{"id":"https://openalex.org/W4280552695","doi":"https://doi.org/10.21437/interspeech.2022-11225","title":"Towards Improved Zero-shot Voice Conversion with Conditional DSVAE","display_name":"Towards Improved Zero-shot Voice Conversion with Conditional DSVAE","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4280552695","doi":"https://doi.org/10.21437/interspeech.2022-11225"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11225","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11225","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/uc/item/48h1j3rd","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108846913","display_name":"Jiachen Lian","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiachen Lian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458065","display_name":"Chunlei Zhang","orcid":"https://orcid.org/0000-0002-6253-2446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunlei Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068922218","display_name":"Gopala K. Anumanchipalli","orcid":"https://orcid.org/0000-0002-9714-7740"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gopala Krishna Anumanchipalli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108846913"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3568,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8264695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2598","last_page":"2602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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":0.984499990940094,"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/T11309","display_name":"Music and Audio Processing","score":0.920799970626831,"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/embedding","display_name":"Embedding","score":0.8038134574890137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5931333899497986},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.579656720161438},{"id":"https://openalex.org/keywords/conditional-probability-distribution","display_name":"Conditional probability distribution","score":0.5744006037712097},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.542704701423645},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4933580458164215},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4922977685928345},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.47703880071640015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4756695330142975},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.47244909405708313},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4642786383628845},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4341639578342438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38461732864379883},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3463855981826782},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3294212222099304},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2875749468803406},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.13325685262680054},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13290631771087646}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8038134574890137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5931333899497986},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.579656720161438},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.5744006037712097},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.542704701423645},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4933580458164215},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4922977685928345},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.47703880071640015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4756695330142975},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.47244909405708313},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4642786383628845},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4341639578342438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38461732864379883},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3463855981826782},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3294212222099304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2875749468803406},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.13325685262680054},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13290631771087646},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-11225","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11225","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt48h1j3rd","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/48h1j3rd","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt48h1j3rd","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/48h1j3rd","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601","https://openalex.org/W4294770367"],"abstract_inverted_index":{"Disentangling":[0],"content":[1,39,68,84,108,124,136,153],"and":[2,41,133,163,174],"speaking":[3],"style":[4],"information":[5,31,90,113],"is":[6,47,96],"essential":[7],"for":[8,30,49],"zero-shot":[9,50,177],"non-parallel":[10],"voice":[11],"conversion":[12],"(VC).":[13],"Our":[14],"previous":[15],"study":[16],"investigated":[17],"a":[18,98,106,119,127,165,171,175],"novel":[19],"framework":[20],"with":[21,110,181],"disentangled":[22],"sequential":[23],"variational":[24],"autoencoder":[25],"(DSVAE)":[26],"as":[27,126],"the":[28,57,64,71,76,83,88,92,130,135,140,147,157,161,182],"backbone":[29],"decomposition.":[32],"We":[33,74,115],"have":[34],"demonstrated":[35],"that":[36,122,152],"simultaneous":[37],"disentangling":[38],"embedding":[40,43,85,109,137],"speaker":[42],"from":[44,139,156],"one":[45,61],"utterance":[46],"feasible":[48],"VC.":[51],"In":[52,143],"this":[53],"study,":[54],"we":[55,102,150],"continue":[56],"direction":[58],"by":[59],"raising":[60],"concern":[62],"about":[63],"prior":[65,79,131],"distribution":[66,80],"of":[67],"branch":[69],"in":[70],"DSVAE":[72,159,184],"baseline.":[73,185],"find":[75],"random":[77],"initialized":[78],"will":[81],"force":[82],"to":[86,104,129],"reduce":[87],"phonetic-structure":[89],"during":[91],"learning":[93],"process,":[94],"which":[95],"not":[97],"desired":[99],"property.":[100],"Here,":[101],"seek":[103],"achieve":[105,164],"better":[107,167,176],"more":[111],"phonetic":[112],"preserved.":[114],"propose":[116],"conditional":[117,158],"DSVAE,":[118],"new":[120],"model":[121],"enables":[123],"bias":[125],"condition":[128],"modeling":[132],"reshapes":[134],"sampled":[138],"posterior":[141],"distribution.":[142],"our":[144],"experiment":[145],"on":[146],"VCTK":[148],"dataset,":[149],"demonstrate":[151],"embeddings":[154],"derived":[155],"overcome":[160],"randomness":[162],"much":[166],"phoneme":[168],"classification":[169],"accuracy,":[170],"stabilized":[172],"vocalization":[173],"VC":[178],"performance":[179],"compared":[180],"competitive":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2025-10-10T00:00:00"}