{"id":"https://openalex.org/W3161674998","doi":"https://doi.org/10.1109/icassp39728.2021.9414082","title":"An End-to-End Speech Accent Recognition Method Based on Hybrid CTC/Attention Transformer ASR","display_name":"An End-to-End Speech Accent Recognition Method Based on Hybrid CTC/Attention Transformer ASR","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161674998","doi":"https://doi.org/10.1109/icassp39728.2021.9414082","mag":"3161674998"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5111740016","display_name":"Qiang Gao","orcid":"https://orcid.org/0000-0002-5815-3048"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Gao","raw_affiliation_strings":["NetEase Youdao,Beijing,China","NetEase Youdao, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao,Beijing,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Youdao, Beijing, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079117782","display_name":"Haiwei Wu","orcid":"https://orcid.org/0000-0001-8807-0254"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiwei Wu","raw_affiliation_strings":["NetEase Youdao,Beijing,China","NetEase Youdao, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao,Beijing,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Youdao, Beijing, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087009451","display_name":"Yanqing Sun","orcid":"https://orcid.org/0000-0002-3140-4572"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanqing Sun","raw_affiliation_strings":["NetEase Youdao,Beijing,China","NetEase Youdao, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao,Beijing,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Youdao, Beijing, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108663480","display_name":"Yitao Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitao Duan","raw_affiliation_strings":["NetEase Youdao,Beijing,China","NetEase Youdao, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Youdao,Beijing,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Youdao, Beijing, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.099,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.8921596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7253","last_page":"7257"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"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":0.9944999814033508,"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":0.8314961194992065},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7371187806129456},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6716916561126709},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6110252141952515},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5612235069274902},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5437977313995361},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.49079927802085876},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4767152667045593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4588504433631897},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42401155829429626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35491350293159485},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11438208818435669},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06483983993530273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314961194992065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7371187806129456},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6716916561126709},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6110252141952515},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5612235069274902},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5437977313995361},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.49079927802085876},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4767152667045593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4588504433631897},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42401155829429626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35491350293159485},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11438208818435669},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06483983993530273},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W996208672","https://openalex.org/W1494198834","https://openalex.org/W1515008200","https://openalex.org/W2069620976","https://openalex.org/W2127141656","https://openalex.org/W2183341477","https://openalex.org/W2462831000","https://openalex.org/W2526425061","https://openalex.org/W2739883972","https://openalex.org/W2786835190","https://openalex.org/W2883651221","https://openalex.org/W2891616026","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2972539100","https://openalex.org/W2972798094","https://openalex.org/W2979578510","https://openalex.org/W3011297857","https://openalex.org/W3048205211","https://openalex.org/W3130041558","https://openalex.org/W3160475509","https://openalex.org/W4252399209","https://openalex.org/W4385245566","https://openalex.org/W6638575559","https://openalex.org/W6718683173","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6781742697","https://openalex.org/W6790915370"],"related_works":["https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W2970530566","https://openalex.org/W2151922127","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4237818736","https://openalex.org/W3179968364","https://openalex.org/W4385572700","https://openalex.org/W4367680763"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,12,35,105],"novel":[4],"accent":[5,42,52,116],"recognition":[6,16,117],"system":[7,103,111],"in":[8,34,114,119],"the":[9,20,26,46,55,59,72,91,97,101,115,120],"framework":[10],"of":[11,88],"transformer-based":[13],"end-to-end":[14],"speech":[15,65],"system.":[17],"To":[18],"incorporate":[19],"pronunciation":[21],"and":[22,57,94],"linguistic":[23],"knowledge":[24],"into":[25],"network,":[27],"we":[28,44],"first":[29],"pre-train":[30],"an":[31,63,86],"ASR":[32],"model":[33],"hybrid":[36],"CTC/attention":[37],"manner.":[38],"Then,":[39],"focusing":[40],"on":[41,71,90,96],"recognition,":[43],"extend":[45],"output":[47],"token":[48],"list":[49],"by":[50,104],"inserting":[51],"labels":[53],"to":[54],"transcripts":[56],"finetune":[58],"network":[60],"parameters":[61],"with":[62],"accented":[64],"dataset.":[66],"Our":[67,109],"work":[68],"is":[69],"evaluated":[70],"Interspeech":[73],"2020":[74],"Accented":[75],"English":[76],"Speech":[77],"Recognition":[78],"Challenge.":[79],"Experiments":[80],"show":[81],"that":[82],"our":[83],"method":[84],"achieves":[85],"accuracy":[87],"72.39%":[89],"test":[92],"set":[93],"80.98%":[95],"development":[98],"set,":[99],"outperforming":[100],"baseline":[102],"very":[106],"large":[107],"margin.":[108],"submitted":[110],"ranked":[112],"second":[113],"task":[118],"challenge.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}