{"id":"https://openalex.org/W7148267950","doi":"https://doi.org/10.1109/asru65441.2025.11434663","title":"Enhancing Code-switched Text-to-Speech Synthesis Capability in Large Language Models with only Monolingual Corpora","display_name":"Enhancing Code-switched Text-to-Speech Synthesis Capability in Large Language Models with only Monolingual Corpora","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148267950","doi":"https://doi.org/10.1109/asru65441.2025.11434663"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5101856485","display_name":"Jiayi Xu","orcid":"https://orcid.org/0000-0003-3465-7927"},"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":"Jing Xu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006527442","display_name":"Daxin Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Daxin Tan","raw_affiliation_strings":["Noah&#x2019;s Ark Lab, Huawei"],"affiliations":[{"raw_affiliation_string":"Noah&#x2019;s Ark Lab, Huawei","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108047889","display_name":"Y\u00ec W\u00e1ng","orcid":"https://orcid.org/0000-0001-5697-0717"},"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":"Jiaqi Wang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132813666","display_name":"Xiao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Noah&#x2019;s Ark Lab, Huawei"],"affiliations":[{"raw_affiliation_string":"Noah&#x2019;s Ark Lab, Huawei","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101856485"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87548352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6721000075340271,"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":0.6721000075340271,"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":0.12559999525547028,"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":0.04089999943971634,"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/natural-language","display_name":"Natural language","score":0.3644999861717224},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3240000009536743},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32100000977516174},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2612999975681305},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.260699987411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823999881744385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5795000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5350000262260437},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6171293258666992,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2078647797","https://openalex.org/W2146927751","https://openalex.org/W2395500689","https://openalex.org/W2936832667","https://openalex.org/W2972659941","https://openalex.org/W3016139610","https://openalex.org/W3096615836","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210177631","https://openalex.org/W4226033575","https://openalex.org/W4226380987","https://openalex.org/W4283067311","https://openalex.org/W4375868953","https://openalex.org/W4381786045","https://openalex.org/W4388122583","https://openalex.org/W4389518827","https://openalex.org/W4389524500","https://openalex.org/W4390075359","https://openalex.org/W4392904805","https://openalex.org/W4402111374"],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1,35],"Language":[2,36],"Models":[3],"(LLMs)":[4],"have":[5],"shown":[6],"potential":[7],"in":[8,24,48,108,111],"speech":[9,61,68,91,131],"generation":[10],"and":[11,70,85,117,133],"recognition,":[12],"their":[13],"applications":[14],"are":[15],"mainly":[16],"confined":[17],"to":[18,39,93],"monolingual":[19,52,90],"scenarios,":[20],"with":[21,50,96,120],"limited":[22,121],"explorations":[23],"code-switched":[25,42,78],"(CS)":[26,79],"contexts.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,55,74],"propose":[32],"a":[33],"Code-Switched":[34],"Model":[37],"(CS-LLM)":[38],"enhance":[40],"the":[41,59,124],"text-to-speech":[43],"synthesis":[44,71,132],"(CS":[45],"TTS)":[46],"capability":[47],"LLMs":[49,65,95],"only":[51],"corpora.":[53],"Specifically,":[54],"begin":[56],"by":[57],"enhancing":[58],"multilingual":[60,67,130],"processing":[62],"ability":[63],"of":[64,113],"through":[66],"recognition":[69],"tasks.":[72],"Then,":[73],"develop":[75],"an":[76],"effective":[77],"data":[80,127],"construction":[81],"strategy":[82],"that":[83,103],"splits":[84],"concatenates":[86],"words":[87],"from":[88],"different":[89],"corpora":[92],"equip":[94],"improved":[97],"CS":[98,109,126],"TTS":[99,110],"ability.":[100],"Experiments":[101],"show":[102],"our":[104],"approach":[105],"outperforms":[106],"baselines":[107],"terms":[112],"naturalness,":[114],"speaker":[115],"consistency":[116],"similarity":[118],"even":[119],"data.":[122],"Additionally,":[123],"constructed":[125],"further":[128],"improves":[129],"recognition.":[134],"<sup":[135],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[136,138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Demo":[139],"page:":[140],"https://jingxu96.github.io/csllm-demo/":[141]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}