{"id":"https://openalex.org/W4392903007","doi":"https://doi.org/10.1109/icassp48485.2024.10447979","title":"Cross-Modal Parallel Training for Improving end-to-end Accented Speech Recognition","display_name":"Cross-Modal Parallel Training for Improving end-to-end Accented Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903007","doi":"https://doi.org/10.1109/icassp48485.2024.10447979"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447979","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/A5101319162","display_name":"Renchang Dong","orcid":"https://orcid.org/0009-0001-0216-7897"},"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":"Renchang Dong","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/A5042316448","display_name":"Dongxing Xu","orcid":"https://orcid.org/0000-0001-7445-1398"},"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":"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":1,"institutions_distinct_count":1,"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":"10396","last_page":"10400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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":0.7597486972808838},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6985357403755188},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.696391761302948},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.580765426158905},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5569945573806763},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5313566327095032},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.49021464586257935},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4524478018283844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3704293370246887},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.276455819606781},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10740360617637634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597486972808838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6985357403755188},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.696391761302948},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.580765426158905},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5569945573806763},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5313566327095032},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.49021464586257935},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4524478018283844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3704293370246887},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.276455819606781},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10740360617637634},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447979","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"},{"id":"https://openalex.org/F4320322374","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2101066392","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2587080466","https://openalex.org/W2603679025","https://openalex.org/W2936774411","https://openalex.org/W2938374794","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962893195","https://openalex.org/W2963250244","https://openalex.org/W2963596039","https://openalex.org/W2964099675","https://openalex.org/W2998356391","https://openalex.org/W3015927303","https://openalex.org/W3096686110","https://openalex.org/W3097777922","https://openalex.org/W3160987270","https://openalex.org/W3211278025","https://openalex.org/W4221163209","https://openalex.org/W4292387508","https://openalex.org/W4293363567","https://openalex.org/W4296068417","https://openalex.org/W4375868963","https://openalex.org/W4384938838","https://openalex.org/W6638749077","https://openalex.org/W6756358366","https://openalex.org/W6771467084"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W3031252497"],"abstract_inverted_index":{"Multi-accent":[0],"speech":[1,9,62],"recognition":[2,10],"is":[3,51,84],"a":[4,24,44,55,73,80],"key":[5],"challenge":[6],"in":[7,42],"current":[8],"due":[11],"to":[12,57,86],"the":[13,32,59,90,121,131,135],"pronunciation":[14,76],"variations":[15,71],"of":[16,35],"different":[17,103],"accents.":[18],"In":[19],"this":[20],"study,":[21],"we":[22],"propose":[23],"Cross-modal":[25],"Parallel":[26],"Training":[27],"(CPT)":[28],"approach":[29],"for":[30,97],"improving":[31,98],"accent":[33,70,93],"robustness":[34],"state-of-the-art":[36],"Conformer-Transducer":[37],"(Conformer-T)":[38],"ASR":[39,100,126,157],"system.":[40],"Specifically,":[41],"CPT,":[43],"novel":[45],"cross-modal":[46],"attention":[47],"and":[48,67,92,109],"fusion":[49],"module":[50],"first":[52],"designed":[53],"as":[54],"frontend":[56],"align":[58],"low-level":[60],"acoustic":[61,91],"representations":[63],"with":[64,107],"phonetic":[65,110],"embeddings,":[66],"thus":[68],"normalizing":[69],"into":[72],"shared":[74],"standard":[75],"latent":[77],"space;":[78],"Then,":[79],"parallel":[81],"training":[82,105],"mechanism":[83],"proposed":[85,132],"simultaneously":[87],"model":[88,151],"both":[89],"normalized":[94],"multi-modal":[95],"features":[96],"accented":[99,125],"performance.":[101],"Moreover,":[102],"multi-objective":[104],"losses":[106],"text-induced":[108],"target":[111],"units":[112],"are":[113,118],"also":[114],"investigated.":[115],"Our":[116],"experiments":[117],"performed":[119],"on":[120,143],"public":[122],"CommonVoice":[123],"English":[124],"tasks,":[127],"results":[128],"show":[129],"that":[130],"CPT":[133],"outperforms":[134],"strong":[136],"baseline":[137],"by":[138],"relative":[139],"9.3%-13.4%":[140],"WER":[141],"reductions":[142],"six":[144],"evaluation":[145],"sets,":[146],"all":[147],"without":[148],"increasing":[149],"any":[150],"parameters":[152],"or":[153],"computational":[154],"costs":[155],"during":[156],"inference.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}