{"id":"https://openalex.org/W4408352651","doi":"https://doi.org/10.1109/icassp49660.2025.10889369","title":"NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers","display_name":"NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352651","doi":"https://doi.org/10.1109/icassp49660.2025.10889369"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889369","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/A5008163534","display_name":"Nohil Park","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Nohil Park","raw_affiliation_strings":["Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087173618","display_name":"Heeseung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heeseung Kim","raw_affiliation_strings":["Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310842","display_name":"Che Hyun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Che Hyun Lee","raw_affiliation_strings":["Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102345025","display_name":"Jooyoung Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jooyoung Choi","raw_affiliation_strings":["Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102529529","display_name":"Jiheum Yeom","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiheum Yeom","raw_affiliation_strings":["Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051318852","display_name":"Sungroh Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungroh Yoon","raw_affiliation_strings":["Seoul National University,ECE, AIIS, ASRI, INMC, ISRC, and IPAI,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,ECE, AIIS, ASRI, INMC, ISRC, and IPAI,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008163534"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02012532,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9771999716758728,"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/T10860","display_name":"Speech and Audio Processing","score":0.958299994468689,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.799228310585022},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7831284999847412},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4984874725341797},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4207035005092621},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4142273962497711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799228310585022},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7831284999847412},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4984874725341797},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4207035005092621},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4142273962497711}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889369","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326288","display_name":"K2","ror":null},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2972359262","https://openalex.org/W3016159759","https://openalex.org/W3097777922","https://openalex.org/W3161109662","https://openalex.org/W4252812408","https://openalex.org/W4281736089","https://openalex.org/W4293363567","https://openalex.org/W4385822372","https://openalex.org/W4385822455","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4387321091","https://openalex.org/W4390832324","https://openalex.org/W4391871574","https://openalex.org/W4395447377","https://openalex.org/W4402112213","https://openalex.org/W4402112533","https://openalex.org/W4404781224","https://openalex.org/W6748588790","https://openalex.org/W6767671539","https://openalex.org/W6779823529","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6796581206","https://openalex.org/W6848735303","https://openalex.org/W6849956205","https://openalex.org/W6851724922","https://openalex.org/W6852985244","https://openalex.org/W6857768880","https://openalex.org/W6859455349","https://openalex.org/W6862144568","https://openalex.org/W6870225445"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2111874347","https://openalex.org/W2640905660"],"abstract_inverted_index":{"We":[0],"present":[1],"NanoVoice,":[2],"a":[3,18,44,60],"personalized":[4],"text-to-speech":[5],"model":[6],"that":[7,48],"efficiently":[8],"constructs":[9],"voice":[10],"adapters":[11,37],"for":[12,38,55,91],"multiple":[13,26],"speakers":[14],"simultaneously.":[15],"NanoVoice":[16,65,73],"introduces":[17],"batch-wise":[19],"speaker":[20,56,92],"adaptation":[21,93],"technique":[22,47],"capable":[23],"of":[24,52,107],"fine-tuning":[25],"references":[27],"in":[28],"parallel,":[29],"significantly":[30],"reducing":[31],"training":[32,81],"time.":[33],"Beyond":[34],"building":[35],"separate":[36],"each":[39],"speaker,":[40],"we":[41],"also":[42],"propose":[43],"parameter":[45,71],"sharing":[46],"reduces":[49],"the":[50,78,105],"number":[51],"parameters":[53,90],"used":[54],"adaptation.":[57],"By":[58],"incorporating":[59],"novel":[61],"trainable":[62],"scale":[63],"matrix,":[64],"mitigates":[66],"potential":[67],"performance":[68,75],"degradation":[69],"during":[70],"sharing.":[72],"achieves":[74],"comparable":[76],"to":[77],"baselines,":[79],"while":[80],"4":[82],"times":[83],"faster":[84],"and":[85,101],"using":[86],"45":[87],"percent":[88],"fewer":[89],"with":[94],"40":[95],"reference":[96],"voices.":[97],"Extensive":[98],"ablation":[99],"studies":[100],"analysis":[102],"further":[103],"validate":[104],"efficiency":[106],"our":[108],"model.":[109]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}