{"id":"https://openalex.org/W2963252329","doi":"https://doi.org/10.21437/interspeech.2018-2525","title":"Investigation of Using Disentangled and Interpretable Representations for One-shot Cross-lingual Voice Conversion","display_name":"Investigation of Using Disentangled and Interpretable Representations for One-shot Cross-lingual Voice Conversion","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2963252329","doi":"https://doi.org/10.21437/interspeech.2018-2525","mag":"2963252329"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2525","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5014830287","display_name":"Seyed Hamidreza Mohammadi","orcid":"https://orcid.org/0000-0002-6892-9241"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Seyed Hamidreza Mohammadi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100359401","display_name":"Tae-Hwan Kim","orcid":"https://orcid.org/0000-0002-5585-6522"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taehwan Kim","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014830287"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.523,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8764151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2833","last_page":"2837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9307000041007996,"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/T10028","display_name":"Topic Modeling","score":0.9229999780654907,"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":0.6203361749649048},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6082166433334351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5733718872070312},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4692430794239044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4219772219657898},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4167470335960388},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10096591711044312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6203361749649048},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6082166433334351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5733718872070312},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4692430794239044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4219772219657898},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4167470335960388},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10096591711044312},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-2525","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.unist.ac.kr:201301/53837","is_oa":false,"landing_page_url":"https://scholarworks.unist.ac.kr/handle/201301/53837","pdf_url":null,"source":{"id":"https://openalex.org/S4306401118","display_name":"Scholarworks@UNIST (Ulsan National Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48566637","host_organization_name":"Ulsan National Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I48566637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"CONFERENCE"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W4287637665","https://openalex.org/W3044321615","https://openalex.org/W4294892107","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2988685434","https://openalex.org/W3192589309"],"abstract_inverted_index":{"We":[0,115,147],"study":[1],"the":[2,60,71,104,117,120,150,168],"problem":[3,61],"of":[4,27,40,73,107,112,119,130],"cross-lingual":[5,175],"voice":[6,109,124,176],"conversion":[7,125],"in":[8,164,167,192],"non-parallel":[9],"speech":[10,22,151,193],"corpora":[11,23],"and":[12,66,69,92,101,133,153,174,189,195],"one-shot":[13],"learning":[14,63],"setting.":[15],"Most":[16],"prior":[17],"work":[18],"require":[19],"either":[20],"parallel":[21],"or":[24,183],"enough":[25],"amount":[26],"training":[28,53,83,87,131,145],"data":[29],"from":[30],"a":[31],"target":[32,46,51,93,113],"speaker.":[33,114],"However,":[34],"we":[35,58,96],"convert":[36],"an":[37,41],"arbitrary":[38,42,90],"sentences":[39],"source":[43,91],"speaker":[44,52],"to":[45,110,137,187],"speaker's":[47],"given":[48,89],"only":[49],"one":[50,144,172],"utterance.":[54,146],"To":[55],"achieve":[56,138],"this,":[57],"formulate":[59],"as":[62],"disentangled":[64],"speaker-specific":[65],"context-specific":[67],"representations":[68,100],"follow":[70],"idea":[72],"[1]":[74],"which":[75],"uses":[76],"Factorized":[77],"Hierarchical":[78],"Variational":[79],"Autoencoder":[80],"(FHVAE).":[81],"After":[82],"FHVAE":[84],"on":[85],"multi-speaker":[86],"data,":[88],"speakers'":[94],"utterance,":[95],"estimate":[97],"those":[98],"latent":[99],"then":[102],"reconstruct":[103],"desired":[105],"utterance":[106],"converted":[108],"that":[111,155],"investigate":[116],"effectiveness":[118],"approach":[121,179],"by":[122],"conducting":[123],"experiments":[126],"with":[127,141],"varying":[128],"size":[129],"utterances":[132],"it":[134],"was":[135],"able":[136],"reasonable":[139],"performance":[140],"even":[142],"just":[143],"also":[148],"examine":[149],"representation":[152],"show":[154],"World":[156],"vocoder":[157],"outperforms":[158],"Short-time":[159],"Fourier":[160],"Transform":[161],"(STFT)":[162],"used":[163],"[1].":[165],"Finally,":[166],"subjective":[169],"tests,":[170],"for":[171],"language":[173],"conversion,":[177],"our":[178],"achieved":[180],"significantly":[181],"better":[182],"comparable":[184],"results":[185],"compared":[186],"VAE-STFT":[188],"GMM":[190],"baselines":[191],"quality":[194],"similarity.":[196]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}