{"id":"https://openalex.org/W3015212790","doi":"https://doi.org/10.1109/icassp40776.2020.9054722","title":"End-to-End Code-Switching TTS with Cross-Lingual Language Model","display_name":"End-to-End Code-Switching TTS with Cross-Lingual Language Model","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015212790","doi":"https://doi.org/10.1109/icassp40776.2020.9054722","mag":"3015212790"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054722","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/A5016792332","display_name":"Xuehao Zhou","orcid":"https://orcid.org/0000-0003-4367-2053"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Xuehao Zhou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103156833","display_name":"Xiaohai Tian","orcid":"https://orcid.org/0000-0001-5219-1249"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaohai Tian","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056020864","display_name":"Grandee Lee","orcid":"https://orcid.org/0000-0001-9603-5141"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Grandee Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016792332"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.7233,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8743916,"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":"7614","last_page":"7618"},"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":0.9977999925613403,"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/T12031","display_name":"Speech and dialogue systems","score":0.9966999888420105,"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":0.8648028373718262},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.6631572246551514},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.661149263381958},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6167922616004944},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5851807594299316},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5665001273155212},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5542581677436829},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5263974666595459},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5234060883522034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4695601761341095},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4610620439052582},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.429782509803772},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11607098579406738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8648028373718262},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.6631572246551514},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.661149263381958},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6167922616004944},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5851807594299316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5665001273155212},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5542581677436829},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5263974666595459},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5234060883522034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4695601761341095},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4610620439052582},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.429782509803772},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11607098579406738},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054722","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W88751538","https://openalex.org/W1767292398","https://openalex.org/W1985371235","https://openalex.org/W2014962660","https://openalex.org/W2078647797","https://openalex.org/W2099531983","https://openalex.org/W2114010348","https://openalex.org/W2120847449","https://openalex.org/W2146927751","https://openalex.org/W2150769028","https://openalex.org/W2284628133","https://openalex.org/W2395500689","https://openalex.org/W2419539795","https://openalex.org/W2471177962","https://openalex.org/W2493916176","https://openalex.org/W2519091744","https://openalex.org/W2525997790","https://openalex.org/W2554000662","https://openalex.org/W2619368999","https://openalex.org/W2747921929","https://openalex.org/W2767052532","https://openalex.org/W2808706139","https://openalex.org/W2889028433","https://openalex.org/W2936832667","https://openalex.org/W2939408446","https://openalex.org/W2949382160","https://openalex.org/W2962739369","https://openalex.org/W2963192573","https://openalex.org/W2963609956","https://openalex.org/W2963712897","https://openalex.org/W2964243274","https://openalex.org/W2964266061","https://openalex.org/W2972359262","https://openalex.org/W2972473628","https://openalex.org/W2972954451","https://openalex.org/W2973177731","https://openalex.org/W2973217961","https://openalex.org/W3007376164","https://openalex.org/W4298174729","https://openalex.org/W6674798237","https://openalex.org/W6695553435","https://openalex.org/W6717262007","https://openalex.org/W6730320939","https://openalex.org/W6736996214","https://openalex.org/W6748573829","https://openalex.org/W6750365303","https://openalex.org/W6752888775","https://openalex.org/W6761768988","https://openalex.org/W6765987481"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Code-switching":[0],"text-to-speech":[1],"(TTS)":[2],"aims":[3],"to":[4,8,26,36,54,70],"enable":[5],"a":[6,13,47],"system":[7],"speak":[9],"two":[10,58,97],"languages":[11,59,69],"with":[12,122],"single":[14],"voice":[15,39,81],"and":[16,104,126],"in":[17,60],"the":[18,38,61,80,88,117],"same":[19,62],"utterance.":[20],"In":[21],"this":[22,91],"paper,":[23],"we":[24,93],"propose":[25],"incorporate":[27],"cross-lingual":[28,42,49],"word":[29,43],"embedding":[30,63],"into":[31],"an":[32],"end-to-end":[33],"TTS":[34],"system,":[35],"improve":[37],"rendering.":[40],"The":[41,108],"embedding,":[44],"generated":[45],"from":[46],"pre-trained":[48],"language":[50],"model,":[51],"is":[52,77],"able":[53],"encode":[55],"words":[56,67],"of":[57,83,90],"space,":[64],"therefore,":[65],"allows":[66],"across":[68],"share":[71],"each":[72],"other's":[73],"contextual":[74],"information,":[75],"which":[76],"useful":[78],"for":[79],"rendering":[82],"code-switching":[84,123],"content.":[85],"To":[86],"investigate":[87],"effectiveness":[89],"idea,":[92],"conduct":[94],"studies":[95],"on":[96],"multi-speaker":[98],"monolingual":[99],"corpora,":[100],"namely,":[101],"THCHS30":[102],"Mandarin":[103],"LibriTTS":[105],"English":[106],"database.":[107],"evaluation":[109],"results":[110],"show":[111],"that":[112],"our":[113],"proposed":[114],"framework":[115],"outperforms":[116],"baseline":[118],"systems":[119],"when":[120],"presented":[121],"text":[124],"input,":[125],"achieves":[127],"state-of-the-art":[128],"performance.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}