{"id":"https://openalex.org/W4405709441","doi":"https://doi.org/10.1109/iscslp63861.2024.10800708","title":"Lightweight Language Model for Speech Synthesis: Attempts and Analysis","display_name":"Lightweight Language Model for Speech Synthesis: Attempts and Analysis","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709441","doi":"https://doi.org/10.1109/iscslp63861.2024.10800708"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5101405311","display_name":"Zhigang Wu","orcid":"https://orcid.org/0000-0001-6144-7277"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhuojun Wu","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407459","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0002-5417-559X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101405311"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7016544,"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":"501","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9771000146865845,"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":0.9771000146865845,"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":0.7554393410682678},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48066675662994385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45281946659088135},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44535213708877563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4053970277309418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554393410682678},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48066675662994385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45281946659088135},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44535213708877563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4053970277309418}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2903739847","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2975414524","https://openalex.org/W3015338123","https://openalex.org/W3030163527","https://openalex.org/W3161480375","https://openalex.org/W3215615641","https://openalex.org/W4307323391","https://openalex.org/W4382202703","https://openalex.org/W4385571011","https://openalex.org/W4385823163","https://openalex.org/W4387595589","https://openalex.org/W4391833199","https://openalex.org/W4392903389","https://openalex.org/W4402111455","https://openalex.org/W6640963894","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6777694618","https://openalex.org/W6778083308","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6847478871","https://openalex.org/W6848735303","https://openalex.org/W6850625674","https://openalex.org/W6936129901"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large-scale":[0],"autoregressive":[1],"text-to-speech":[2],"(TTS)":[3],"models":[4,19],"can":[5,121],"generate":[6],"speech":[7],"that":[8],"is":[9,21,88],"nearly":[10],"indistinguishable":[11],"from":[12],"human":[13],"speech.":[14],"However,":[15],"training":[16,76],"large":[17],"language":[18],"(LLMs)":[20],"challenging":[22],"due":[23],"to":[24,49,103,115],"memory":[25],"and":[26,53,62,84,94,110],"computational":[27],"constraints.":[28],"This":[29,98],"paper":[30,99],"describes":[31],"our":[32,82,101],"TTS":[33,109],"method":[34,83],"for":[35,107],"the":[36,46,58,64,69,78,112],"2024":[37],"Conversational":[38],"Voice":[39],"Clone":[40],"Challenge":[41],"(CoVoC).":[42],"Our":[43,118],"approach":[44],"modifies":[45],"LauraGPT":[47],"model":[48],"synthesize":[50],"mixed":[51],"Chinese":[52,59],"English":[54],"text":[55],"by":[56],"expanding":[57],"pinyin":[60],"vocabulary":[61],"reducing":[63],"number":[65],"of":[66],"layers":[67],"in":[68,91],"decoder-only":[70],"Transformer":[71],"architecture.":[72],"Despite":[73],"using":[74],"minimal":[75],"data,":[77],"performance":[79],"gap":[80],"between":[81],"other":[85],"constrained":[86],"systems":[87],"relatively":[89],"small":[90],"both":[92],"subjective":[93],"some":[95],"objective":[96],"evaluations.":[97],"discusses":[100],"attempt":[102],"train":[104],"lightweight":[105],"LLMs":[106],"zero-shot":[108],"analyzes":[111],"factors":[113],"contributing":[114],"low":[116],"performance.":[117],"audio":[119],"samples":[120],"be":[122],"accessed":[123],"online<sup":[124],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[125,127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://axunyi.github.io/lwllmtts/.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}