{"id":"https://openalex.org/W4393342192","doi":"https://doi.org/10.1145/3649501","title":"MRMI-TTS: Multi-Reference Audios and Mutual Information Driven Zero-Shot Voice Cloning","display_name":"MRMI-TTS: Multi-Reference Audios and Mutual Information Driven Zero-Shot Voice Cloning","publication_year":2024,"publication_date":"2024-03-30","ids":{"openalex":"https://openalex.org/W4393342192","doi":"https://doi.org/10.1145/3649501"},"language":"en","primary_location":{"id":"doi:10.1145/3649501","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649501","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649501","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3649501","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100348255","display_name":"Yi-Ting Chen","orcid":"https://orcid.org/0000-0001-6748-6832"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ting Chen","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6748-6832","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101423349","display_name":"Wanting Li","orcid":"https://orcid.org/0000-0002-8101-5567"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanting Li","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8101-5567","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014238603","display_name":"Buzhou Tang","orcid":"https://orcid.org/0000-0003-0271-8246"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Buzhou Tang","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0271-8246","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.2778,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57602779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"23","issue":"5","first_page":"1","last_page":"14"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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/cloning","display_name":"Cloning (programming)","score":0.7138513922691345},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6831183433532715},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5687302350997925},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.4198291301727295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3704864978790283},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18602418899536133},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11122116446495056},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09410303831100464}],"concepts":[{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.7138513922691345},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6831183433532715},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5687302350997925},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.4198291301727295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3704864978790283},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18602418899536133},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11122116446495056},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09410303831100464},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649501","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649501","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649501","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3649501","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649501","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649501","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393342192.pdf","grobid_xml":"https://content.openalex.org/works/W4393342192.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2747874407","https://openalex.org/W2752796333","https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2890964092","https://openalex.org/W2914049472","https://openalex.org/W2962788625","https://openalex.org/W2963609956","https://openalex.org/W2963799213","https://openalex.org/W2963964591","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972659941","https://openalex.org/W2991327923","https://openalex.org/W2995181338","https://openalex.org/W3015826515","https://openalex.org/W3016159759","https://openalex.org/W3016181583","https://openalex.org/W3092028330","https://openalex.org/W3095199334","https://openalex.org/W3096086473","https://openalex.org/W3097777922","https://openalex.org/W3139170550","https://openalex.org/W3161436426","https://openalex.org/W3161704465","https://openalex.org/W3196584150","https://openalex.org/W3197659778","https://openalex.org/W3198533616","https://openalex.org/W3205316472","https://openalex.org/W3213544594","https://openalex.org/W4225746985","https://openalex.org/W4226332109","https://openalex.org/W4385245566","https://openalex.org/W6600339963","https://openalex.org/W6739901393","https://openalex.org/W6748588790"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966"],"abstract_inverted_index":{"Voice":[0],"cloning":[1,22,42,59,219],"in":[2,100,191,237],"text-to-speech":[3],"(TTS)":[4],"is":[5,60],"the":[6,10,43,67,166,178,212,216,225,234,245],"process":[7],"of":[8,12,45,56,193,232],"replicating":[9],"voice":[11,21,29,44,58,218],"a":[13,50,63,74,79,84,111,119,138,142,229],"target":[14,68],"speaker":[15,48,64,75,81,94,101,116,124,129,139,148,235],"with":[16],"limited":[17],"data.":[18],"Among":[19],"various":[20],"techniques,":[23],"this":[24,107],"article":[25,108],"focuses":[26],"on":[27,155,165,177,215,244],"zero-shot":[28,57,217],"cloning.":[30],"Although":[31],"existing":[32],"TTS":[33],"models":[34],"can":[35,187],"generate":[36],"high-quality":[37],"speech":[38,190],"for":[39,199],"seen":[40],"speakers,":[41],"an":[46],"unseen":[47,200],"remains":[49],"challenging":[51],"task.":[52,220],"The":[53,126,158],"key":[54],"aspect":[55],"to":[61,77,122,169,203],"obtain":[62,78,146],"embedding":[65,82,117,130,133,206,236],"from":[66,83,92,134],"speaker.":[69],"Previous":[70],"works":[71],"have":[72],"used":[73],"encoder":[76,140],"fixed-size":[80],"single":[85],"reference":[86,205],"audio":[87],"unsupervised,":[88],"but":[89],"they":[90],"suffer":[91],"insufficient":[93],"information":[95,98,163,172],"and":[96,131,141,196],"content":[97,132,143],"leakage":[99],"embedding.":[102,175],"To":[103,145],"address":[104],"these":[105],"issues,":[106],"proposes":[109],"MRMI-TTS,":[110],"FastSpeech2-based":[112],"framework":[113],"that":[114,184,224],"uses":[115],"as":[118],"conditioning":[120],"variable":[121],"provide":[123],"information.":[125],"MRMI-TTS":[127],"extracts":[128],"multi-reference":[135,150],"audios":[136,151],"using":[137],"encoder.":[144],"sufficient":[147],"information,":[149],"are":[152,242],"selected":[153],"based":[154],"sentence":[156],"similarity.":[157],"proposed":[159,226],"model":[160],"applies":[161],"mutual":[162],"minimization":[164],"two":[167],"embeddings":[168],"remove":[170],"entangled":[171],"within":[173],"each":[174],"Experiments":[176],"public":[179],"English":[180],"dataset":[181],"VCTK":[182],"show":[183],"our":[185,209],"method":[186,210,227],"improve":[188],"synthesized":[189],"terms":[192],"both":[194],"similarity":[195],"naturalness,":[197],"even":[198],"speakers.":[201],"Compared":[202],"state-of-the-art":[204],"learned":[207],"methods,":[208],"achieves":[211],"best":[213],"performance":[214],"Furthermore,":[221],"we":[222],"demonstrate":[223],"has":[228],"better":[230],"capability":[231],"maintaining":[233],"different":[238],"languages.":[239],"Sample":[240],"outputs":[241],"available":[243],"demo":[246],"page.":[247],"1":[248]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}