{"id":"https://openalex.org/W4391021547","doi":"https://doi.org/10.1109/asru57964.2023.10389672","title":"Towards General-Purpose Text-Instruction-Guided Voice Conversion","display_name":"Towards General-Purpose Text-Instruction-Guided Voice Conversion","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021547","doi":"https://doi.org/10.1109/asru57964.2023.10389672"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5113145177","display_name":"Chun-Yi Kuan","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":"Chun-Yi Kuan","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029645824","display_name":"Chen-An Li","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":"Chen-An Li","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025040028","display_name":"Tsu-Yuan Hsu","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":"Tsu-Yuan Hsu","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109641559","display_name":"Tse-Yang Lin","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":"Tse-Yang Lin","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111114748","display_name":"Ho-Lam Chung","orcid":"https://orcid.org/0000-0003-3847-0166"},"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":"Ho-Lam Chung","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073201681","display_name":"Kai\u2010Wei Chang","orcid":"https://orcid.org/0000-0002-4991-5274"},"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":"Kai-Wei Chang","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001306222","display_name":"Shuo-Yiin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo-Yiin Chang","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"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":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9940000176429749,"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/T11309","display_name":"Music and Audio Processing","score":0.9872000217437744,"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/computer-science","display_name":"Computer science","score":0.7318066358566284},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45925045013427734},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42605340480804443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318066358566284},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45925045013427734},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42605340480804443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W2077801020","https://openalex.org/W2120605154","https://openalex.org/W2148846882","https://openalex.org/W2532494225","https://openalex.org/W2576309025","https://openalex.org/W2774848319","https://openalex.org/W2889061305","https://openalex.org/W2899361462","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2963539064","https://openalex.org/W2963830550","https://openalex.org/W2964069186","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W2979938509","https://openalex.org/W3015241559","https://openalex.org/W3015805741","https://openalex.org/W3016243847","https://openalex.org/W3025680351","https://openalex.org/W3034999214","https://openalex.org/W3095936335","https://openalex.org/W3098557217","https://openalex.org/W3102628737","https://openalex.org/W3140429000","https://openalex.org/W3161627112","https://openalex.org/W3161695192","https://openalex.org/W3162512456","https://openalex.org/W3168719651","https://openalex.org/W3196475561","https://openalex.org/W3196667132","https://openalex.org/W3197763626","https://openalex.org/W3207300132","https://openalex.org/W3210530853","https://openalex.org/W3215615641","https://openalex.org/W4205742757","https://openalex.org/W4221146610","https://openalex.org/W4225680573","https://openalex.org/W4226162428","https://openalex.org/W4226278401","https://openalex.org/W4300980117","https://openalex.org/W4301371414","https://openalex.org/W4307323391","https://openalex.org/W4312732823","https://openalex.org/W4313679638","https://openalex.org/W4318718996","https://openalex.org/W4318752004","https://openalex.org/W4323651091","https://openalex.org/W4367365521","https://openalex.org/W4372270198","https://openalex.org/W4375869257","https://openalex.org/W4377010126","https://openalex.org/W4377865046","https://openalex.org/W4378501656","https://openalex.org/W4379539302","https://openalex.org/W4380136719","https://openalex.org/W4381786045","https://openalex.org/W4381827575","https://openalex.org/W4382603054","https://openalex.org/W4385574033","https://openalex.org/W4385822787","https://openalex.org/W4390075359","https://openalex.org/W4390912423","https://openalex.org/W4398152753","https://openalex.org/W6746801104","https://openalex.org/W6761580982","https://openalex.org/W6762533536","https://openalex.org/W6769216209","https://openalex.org/W6803547063","https://openalex.org/W6805710207","https://openalex.org/W6810738896","https://openalex.org/W6840412704","https://openalex.org/W6845479124","https://openalex.org/W6848735303","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6849798658","https://openalex.org/W6850334629","https://openalex.org/W6852240503","https://openalex.org/W6852781825","https://openalex.org/W6852859116","https://openalex.org/W6853096648","https://openalex.org/W6853188576","https://openalex.org/W6853611000","https://openalex.org/W6853888607","https://openalex.org/W6853998256"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,18,24,59,66],"novel":[4],"voice":[5,52],"conversion":[6],"(VC)":[7],"model,":[8],"guided":[9],"by":[10],"text":[11,45,81],"instructions":[12,82,144],"such":[13],"as":[14,83],"\u201carticulate":[15],"slowly":[16],"with":[17],"deep":[19],"tone\u201c":[20],"or":[21],"\u201cspeak":[22],"in":[23,72,129,142],"cheerful":[25],"boyish":[26],"voice\u201d.":[27],"Unlike":[28],"traditional":[29],"methods":[30],"that":[31],"rely":[32,104],"on":[33,105],"reference":[34],"utterances":[35],"to":[36,51,86,99,114],"determine":[37],"the":[38,41,73,88,94,119,136],"attributes":[39],"of":[40,68,76,93,118,127,139],"converted":[42,77],"speech,":[43,121],"using":[44],"instruction":[46],"adds":[47],"versatility":[48],"and":[49,90,111,145],"specificity":[50],"conversion.":[53],"The":[54],"proposed":[55],"VC":[56],"model":[57,63,123,141],"is":[58],"neural":[60],"codec":[61],"language":[62],"which":[64,102],"processes":[65],"sequence":[67,75],"discrete":[69],"codes,":[70],"resulting":[71],"code":[74],"speech.":[78,96],"It":[79],"utilizes":[80],"style":[84],"prompts":[85],"modify":[87],"prosody":[89,110],"emotional":[91],"information":[92,126],"given":[95],"In":[97],"contrast":[98],"previous":[100],"approaches,":[101],"often":[103],"employing":[106],"separate":[107],"encoders":[108,113],"like":[109],"content":[112],"handle":[115],"different":[116],"aspects":[117],"source":[120],"our":[122,140],"handles":[124],"various":[125],"speech":[128],"an":[130],"end-to-end":[131],"manner.":[132],"Experiments":[133],"have":[134],"demonstrated":[135],"impressive":[137],"capabilities":[138],"comprehending":[143],"delivering":[146],"reasonable":[147],"results":[148],"<sup":[149],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[151],".":[152]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}