{"id":"https://openalex.org/W3163487528","doi":"https://doi.org/10.1109/icassp39728.2021.9414428","title":"Decoupling Pronunciation and Language for End-to-End Code-Switching Automatic Speech Recognition","display_name":"Decoupling Pronunciation and Language for End-to-End Code-Switching Automatic Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163487528","doi":"https://doi.org/10.1109/icassp39728.2021.9414428","mag":"3163487528"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414428","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/A5100328840","display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0001-8536-8493"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101817056","display_name":"Zhengkun Tian","orcid":"https://orcid.org/0000-0002-0469-3049"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengkun Tian","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624455","display_name":"Ye Bai","orcid":"https://orcid.org/0000-0001-5533-6909"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Bai","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["CAS Center for Excellence in Brain Science and Intelligence Technology, China","NLPR, Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi wen","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8393,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78292175,"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":"6249","last_page":"6253"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9916999936103821,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.851995050907135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314094305038452},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6830103397369385},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.588566780090332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5823940634727478},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.4708264172077179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.305991530418396},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17133793234825134},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14082834124565125}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.851995050907135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314094305038452},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6830103397369385},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.588566780090332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5823940634727478},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.4708264172077179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.305991530418396},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17133793234825134},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14082834124565125},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414428","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":0.8100000023841858,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2168708086","https://openalex.org/W2327501763","https://openalex.org/W2883989418","https://openalex.org/W2886820613","https://openalex.org/W2888779557","https://openalex.org/W2892009249","https://openalex.org/W2926989360","https://openalex.org/W2936774411","https://openalex.org/W2939069254","https://openalex.org/W2962704885","https://openalex.org/W2962780374","https://openalex.org/W2962961016","https://openalex.org/W2963403868","https://openalex.org/W2964002616","https://openalex.org/W2972625221","https://openalex.org/W2972702443","https://openalex.org/W2972991710","https://openalex.org/W3029522047","https://openalex.org/W3042170933","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6777856084","https://openalex.org/W6780815891"],"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/W2771594921","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W2359469050"],"abstract_inverted_index":{"Despite":[0],"the":[1,19,23,46,94,98,107,131,136,152,163,167,177],"recent":[2],"significant":[3],"advances":[4],"witnessed":[5],"in":[6,90],"end-to-end":[7],"(E2E)":[8],"ASR":[9],"system":[10],"for":[11,14,86],"code-switching,":[12],"hunger":[13],"audio-text":[15],"paired":[16,38,77,101,141],"data":[17,39,43,50,89,102,126,143],"limits":[18],"further":[20],"improvement":[21],"of":[22,48,118,144],"models\u2019":[24],"performance.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29],"propose":[30],"a":[31,148],"decoupled":[32,55,132],"transformer":[33,133,175],"model":[34,53,134,146],"to":[35,44,105,147],"use":[36],"mono-lingual":[37],"and":[40,62,127],"unpaired":[41,120,128],"text":[42,121,129],"alleviate":[45],"problem":[47],"code-switching":[49,140,170],"shortage.":[51],"The":[52,66],"is":[54,103],"into":[56],"two":[57,153],"parts:":[58],"audio-to-phoneme":[59],"(A2P)":[60],"network":[61,68,111],"phoneme-to-text":[63],"(P2T)":[64],"network.":[65,109],"A2P":[67],"can":[69,112],"learn":[70],"acoustic":[71],"pattern":[72],"scenarios":[73],"using":[74,124],"large-scale":[75],"monolingual":[76,125],"data.":[78,122],"Meanwhile,":[79],"it":[80],"generates":[81],"multiple":[82],"phoneme":[83],"sequence":[84],"candidates":[85],"single":[87],"audio":[88],"real":[91],"time":[92],"during":[93],"training":[95,142],"process.":[96],"Then":[97],"generated":[99],"phoneme-text":[100],"used":[104],"train":[106],"P2T":[108],"This":[110],"be":[113],"pre-trained":[114],"with":[115,173],"large":[116],"amounts":[117],"external":[119],"By":[123],"data,":[130],"reduces":[135],"high":[137],"dependency":[138],"on":[139,166],"E2E":[145],"certain":[149],"extent.":[150],"Finally,":[151],"networks":[154],"are":[155],"optimized":[156],"jointly":[157],"through":[158],"attention":[159],"fusion.":[160],"We":[161],"evaluate":[162],"proposed":[164,178],"method":[165,179],"public":[168],"Mandarin-English":[169],"dataset.":[171],"Compared":[172],"our":[174],"baseline,":[176],"achieves":[180],"18.14%":[181],"relative":[182],"mix":[183],"error":[184],"rate":[185],"reduction.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-28T08:01:55.173337","created_date":"2025-10-10T00:00:00"}