://openalex.org/W2890964092","https://openalex.org/W2962684181","https://openalex.org/W2962780374","https://openalex.org/W2962893195","https://openalex.org/W2973094925","https://openalex.org/W3015723617","https://openalex.org/W3018242354","https://openalex.org/W3036601975","https://openalex.org/W3044481399","https://openalex.org/W3094861840","https://openalex.org/W3161909236","https://openalex.org/W3162061711","https://openalex.org/W3162812479","https://openalex.org/W3174329270","https://openalex.org/W3194701944","https://openalex.org/W4221040649","https://openalex.org/W4313225742","https://openalex.org/W4319586290","https://openalex.org/W4319586935","https://openalex.org/W6631362777","https://openalex.org/W6639480849","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W2507083698","https://openalex.org/W2465473908","https://openalex.org/W49590631","https://openalex.org/W2370788932","https://openalex.org/W4301230705","https://openalex.org/W2474947928","https://openalex.org/W2967415048","https://openalex.org/W1489682032"],"abstract_inverted_index":{"The":[0],"northern":[1,101],"and":[2,15,43,63,102],"southern":[3,36,103],"accents":[4,37],"of":[5,13,32,91,96,100,113],"the":[6,73,88,97,116,125],"Vietnamese":[7,18,39,104,114,129],"exhibit":[8],"pronunciation":[9,89],"differences":[10],"in":[11,25,38,47,128],"terms":[12],"tones":[14],"rhythms.":[16],"Existing":[17],"pre-trained":[19,74],"speech":[20,40,75,130],"models":[21,42,132],"show":[22],"a":[23,30,44,55,111],"bias":[24],"accent":[26,64,135],"representation,":[27],"leading":[28],"to":[29],"lack":[31],"generalization":[33],"capability":[34],"for":[35],"recognition":[41,48,131],"noticeable":[45],"decrease":[46],"accuracy.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,86],"propose":[54],"decoupled-enhanced":[56],"adaptive":[57,94],"representation":[58,95],"strategy":[59],"guided":[60],"by":[61,82,134],"prosody":[62],"domain":[65],"label":[66],"information.":[67],"Through":[68],"Domain":[69],"Adversarial":[70],"Training":[71],"(DAT),":[72],"model":[76],"decouples":[77],"domain-invariant":[78],"content":[79],"features.":[80],"Simultaneously,":[81],"incorporating":[83],"prosodic":[84],"features,":[85],"enhance":[87],"information":[90],"Vietnamese,":[92],"enabling":[93],"distinctive":[98],"characteristics":[99],"accents.":[105],"Evaluating":[106],"our":[107],"proposed":[108],"method":[109],"on":[110],"dataset":[112],"accents,":[115],"results":[117],"demonstrate":[118],"its":[119],"superiority":[120],"over":[121],"existing":[122],"approaches,":[123],"mitigating":[124],"performance":[126],"degradation":[127],"caused":[133],"differences.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
