{"id":"https://openalex.org/W3198218550","doi":"https://doi.org/10.21437/interspeech.2021-208","title":"A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion","display_name":"A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198218550","doi":"https://doi.org/10.21437/interspeech.2021-208","mag":"3198218550"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-208","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066130866","display_name":"Yuhuai Peng","orcid":"https://orcid.org/0000-0001-9343-5377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Huai Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045615570","display_name":"Ching-Feng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ching-Feng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","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":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1329","last_page":"1333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9696999788284302,"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/speech-recognition","display_name":"Speech recognition","score":0.6630251407623291},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.653934121131897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6096696257591248},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4888281226158142},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1114378273487091}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6630251407623291},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.653934121131897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6096696257591248},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4888281226158142},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1114378273487091},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-208","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2499802997","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466","https://openalex.org/W2757081366"],"abstract_inverted_index":{"We":[0,137],"propose":[1],"a":[2,34,58,79,90,94,102,109],"new":[3],"paradigm":[4],"for":[5,62],"maintaining":[6,160],"speaker":[7,96,115,162],"identity":[8,116],"in":[9,68],"dysarthric":[10,18,87,157],"voice":[11],"conversion":[12],"(DVC).":[13],"The":[14],"poor":[15],"quality":[16,154],"of":[17,33,49,54,73,93,117,124,132,148,155],"speech":[19,31,72,88,92,120,158],"can":[20],"be":[21,130],"greatly":[22],"improved":[23],"by":[24],"statistical":[25],"VC,":[26],"but":[27],"as":[28,97],"the":[29,47,50,74,85,114,118,125,134,146,153,156,161],"normal":[30,71,91],"utterances":[32],"dysarthria":[35],"patient":[36,75,126],"are":[37],"nearly":[38],"impossible":[39],"to":[40,45,122,129,151],"collect,":[41],"previous":[42],"work":[43],"failed":[44],"recover":[46],"individuality":[48],"patient.":[51],"In":[52],"light":[53],"this,":[55],"we":[56],"suggest":[57],"novel,":[59],"two-stage":[60],"approach":[61,150],"DVC,":[63],"which":[64],"is":[65,76],"highly":[66],"flexible":[67],"that":[69,123],"no":[70],"required.":[77],"First,":[78],"powerful":[80],"parallel":[81],"sequence-to-sequence":[82],"model":[83,106],"converts":[84,113],"input":[86],"into":[89],"reference":[95,119],"an":[98],"intermediate":[99],"product,":[100],"and":[101],"nonparallel,":[103],"frame-wise":[104],"VC":[105],"realized":[107],"with":[108],"variational":[110],"autoencoder":[111],"then":[112],"back":[121],"while":[127,159],"assumed":[128],"capable":[131],"preserving":[133],"enhanced":[135],"quality.":[136],"investigate":[138],"several":[139],"design":[140],"options.":[141],"Experimental":[142],"evaluation":[143],"results":[144],"demonstrate":[145],"potential":[147],"our":[149],"improving":[152],"identity.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}