{"id":"https://openalex.org/W4408353629","doi":"https://doi.org/10.1109/icassp49660.2025.10890588","title":"Boosting Large Language Model for Speech Synthesis: An Empirical Study","display_name":"Boosting Large Language Model for Speech Synthesis: An Empirical Study","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353629","doi":"https://doi.org/10.1109/icassp49660.2025.10890588"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5111019859","display_name":"Hongkun Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongkun Hao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557565","display_name":"Long Zhou","orcid":"https://orcid.org/0009-0006-1919-4943"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Long Zhou","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026334377","display_name":"Shujie Hu","orcid":"https://orcid.org/0000-0002-8475-4912"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Shujie Hu","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683975","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0003-1223-6160"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Furu Wei","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5111019859"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":13.9889,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.9838885,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9883000254631042,"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":0.9883000254631042,"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":0.906000018119812,"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":0.7870943546295166},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7676652073860168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4647276699542999},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4619702398777008},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4548732042312622},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4510931968688965},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42889881134033203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.345417857170105},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06779667735099792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870943546295166},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7676652073860168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4647276699542999},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4619702398777008},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4548732042312622},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4510931968688965},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42889881134033203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.345417857170105},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06779667735099792},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W3095410713","https://openalex.org/W3097206152","https://openalex.org/W3209984917","https://openalex.org/W4307323391","https://openalex.org/W4389519587","https://openalex.org/W4389524500","https://openalex.org/W4391021666","https://openalex.org/W4392903956","https://openalex.org/W4402671548","https://openalex.org/W4404781855","https://openalex.org/W4404783556","https://openalex.org/W4406417959","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6761164592","https://openalex.org/W6761551260","https://openalex.org/W6771812881","https://openalex.org/W6796581206","https://openalex.org/W6810738896","https://openalex.org/W6811340617","https://openalex.org/W6846002521","https://openalex.org/W6848735303","https://openalex.org/W6850015000","https://openalex.org/W6850334629","https://openalex.org/W6852800892","https://openalex.org/W6853116092","https://openalex.org/W6853611000","https://openalex.org/W6853998256","https://openalex.org/W6854866820","https://openalex.org/W6855801281","https://openalex.org/W6857054612","https://openalex.org/W6859099255"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2571255492"],"abstract_inverted_index":{"Large":[0],"language":[1,10,17],"models":[2,182],"(LLMs)":[3],"have":[4],"made":[5],"significant":[6,191],"advancements":[7],"in":[8,151],"natural":[9],"processing":[11],"and":[12,25,43,79,91,103,105,108,138,141,154,189],"are":[13],"concurrently":[14],"extending":[15],"the":[16,30,44,69,130,145,168,173],"ability":[18,70],"to":[19,71,124,128],"other":[20],"modalities,":[21],"such":[22],"as":[23,112,167],"speech":[24,51,92,131,149,180],"vision.":[26],"Nevertheless,":[27],"most":[28],"of":[29,65,101,147],"previous":[31],"work":[32,136],"focuses":[33],"on":[34],"prompting":[35],"LLMs":[36,49,67,90,102,107,111,126,140,166],"with":[37,50,68,183],"perception":[38],"abilities":[39],"like":[40],"auditory":[41],"comprehension,":[42],"effective":[45],"approach":[46],"for":[47],"augmenting":[48],"synthesis":[52,81,93,132,181],"capabilities":[53],"remains":[54],"ambiguous.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"conduct":[60],"a":[61,113,184,190],"comprehensive":[62],"empirical":[63],"exploration":[64],"boosting":[66],"generate":[72],"speech,":[73],"by":[74],"combining":[75],"pre-trained":[76],"LLM":[77],"LLaMA/OPT":[78],"text-to-speech":[80],"model":[82],"VALL-E.":[83],"We":[84],"compare":[85],"three":[86,161],"integration":[87],"methods":[88,164],"between":[89],"models,":[94],"including":[95],"directly":[96,127],"fine-tuned":[97],"LLMs,":[98],"superposed":[99,139],"layers":[100],"VALL-E,":[104],"coupled":[106,163],"VALL-E":[109,142],"using":[110,121],"powerful":[114],"text":[115,169],"encoder.":[116],"Experimental":[117],"results":[118],"show":[119],"that,":[120],"LoRA":[122],"method":[123],"fine-tune":[125],"boost":[129],"capability":[133],"does":[134],"not":[135],"well,":[137],"can":[143,171],"improve":[144],"quality":[146],"generated":[148],"both":[150],"speaker":[152,187],"similarity":[153,188],"word":[155],"error":[156],"rate":[157],"(WER).":[158],"Among":[159],"these":[160],"methods,":[162],"leveraging":[165],"encoder":[170],"achieve":[172],"best":[174],"performance,":[175],"making":[176],"it":[177],"outperform":[178],"original":[179],"consistently":[185],"better":[186],"(10.9%)":[192],"WER":[193],"reduction.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}