{"id":"https://openalex.org/W4210331460","doi":"https://doi.org/10.1109/asru51503.2021.9687961","title":"Learning Language and Speaker Information for Code-Switch Speech Synthesis with Limited Data","display_name":"Learning Language and Speaker Information for Code-Switch Speech Synthesis with Limited Data","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210331460","doi":"https://doi.org/10.1109/asru51503.2021.9687961"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687961","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5070348458","display_name":"Mengxin Chai","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengxin Chai","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000235693","display_name":"Shaotong Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaotong Guo","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107748760","display_name":"Gong Cheng","orcid":"https://orcid.org/0009-0004-0272-3541"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Gong","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050763764","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-4005-5036"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","Japan Advanced Institute of Science and Technology, Ishikawa, Japan","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620206","display_name":"Ju Zhang","orcid":"https://orcid.org/0000-0002-0378-6497"},"institutions":[{"id":"https://openalex.org/I4210094894","display_name":"China Automotive Technology and Research Center","ror":"https://ror.org/00r5r6807","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210094894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Zhang","raw_affiliation_strings":["Huiyan Technology (Tianjin) Co., Ltd.,China","Huiyan Technology (Tianjin) Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"Huiyan Technology (Tianjin) Co., Ltd.,China","institution_ids":["https://openalex.org/I4210094894"]},{"raw_affiliation_string":"Huiyan Technology (Tianjin) Co., Ltd., China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070348458"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.21471303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"602","last_page":"609"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.9962000250816345,"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":0.8044388890266418},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5981033444404602},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5825300216674805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5662298202514648},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5492715835571289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5339281558990479},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47274598479270935},{"id":"https://openalex.org/keywords/pinyin","display_name":"Pinyin","score":0.4466783404350281},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44308406114578247},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17423897981643677},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14532405138015747}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044388890266418},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5981033444404602},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5825300216674805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5662298202514648},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5492715835571289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339281558990479},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47274598479270935},{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.4466783404350281},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44308406114578247},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17423897981643677},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14532405138015747},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/asru51503.2021.9687961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687961","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5633359880","display_name":null,"funder_award_id":"61771333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8651560819","display_name":null,"funder_award_id":"2018YFB1305200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W88751538","https://openalex.org/W1964478843","https://openalex.org/W2025638820","https://openalex.org/W2050939913","https://openalex.org/W2078647797","https://openalex.org/W2099531983","https://openalex.org/W2107201284","https://openalex.org/W2114010348","https://openalex.org/W2146927751","https://openalex.org/W2164107060","https://openalex.org/W2187089797","https://openalex.org/W2395500689","https://openalex.org/W2398071208","https://openalex.org/W2398462115","https://openalex.org/W2401698713","https://openalex.org/W2494654097","https://openalex.org/W2525997790","https://openalex.org/W2554000662","https://openalex.org/W2747921929","https://openalex.org/W2766812927","https://openalex.org/W2900819823","https://openalex.org/W2901389167","https://openalex.org/W2936832667","https://openalex.org/W2946200149","https://openalex.org/W2963091184","https://openalex.org/W2963964591","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2972457126","https://openalex.org/W3015212790","https://openalex.org/W3095012670","https://openalex.org/W3095873922","https://openalex.org/W3096514088","https://openalex.org/W3099891349","https://openalex.org/W3196467321","https://openalex.org/W6674798237","https://openalex.org/W6712869911","https://openalex.org/W6727427871","https://openalex.org/W6730320939","https://openalex.org/W6743753889","https://openalex.org/W6745697700"],"related_works":["https://openalex.org/W2355589192","https://openalex.org/W2383579380","https://openalex.org/W2599785913","https://openalex.org/W2357614476","https://openalex.org/W2391413009","https://openalex.org/W2977960882","https://openalex.org/W4214677368","https://openalex.org/W2787859844","https://openalex.org/W2599178495","https://openalex.org/W2385323919"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,12,75,138],"synthesis":[2,13,76],"demonstrates":[3],"remarkable":[4],"performance":[5,164],"in":[6,139,168,180],"monolingual":[7],"speech,":[8],"whereas":[9],"code-switching":[10],"(CS)":[11],"remains":[14],"a":[15,52,65,147],"challenge":[16],"owing":[17],"to":[18,71,82,111,126,188],"the":[19,73,94,101,117,128,155,160,171,183,189],"sparsity":[20],"of":[21,68,77,141,150,166,170,178,182],"data":[22,70],"and":[23,43,60,79,86,100,115,143,175],"diverse":[24],"syntactic":[25],"structures":[26],"across":[27],"languages.":[28,129],"Previous":[29],"studies":[30],"show":[31],"that":[32,159],"large":[33],"mixed-lingual":[34,69,151],"corpora":[35],"are":[36],"essential":[37],"for":[38],"effective":[39],"learning":[40],"text/language":[41],"representations":[42],"target":[44],"speaker":[45,144],"information.":[46],"In":[47,153],"this":[48],"study,":[49],"we":[50,88,134],"propose":[51],"method":[53,162],"using":[54,146],"three":[55],"independent":[56],"encoders":[57],"(text,":[58],"language,":[59],"speaker),":[61],"which":[62,97,120],"requires":[63],"only":[64],"small":[66,148],"amount":[67,149],"realize":[72],"CS":[74],"Mandarin":[78,85],"English.":[80],"Additionally,":[81],"distinguish":[83],"between":[84],"English,":[87],"investigate":[89],"two":[90],"text-representation":[91],"methods:":[92],"(1)":[93],"implicit":[95],"method,":[96,119,133],"uses":[98,121],"Pinyin":[99],"CMU":[102],"<sup":[103,106],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[104,107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[105,108],"http://www.speech.cs.cmu.edu/cgi-bin/cmudict":[109],"dictionary":[110],"represent":[112],"both":[113],"languages;":[114],"(2)":[116],"explicit":[118],"language":[122],"markers":[123],"i.e.,":[124],"masks,":[125],"differentiate":[127],"Through":[130],"our":[131],"proposed":[132,161],"can":[135],"improve":[136],"synthesized":[137],"terms":[140,169,181],"quality":[142],"similarity":[145],"data.":[152],"addition,":[154],"experimental":[156],"results":[157],"demonstrate":[158],"achieves":[163],"improvement":[165,177],"0.06":[167],"mean":[172],"opinion":[173],"score":[174],"absolute":[176],"0.64%":[179],"character":[184],"error":[185],"rate":[186],"compared":[187],"baseline":[190],"method.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
