{"id":"https://openalex.org/W4372260242","doi":"https://doi.org/10.1109/icassp49357.2023.10097178","title":"Personalized Lightweight Text-to-Speech: Voice Cloning with Adaptive Structured Pruning","display_name":"Personalized Lightweight Text-to-Speech: Voice Cloning with Adaptive Structured Pruning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260242","doi":"https://doi.org/10.1109/icassp49357.2023.10097178"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5071504898","display_name":"Sung-Feng Huang","orcid":"https://orcid.org/0000-0002-9720-811X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Sung-Feng Huang","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087434278","display_name":"Chia-Ping Chen","orcid":"https://orcid.org/0000-0002-7022-3061"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chia-Ping Chen","raw_affiliation_strings":["Intelligo Technology Inc"],"affiliations":[{"raw_affiliation_string":"Intelligo Technology Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042581267","display_name":"Zhisheng Chen","orcid":"https://orcid.org/0000-0002-0854-2547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi-Sheng Chen","raw_affiliation_strings":["Intelligo Technology Inc"],"affiliations":[{"raw_affiliation_string":"Intelligo Technology Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113463271","display_name":"Yu-Pao Tsai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Pao Tsai","raw_affiliation_strings":["Intelligo Technology Inc"],"affiliations":[{"raw_affiliation_string":"Intelligo Technology Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071504898"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.7842,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74370436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9998999834060669,"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":0.9987000226974487,"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":0.9973999857902527,"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":0.7612340450286865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6857850551605225},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5786184072494507},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.567112922668457},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4323023557662964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4123688340187073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38320663571357727},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1097344160079956},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0654524564743042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612340450286865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6857850551605225},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5786184072494507},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.567112922668457},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4323023557662964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4123688340187073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38320663571357727},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1097344160079956},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0654524564743042},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2890964092","https://openalex.org/W2892620417","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2963828549","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W3015826515","https://openalex.org/W3033411150","https://openalex.org/W3095035471","https://openalex.org/W3095199334","https://openalex.org/W3096086473","https://openalex.org/W3097531247","https://openalex.org/W3128910262","https://openalex.org/W3160919572","https://openalex.org/W3161704465","https://openalex.org/W3161959914","https://openalex.org/W3198860978","https://openalex.org/W3203852729","https://openalex.org/W3213227271","https://openalex.org/W3213544594","https://openalex.org/W4298857617","https://openalex.org/W6745499552","https://openalex.org/W6745569068","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6790220310","https://openalex.org/W6791222748","https://openalex.org/W6803159591","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2355171581","https://openalex.org/W4229439743"],"abstract_inverted_index":{"Personalized":[0],"TTS":[1,15,23,54,91],"is":[2,74],"an":[3],"exciting":[4],"and":[5,31],"highly":[6],"desired":[7],"application":[8],"that":[9,149],"allows":[10],"users":[11],"to":[12,56,60,67,77,98,123,160],"train":[13],"their":[14],"voice":[16,124],"using":[17,150],"only":[18],"a":[19,32,52,101,107,138],"few":[20],"recordings.":[21],"However,":[22],"training":[24,127],"typically":[25,49],"requires":[26],"many":[27],"hours":[28],"of":[29],"recording":[30],"large":[33,102],"model,":[34,104],"making":[35],"it":[36],"unsuitable":[37],"for":[38,110,142],"deployment":[39],"on":[40],"mobile":[41],"devices.":[42],"To":[43],"overcome":[44],"this":[45,115],"limitation,":[46],"related":[47,82],"works":[48,83],"require":[50],"fine-tuning":[51],"pre-trained":[53,103],"model":[55,141,158],"preserve":[57],"its":[58],"ability":[59],"generate":[61],"high-quality":[62],"audio":[63],"samples":[64],"while":[65,164],"adapting":[66],"the":[68,90,111,128,157],"target":[69,144],"speaker\u2019s":[70],"voice.":[71],"This":[72],"process":[73],"commonly":[75],"referred":[76],"as":[78],"\"voice":[79],"cloning.\"":[80],"Although":[81],"have":[84],"achieved":[85],"significant":[86,108],"success":[87],"in":[88,106],"changing":[89],"model\u2019s":[92],"voice,":[93],"they":[94],"are":[95],"still":[96],"required":[97],"fine-tune":[99],"from":[100],"resulting":[105],"size":[109,159],"voice-cloned":[112],"model.":[113],"In":[114],"paper,":[116],"we":[117,135,154],"propose":[118],"applying":[119],"trainable":[120],"structured":[121,129,152],"pruning":[122,130],"cloning.":[125],"By":[126],"masks":[131],"with":[132],"voice-cloning":[133,167],"data,":[134],"can":[136,155],"produce":[137],"unique":[139],"pruned":[140],"each":[143],"speaker.":[145],"Our":[146],"experiments":[147],"demonstrate":[148],"learnable":[151],"pruning,":[153],"compress":[156],"7":[161],"times":[162],"smaller":[163],"achieving":[165],"comparable":[166],"performance.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}