{"id":"https://openalex.org/W4200225196","doi":"https://doi.org/10.1145/3461615.3491106","title":"Improving Model Stability and Training Efficiency in Fast, High Quality Expressive Voice Conversion System","display_name":"Improving Model Stability and Training Efficiency in Fast, High Quality Expressive Voice Conversion System","publication_year":2021,"publication_date":"2021-10-18","ids":{"openalex":"https://openalex.org/W4200225196","doi":"https://doi.org/10.1145/3461615.3491106"},"language":"en","primary_location":{"id":"doi:10.1145/3461615.3491106","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3491106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","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/A5079531245","display_name":"Zhiyuan Zhao","orcid":"https://orcid.org/0000-0002-1227-5058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhao","raw_affiliation_strings":["UBTECH Robotics Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTECH Robotics Corp, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101063775","display_name":"Jingjun Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingjun Liang","raw_affiliation_strings":["UBTECH Robotics Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTECH Robotics Corp, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110945421","display_name":"Zehong Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehong Zheng","raw_affiliation_strings":["UBTECH Robotics Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTECH Robotics Corp, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113953458","display_name":"Linhuang Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linhuang Yan","raw_affiliation_strings":["UBTECH Robotics Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTECH Robotics Corp, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037948910","display_name":"Yang Zhi-yong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Yang","raw_affiliation_strings":["UBTECH Robotics Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTECH Robotics Corp, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112819004","display_name":"Wan Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan Ding","raw_affiliation_strings":["UBTECH Robotics Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTECH Robotics Corp, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091779986","display_name":"Dongyan Huang","orcid":"https://orcid.org/0000-0001-8844-8579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongyan Huang","raw_affiliation_strings":["UBTECH Robotics Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTECH Robotics Corp, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5597,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74466316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"79"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9945999979972839,"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/T12031","display_name":"Speech and dialogue systems","score":0.9835000038146973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7241522669792175},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6090001463890076},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5983424186706543},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5775946974754333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4618351459503174},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10000729560852051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7241522669792175},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6090001463890076},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5983424186706543},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5775946974754333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4618351459503174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10000729560852051},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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},{"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:10.1145/3461615.3491106","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3491106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1977362459","https://openalex.org/W2077801020","https://openalex.org/W2086796102","https://openalex.org/W2152859600","https://openalex.org/W2471520273","https://openalex.org/W2903739847","https://openalex.org/W2963542120","https://openalex.org/W2972473628","https://openalex.org/W2972970915","https://openalex.org/W3082130377","https://openalex.org/W4235201968"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W2358668433","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2997094352"],"abstract_inverted_index":{"Voice":[0],"conversion":[1],"(VC)":[2],"systems":[3],"have":[4],"made":[5],"significant":[6],"progress":[7],"owing":[8],"to":[9,80,100,106,132,176,181],"advanced":[10],"deep":[11],"learning":[12],"methods.":[13],"Current":[14],"research":[15],"is":[16,98,135,159,174],"not":[17],"only":[18],"concerned":[19],"with":[20,46],"high-quality":[21],"and":[22,59,61,85,147,202],"fast":[23],"audio":[24],"synthesis,":[25],"but":[26],"also":[27,63],"richer":[28],"expressiveness.":[29],"The":[30,186],"most":[31],"popular":[32],"VC":[33,90,157,179],"system":[34,53,130,145,158,167,180,197],"was":[35],"constructed":[36],"from":[37,55],"the":[38,82,102,113,123,143,148,165,177,193,196],"concatenation":[39],"of":[40,68,88,104,128,142,155,164],"an":[41,78],"automatic":[42],"speech":[43,184,204],"recognition":[44,58],"module":[45,49],"a":[47,65,71,89,93],"text-to-speech":[48],"(ASR-TTS).":[50],"Yet":[51],"this":[52],"suffers":[54],"errors":[56],"in":[57],"pronunciation":[60],"it":[62],"requires":[64],"large":[66],"amount":[67],"data":[69,94],"for":[70],"pre-trained":[72,178],"ASR":[73],"mode":[74],"l.":[75],"We":[76],"propose":[77],"approach":[79],"improve":[81],"model":[83],"stability":[84],"training":[86,114],"efficiency":[87],"system.":[91],"Firstly,":[92],"redundancy":[95],"reduction":[96],"method":[97],"used":[99],"balance":[101],"distribution":[103],"vocabulary":[105],"avoid":[107],"uncommon":[108],"words":[109],"being":[110],"ignored":[111],"during":[112],"process;":[115],"by":[116],"adding":[117],"connectionist":[118],"temporal":[119],"classification":[120],"(CTC)":[121],"loss,":[122],"word":[124],"error":[125],"rate":[126,153,169],"(WER)":[127],"our":[129,156],"reduces":[131],"3.02%,":[133],"which":[134],"5.63":[136],"percentage":[137],"points":[138],"lower":[139],"than":[140,162],"that":[141,163,189],"ASR-TTS":[144],"(8.65%),":[146],"inference":[149],"speed":[150],"(e.g.,":[151],"real-time":[152],"19.32)":[154],"much":[160],"higher":[161],"baseline":[166],"(real-time":[168],"2.24).":[170],"Finally,":[171],"emotional":[172],"embedding":[173],"added":[175],"generate":[182],"expressive":[183,203],"conversion.":[185],"results":[187],"show":[188],"after":[190],"fine-tuning":[191],"on":[192],"multi-emotional":[194],"dataset,":[195],"can":[198],"achieve":[199],"high":[200],"quality":[201],"synthesis.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}