{"id":"https://openalex.org/W2972399707","doi":"https://doi.org/10.21437/interspeech.2019-1798","title":"One-Shot Voice Conversion with Disentangled Representations by Leveraging Phonetic Posteriorgrams","display_name":"One-Shot Voice Conversion with Disentangled Representations by Leveraging Phonetic Posteriorgrams","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972399707","doi":"https://doi.org/10.21437/interspeech.2019-1798","mag":"2972399707"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1798","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Seyed Hamidreza Mohammadi","raw_affiliation_strings":[],"raw_orcid":null,"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":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2028,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84996975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9902999997138977,"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/T11448","display_name":"Face recognition and analysis","score":0.9161999821662903,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7612786293029785},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6922672986984253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6013157963752747},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4581356346607208},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3632102608680725},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09491556882858276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612786293029785},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6922672986984253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6013157963752747},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4581356346607208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3632102608680725},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09491556882858276},{"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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.2019-1798","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.unist.ac.kr:201301/53835","is_oa":false,"landing_page_url":"https://scholarworks.unist.ac.kr/handle/201301/53835","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":[{"display_name":"Reduced inequalities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10"}],"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/W3044321615","https://openalex.org/W4294892107","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2357748469","https://openalex.org/W2392917037","https://openalex.org/W2046675961"],"abstract_inverted_index":{"We":[0,74,111],"propose":[1,100],"voice":[2,24,64],"conversion":[3,17,65],"model":[4,142,148],"from":[5],"arbitrary":[6,10,77,81],"source":[7,29,43,82],"speaker":[8,12,30,44,47,83,93,106,120],"to":[9,21,31,40,84,101,134,165],"target":[11,34,46,85,92],"with":[13,52,130],"disentangled":[14,103],"representations.":[15],"Voice":[16],"is":[18,139],"a":[19,113,131,140],"task":[20],"convert":[22,75],"the":[23,61,155],"of":[25,28,33,63,79,105],"spoken":[26],"utterance":[27],"that":[32],"speaker.":[35],"Most":[36],"prior":[37],"work":[38],"require":[39],"know":[41],"either":[42,53],"or":[45,48,55,90,146],"both":[49],"in":[50,66],"training,":[51],"parallel":[54],"non-parallel":[56],"corpus.":[57],"Instead,":[58],"we":[59,99],"study":[60],"problem":[62],"nonparallel":[67],"speech":[68],"corpora":[69],"and":[70,108,122,150],"one-shot":[71],"learning":[72],"setting.":[73],"an":[76,80],"sentences":[78],"speakers":[86],"given":[87],"only":[88],"one":[89],"few":[91],"training":[94,145],"utterances.":[95,137],"To":[96],"achieve":[97],"this,":[98],"use":[102,112],"representations":[104],"identity":[107],"linguistic":[109,126],"context.":[110],"recurrent":[114],"neural":[115],"network":[116],"(RNN)":[117],"encoder":[118],"for":[119],"embedding":[121],"phonetic":[123],"posteriorgram":[124],"as":[125],"context":[127],"encoding,":[128],"along":[129],"RNN":[132],"decoder":[133],"generate":[135],"converted":[136],"Ours":[138],"simpler":[141],"without":[143],"adversarial":[144],"hierarchical":[147],"design":[149],"thus":[151],"more":[152],"efficient.":[153],"In":[154],"subjective":[156],"tests,":[157],"our":[158],"approach":[159],"achieved":[160],"significantly":[161],"better":[162],"results":[163],"compared":[164],"baseline":[166],"regarding":[167],"similarity.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}