{"id":"https://openalex.org/W2885820941","doi":"https://doi.org/10.1109/slt.2018.8639647","title":"Rhythm-Flexible Voice Conversion Without Parallel Data Using Cycle-GAN Over Phoneme Posteriorgram Sequences","display_name":"Rhythm-Flexible Voice Conversion Without Parallel Data Using Cycle-GAN Over Phoneme Posteriorgram Sequences","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2885820941","doi":"https://doi.org/10.1109/slt.2018.8639647","mag":"2885820941"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5074874599","display_name":"Cheng-chieh Yeh","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":true,"raw_author_name":"Cheng-chieh Yeh","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034235870","display_name":"Po\u2010Chun Hsu","orcid":"https://orcid.org/0000-0002-6509-9377"},"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":"Po-chun Hsu","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049062211","display_name":"Ju-Chieh Chou","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":"Ju-chieh Chou","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","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"],"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/A5044010123","display_name":"Lin-shan Lee","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":"Lin-shan Lee","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"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":5,"corresponding_author_ids":["https://openalex.org/A5074874599"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":2.2804,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90921417,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"274","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.7438240051269531},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7078115344047546},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.6834955811500549},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5985214114189148},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5724949836730957},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5713980793952942},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5659759044647217},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.43998444080352783},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42956608533859253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3994140028953552},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3689761757850647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14250025153160095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7438240051269531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7078115344047546},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.6834955811500549},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5985214114189148},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5724949836730957},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5713980793952942},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5659759044647217},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.43998444080352783},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42956608533859253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3994140028953552},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3689761757850647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14250025153160095},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"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":59,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W1494198834","https://openalex.org/W1540882196","https://openalex.org/W1588037970","https://openalex.org/W1959608418","https://openalex.org/W2022125261","https://openalex.org/W2049515993","https://openalex.org/W2077801020","https://openalex.org/W2099471712","https://openalex.org/W2120605154","https://openalex.org/W2120847449","https://openalex.org/W2123003832","https://openalex.org/W2124641009","https://openalex.org/W2125389028","https://openalex.org/W2126143605","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2142300631","https://openalex.org/W2156142001","https://openalex.org/W2507912506","https://openalex.org/W2518172956","https://openalex.org/W2518312472","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2531207078","https://openalex.org/W2532494225","https://openalex.org/W2608338293","https://openalex.org/W2651834199","https://openalex.org/W2666408839","https://openalex.org/W2747874407","https://openalex.org/W2774848319","https://openalex.org/W2787748320","https://openalex.org/W2805669069","https://openalex.org/W2962793481","https://openalex.org/W2962896155","https://openalex.org/W2963539064","https://openalex.org/W2963609956","https://openalex.org/W2963767194","https://openalex.org/W2963808252","https://openalex.org/W2963830550","https://openalex.org/W2964069186","https://openalex.org/W2964135678","https://openalex.org/W2964308564","https://openalex.org/W4320013936","https://openalex.org/W6600438624","https://openalex.org/W6632513598","https://openalex.org/W6635180523","https://openalex.org/W6640963894","https://openalex.org/W6678815747","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6728267052","https://openalex.org/W6736811364","https://openalex.org/W6736996214","https://openalex.org/W6737196085","https://openalex.org/W6745718552","https://openalex.org/W6746801104","https://openalex.org/W6751928472","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W258725851"],"abstract_inverted_index":{"Speaking":[0],"rate":[1],"refers":[2],"to":[3,18,58,67,86,89,120,146,168],"the":[4,14,68,79,82,92,97,101,108,112,122,148,151,161],"average":[5],"number":[6],"of":[7,23,34,81,91],"phonemes":[8,25],"within":[9,26],"some":[10],"unit":[11],"time,":[12],"while":[13],"rhythmic":[15,105],"patterns":[16,106],"refer":[17],"duration":[19],"distributions":[20],"for":[21,41,76,107,155],"realizations":[22],"different":[24,27,40,42,156],"phonetic":[28],"structures.":[29],"Both":[30],"are":[31,130],"key":[32],"components":[33],"prosody":[35],"in":[36,99],"speech,":[37],"which":[38,95],"is":[39,166],"speakers.":[43,157],"Models":[44],"like":[45],"cycle-consistent":[46],"adversarial":[47],"network":[48,70],"(Cycle-GAN)":[49],"and":[50,72,104],"variational":[51],"auto-encoder":[52],"(VAE)":[53],"have":[54],"been":[55],"successfully":[56],"applied":[57],"voice":[59,171],"conversion":[60,172],"tasks":[61],"without":[62,173],"parallel":[63,127,175],"data.":[64,176],"However,":[65],"due":[66],"neural":[69],"architectures":[71],"feature":[73],"vectors":[74],"chosen":[75],"these":[77],"approaches,":[78],"length":[80,124,162],"predicted":[83],"utterance":[84],"has":[85],"be":[87],"fixed":[88],"that":[90],"input":[93],"utterance,":[94],"limits":[96],"flexibility":[98],"mimicking":[100],"speaking":[102],"rates":[103],"target":[109],"speaker.":[110],"On":[111],"other":[113],"hand,":[114],"sequence-to-sequence":[115,140],"learning":[116],"model":[117,141],"was":[118],"used":[119],"remove":[121],"above":[123,165],"constraint,":[125],"but":[126],"training":[128],"data":[129],"needed.":[131],"In":[132,158],"this":[133,159],"paper,":[134],"we":[135],"propose":[136],"an":[137],"approach":[138],"utilizing":[139],"trained":[142],"with":[143],"unsupervised":[144],"Cycle-GAN":[145],"perform":[147],"transformation":[149],"between":[150],"phoneme":[152],"posteriorgram":[153],"sequences":[154],"way,":[160],"constraint":[163],"mentioned":[164],"removed":[167],"offer":[169],"rhythm-flexible":[170],"requiring":[174],"Preliminary":[177],"evaluation":[178],"on":[179],"two":[180],"datasets":[181],"showed":[182],"very":[183],"encouraging":[184],"results.":[185]},"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":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}