{"id":"https://openalex.org/W3016139610","doi":"https://doi.org/10.1109/icassp40776.2020.9053094","title":"Code-Switched Speech Synthesis Using Bilingual Phonetic Posteriorgram with Only Monolingual Corpora","display_name":"Code-Switched Speech Synthesis Using Bilingual Phonetic Posteriorgram with Only Monolingual Corpora","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016139610","doi":"https://doi.org/10.1109/icassp40776.2020.9053094","mag":"3016139610"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5013296368","display_name":"Yuewen Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yuewen Cao","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Tencent, Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346795","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0002-1860-5126"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Tencent, Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent, Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent, Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5013296368"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.6556,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.8715066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7619","last_page":"7623"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9977999925613403,"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":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.8235393762588501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6973937749862671},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5205146670341492},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5042310953140259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45656830072402954},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.412035197019577},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3442460298538208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235393762588501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6973937749862671},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5205146670341492},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5042310953140259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45656830072402954},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.412035197019577},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3442460298538208},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W36870606","https://openalex.org/W88751538","https://openalex.org/W113498433","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1767292398","https://openalex.org/W2014962660","https://openalex.org/W2078647797","https://openalex.org/W2099531983","https://openalex.org/W2114010348","https://openalex.org/W2119929864","https://openalex.org/W2146927751","https://openalex.org/W2171019095","https://openalex.org/W2395500689","https://openalex.org/W2398071208","https://openalex.org/W2401207139","https://openalex.org/W2507912506","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2525997790","https://openalex.org/W2554000662","https://openalex.org/W2619368999","https://openalex.org/W2888922217","https://openalex.org/W2889329491","https://openalex.org/W2936832667","https://openalex.org/W2938583109","https://openalex.org/W2949382160","https://openalex.org/W2963242190","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2972565052","https://openalex.org/W2973177731","https://openalex.org/W3127686677","https://openalex.org/W4289383906","https://openalex.org/W6601527497","https://openalex.org/W6604531305","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6674798237","https://openalex.org/W6677973343","https://openalex.org/W6712053557","https://openalex.org/W6713123361","https://openalex.org/W6726528559","https://openalex.org/W6727427871","https://openalex.org/W6730320939","https://openalex.org/W6755300632","https://openalex.org/W6789826613","https://openalex.org/W7075696416"],"related_works":["https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2152945827","https://openalex.org/W2036933852","https://openalex.org/W2015513221","https://openalex.org/W2181773877","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793","https://openalex.org/W2349468610"],"abstract_inverted_index":{"Synthesizing":[0],"fluent":[1],"code-switched":[2,178],"(CS)":[3],"speech":[4,45,75,89,168],"with":[5,31],"consistent":[6],"voice":[7],"using":[8,47,142],"only":[9,48],"monolingual":[10,49,68,73],"corpora":[11],"is":[12,28,54,63,79,121],"still":[13],"a":[14,38],"challenging":[15],"task,":[16],"since":[17],"language":[18],"alternation":[19],"seldom":[20],"occurs":[21],"during":[22],"training":[23,113],"and":[24,60,92,130,133,172],"the":[25,86,101,125,134,159,162,176],"speaker":[26,151,155,173],"identity":[27],"directly":[29],"correlated":[30],"language.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"present":[37],"bilingual":[39,52,82,110,131,135],"phonetic":[40,95],"posteriorgram":[41],"(PPG)":[42],"based":[43,119,147],"CS":[44],"synthesizer":[46],"corpora.":[50],"The":[51,105],"PPG":[53,83],"used":[55,122],"to":[56,123,139,153],"bridge":[57],"across":[58],"speakers":[59],"languages,":[61],"which":[62],"formed":[64],"by":[65],"stacking":[66],"two":[67,72],"PPGs":[69,111,136],"extracted":[70],"from":[71,112],"speaker-independent":[74],"recognition":[76],"systems.":[77],"It":[78],"assumed":[80],"that":[81],"can":[84],"represent":[85],"articulation":[87],"of":[88,97,161,167,175],"sounds":[90],"speaker-independently":[91],"captures":[93],"accurate":[94],"information":[96],"both":[98],"languages":[99],"in":[100,165],"same":[102],"feature":[103],"space.":[104],"proposed":[106,163],"model":[107,120,148,164],"first":[108],"extracts":[109],"data.":[114],"Then":[115],"an":[116],"encoder-":[117],"decoder":[118],"learn":[124],"relationship":[126],"between":[127],"input":[128],"text":[129],"PPGs,":[132],"are":[137],"mapped":[138],"acoustic":[140],"features":[141],"bidirectional":[143],"long-short":[144],"term":[145],"memory":[146],"conditioned":[149],"on":[150],"embedding":[152],"control":[154],"identity.":[156],"Experiments":[157],"validate":[158],"effectiveness":[160],"terms":[166],"intelligibility,":[169],"audio":[170],"fidelity":[171],"consistency":[174],"generated":[177],"speech.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}