{"id":"https://openalex.org/W4372260434","doi":"https://doi.org/10.1109/icassp49357.2023.10096399","title":"LIMI-VC: A Light Weight Voice Conversion Model with Mutual Information Disentanglement","display_name":"LIMI-VC: A Light Weight Voice Conversion Model with Mutual Information Disentanglement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260434","doi":"https://doi.org/10.1109/icassp49357.2023.10096399"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096399","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/A5068030070","display_name":"Liangjie Huang","orcid":"https://orcid.org/0000-0003-0770-1582"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liangjie Huang","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071435827","display_name":"Yuan Tian","orcid":"https://orcid.org/0000-0001-6073-8582"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Yuan","raw_affiliation_strings":["Baidu (China) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Baidu (China) Co., Ltd","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014231387","display_name":"Yunming Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunming Liang","raw_affiliation_strings":["Baidu (China) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Baidu (China) Co., Ltd","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662054","display_name":"Zeyu Chen","orcid":"https://orcid.org/0000-0001-6286-0581"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Chen","raw_affiliation_strings":["Baidu (China) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Baidu (China) Co., Ltd","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103538052","display_name":"Can Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Wen","raw_affiliation_strings":["Baidu (China) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Baidu (China) Co., Ltd","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006684220","display_name":"Yanlu Xie","orcid":"https://orcid.org/0000-0001-6765-4808"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlu Xie","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052176517","display_name":"Jinsong Zhang","orcid":"https://orcid.org/0000-0002-1603-3136"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Zhang","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102845007","display_name":"Dengfeng Ke","orcid":"https://orcid.org/0000-0001-8459-0412"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengfeng Ke","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5068030070"],"corresponding_institution_ids":["https://openalex.org/I115212828"],"apc_list":null,"apc_paid":null,"fwci":0.6203,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63186637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9991999864578247,"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/timbre","display_name":"Timbre","score":0.8695176839828491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7368757128715515},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.687089741230011},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.667661190032959},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6241984367370605},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5520777702331543},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4915686547756195},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48654118180274963},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4272221624851227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37796300649642944},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17600879073143005}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8695176839828491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368757128715515},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.687089741230011},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.667661190032959},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6241984367370605},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5520777702331543},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4915686547756195},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48654118180274963},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4272221624851227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37796300649642944},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17600879073143005},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096399","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2945478979","https://openalex.org/W2949759968","https://openalex.org/W2953333557","https://openalex.org/W2954386831","https://openalex.org/W3034794073","https://openalex.org/W3036928441","https://openalex.org/W3098557217","https://openalex.org/W3160919572","https://openalex.org/W3161627112","https://openalex.org/W3197659778","https://openalex.org/W3198082505","https://openalex.org/W3213227271","https://openalex.org/W4205742757","https://openalex.org/W4224309976","https://openalex.org/W4225939199","https://openalex.org/W4286747238","https://openalex.org/W4293469690","https://openalex.org/W4296068587","https://openalex.org/W6729906282","https://openalex.org/W6762533536","https://openalex.org/W6762796984","https://openalex.org/W6765069029","https://openalex.org/W6776390925","https://openalex.org/W6779459370","https://openalex.org/W6803159591","https://openalex.org/W6810889627"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W3109975354","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W2037604299"],"abstract_inverted_index":{"Voice":[0],"conversion(VC)":[1],"model":[2,75,101,123],"aims":[3],"to":[4,9,20,113],"convert":[5],"the":[6,10,22,35,48,58,61,65,74,82,99,105,126],"source":[7,129],"timbre":[8,36,66],"target":[11],"one.":[12],"Recently,":[13],"many":[14],"VC":[15],"models":[16,19,30,91],"utilize":[17],"pre-trained":[18,29,90],"enhance":[21],"performance":[23],"and":[24,37,64,86,131],"achieve":[25],"good":[26],"results.":[27],"However,":[28],"could":[31],"not":[32],"somehow":[33],"disentangle":[34],"linguistic":[38,62],"information,":[39],"thus":[40],"resulting":[41],"in":[42,76],"a":[43,77],"redundancy,":[44],"which":[45],"may":[46],"hurt":[47],"conversion":[49],"performance.":[50],"In":[51],"this":[52],"paper":[53],"we":[54],"proposed":[55,100],"LIMI-VC,":[56],"reducing":[57],"redundancy":[59],"between":[60],"content":[63],"information":[67,70],"with":[68,107],"mutual":[69],"disentanglement.":[71],"We":[72],"design":[73],"light":[78],"weight":[79],"form,":[80],"for":[81],"sake":[83],"of":[84],"parameter":[85],"computation":[87],"efficiency":[88],"when":[89],"are":[92],"commonly":[93],"used":[94],"nowadays.":[95],"Experiments":[96],"show":[97],"that":[98,121],"can":[102],"still":[103],"improve":[104],"performance,":[106],"15":[108],"times":[109],"smaller":[110],"size,":[111],"compared":[112],"baseline.":[114,127],"An":[115],"out-of-domain":[116],"cross-lingual":[117],"inference":[118],"also":[119],"shows":[120],"our":[122],"greatly":[124],"outperforms":[125],"Our":[128],"code":[130],"audio":[132],"examples":[133],"will":[134],"be":[135],"available":[136],"at:":[137],"https://github.com/WongLaw/LIMI-VC.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}