{"id":"https://openalex.org/W3197530164","doi":"https://doi.org/10.21437/interspeech.2021-1495","title":"E2E-Based Multi-Task Learning Approach to Joint Speech and Accent Recognition","display_name":"E2E-Based Multi-Task Learning Approach to Joint Speech and Accent Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197530164","doi":"https://doi.org/10.21437/interspeech.2021-1495","mag":"3197530164"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1495","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5100729891","display_name":"Jicheng Zhang","orcid":"https://orcid.org/0000-0001-8797-2053"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jicheng Zhang","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051467915","display_name":"Yizhou Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Peng","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046222772","display_name":"Van Tung Pham","orcid":"https://orcid.org/0000-0002-2103-1901"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Van Tung Pham","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039696635","display_name":"Haihua Xu","orcid":"https://orcid.org/0000-0002-2220-8465"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haihua Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8988,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93519414,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1519","last_page":"1523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8723000288009644,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8723000288009644,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8289999961853027,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7826359272003174},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7029278874397278},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6806986927986145},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.633735716342926},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6222495436668396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49366435408592224},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4926500916481018},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.43857595324516296},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07538273930549622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826359272003174},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7029278874397278},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6806986927986145},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.633735716342926},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6222495436668396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49366435408592224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4926500916481018},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.43857595324516296},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07538273930549622},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1495","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W107354767","https://openalex.org/W2085628288","https://openalex.org/W2163922914","https://openalex.org/W2407080277","https://openalex.org/W2515121265","https://openalex.org/W2526425061","https://openalex.org/W2603679025","https://openalex.org/W2786835190","https://openalex.org/W2889488531","https://openalex.org/W2889494795","https://openalex.org/W2889785444","https://openalex.org/W2890704021","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962893195","https://openalex.org/W2964099675","https://openalex.org/W2972539100","https://openalex.org/W2972815379","https://openalex.org/W3010079431","https://openalex.org/W3010788072","https://openalex.org/W3023256384","https://openalex.org/W3096215352","https://openalex.org/W3111562797","https://openalex.org/W3160475509","https://openalex.org/W3162508345","https://openalex.org/W4287553982","https://openalex.org/W4287600974","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1980564716","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4367680763","https://openalex.org/W4252005663","https://openalex.org/W2365914832","https://openalex.org/W2352261042","https://openalex.org/W2951720331"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,41,70,118],"propose":[4],"a":[5,96,123],"single":[6],"multi-task":[7],"learning":[8],"framework":[9,23],"to":[10,61,111,145],"perform":[11],"End-to-End":[12],"(E2E)":[13],"speech":[14],"recognition":[15,19,165,172],"(ASR)":[16],"and":[17,54,156,162],"accent":[18,171],"(AR)":[20],"simultaneously.The":[21],"proposed":[22,76,139],"is":[24,47,59,86,109],"not":[25],"only":[26,122],"more":[27],"compact":[28],"but":[29],"can":[30],"also":[31],"yield":[32,112],"comparable":[33],"or":[34],"even":[35],"better":[36,113,130],"results":[37,114,132,143],"than":[38,133],"standalone":[39,148,161],"systems.Specifically,":[40],"found":[42,119],"that":[43,120],"the":[44,51,55,67,75,79,83,101,105,127,135,138,146],"overall":[45,136],"performance":[46],"predominantly":[48],"determined":[49],"by":[50],"ASR":[52,57,94,150],"task,":[53,95],"E2E-based":[56],"pretraining":[58],"essential":[60],"achieve":[62],"improved":[63],"performance,":[64],"particularly":[65],"for":[66,82,115,170],"AR":[68,84,102,131],"task.Additionally,":[69],"conduct":[71],"several":[72],"analyses":[73],"of":[74,93,126],"method.First,":[77],"though":[78],"objective":[80,107],"loss":[81],"task":[85,103],"much":[87],"smaller":[88,97],"compared":[89],"with":[90,100],"its":[91],"counterpart":[92],"weighting":[98],"factor":[99],"in":[104],"joint":[106,164],"function":[108],"necessary":[110],"each":[116],"task.Second,":[117],"sharing":[121,134],"few":[124],"layers":[125],"encoder":[128],"yields":[129],"encoder.Experimentally,":[137],"method":[140],"produces":[141],"WER":[142],"close":[144],"best":[147],"E2E":[149],"ones,":[151],"while":[152],"it":[153],"achieves":[154],"7.7%":[155],"4.2%":[157],"relative":[158],"improvement":[159],"over":[160],"single-task-based":[163],"methods":[166],"on":[167],"test":[168],"set":[169],"respectively.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6}],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2025-10-10T00:00:00"}