{"id":"https://openalex.org/W3015434413","doi":"https://doi.org/10.1109/icassp40776.2020.9053854","title":"One-Shot Voice Conversion by Vector Quantization","display_name":"One-Shot Voice Conversion by Vector Quantization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015434413","doi":"https://doi.org/10.1109/icassp40776.2020.9053854","mag":"3015434413"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5017182348","display_name":"Da-Yi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Da-Yi Wu","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7734","last_page":"7738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9991000294685364,"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/embedding","display_name":"Embedding","score":0.8777083158493042},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.8343194723129272},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6715620756149292},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6212211847305298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6053457260131836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5856846570968628},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4501049220561981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42916348576545715},{"id":"https://openalex.org/keywords/learning-vector-quantization","display_name":"Learning vector quantization","score":0.41296151280403137},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38436025381088257},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3450906276702881},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09818202257156372}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8777083158493042},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.8343194723129272},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6715620756149292},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6212211847305298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6053457260131836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5856846570968628},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4501049220561981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42916348576545715},{"id":"https://openalex.org/C40567965","wikidata":"https://www.wikidata.org/wiki/Q1820283","display_name":"Learning vector quantization","level":3,"score":0.41296151280403137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38436025381088257},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3450906276702881},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09818202257156372},{"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":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2156142001","https://openalex.org/W2173520492","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2603777577","https://openalex.org/W2608338293","https://openalex.org/W2752796333","https://openalex.org/W2885820941","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2949382160","https://openalex.org/W2962896155","https://openalex.org/W2963539064","https://openalex.org/W2963684088","https://openalex.org/W2963799213","https://openalex.org/W2971074500","https://openalex.org/W2972659941","https://openalex.org/W2972849140","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W6640963894","https://openalex.org/W6685352114","https://openalex.org/W6762533536","https://openalex.org/W6762931180","https://openalex.org/W6768192883"],"related_works":["https://openalex.org/W2100968651","https://openalex.org/W4243803532","https://openalex.org/W1530525041","https://openalex.org/W4244998381","https://openalex.org/W2352648934","https://openalex.org/W4230688072","https://openalex.org/W1915693853","https://openalex.org/W2378212145","https://openalex.org/W2798892016","https://openalex.org/W2202992072"],"abstract_inverted_index":{"In":[0],"this":[1,48],"paper,":[2],"we":[3],"propose":[4],"a":[5,27,51],"vector":[6,40],"quantization":[7],"(VQ)":[8],"based":[9],"one-shot":[10,66],"voice":[11],"conversion":[12],"(VC)":[13],"approach":[14,49],"without":[15],"any":[16],"supervision":[17],"on":[18],"speaker":[19,43,59],"label.":[20],"We":[21,45],"model":[22],"the":[23,34,42,56],"content":[24,57],"embedding":[25],"as":[26,41],"series":[28],"of":[29],"discrete":[30],"codes":[31],"and":[32,38,58,65],"take":[33],"difference":[35],"between":[36],"quantize-before":[37],"quantize-after":[39],"embedding.":[44],"show":[46],"that":[47],"has":[50],"strong":[52],"ability":[53],"to":[54],"disentangle":[55],"information":[60],"with":[61],"reconstruction":[62],"loss":[63],"only,":[64],"VC":[67],"is":[68],"thus":[69],"achieved.":[70]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}