{"id":"https://openalex.org/W3095953768","doi":"https://doi.org/10.1109/icassp39728.2021.9413699","title":"Fragmentvc: Any-To-Any Voice Conversion by End-To-End Extracting and Fusing Fine-Grained Voice Fragments with Attention","display_name":"Fragmentvc: Any-To-Any Voice Conversion by End-To-End Extracting and Fusing Fine-Grained Voice Fragments with Attention","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3095953768","doi":"https://doi.org/10.1109/icassp39728.2021.9413699","mag":"3095953768"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.14150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047521320","display_name":"Yist Y. Lin","orcid":"https://orcid.org/0009-0000-9054-1596"},"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":"Yist Y. Lin","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072923563","display_name":"Chung-Ming Chien","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":"Chung-Ming Chien","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084818946","display_name":"Jheng-Hao 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":"Jheng-Hao Lin","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","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","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","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","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047521320"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.56,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71572389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5939","last_page":"5943"},"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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/T10860","display_name":"Speech and Audio Processing","score":0.9948999881744385,"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/utterance","display_name":"Utterance","score":0.8557770252227783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7592454552650452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7267963290214539},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6464575529098511},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6018762588500977},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6017436981201172},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5377628207206726},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.45986175537109375},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4262336492538452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3748653531074524},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07223361730575562},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05935069918632507}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8557770252227783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592454552650452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7267963290214539},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6464575529098511},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6018762588500977},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6017436981201172},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5377628207206726},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.45986175537109375},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4262336492538452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3748653531074524},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07223361730575562},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05935069918632507},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.14150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14150","pdf_url":"https://arxiv.org/pdf/2010.14150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3095953768","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.14150.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.14150","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.14150","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/2g9f-k613","is_oa":true,"landing_page_url":"https://doi.org/10.17023/2g9f-k613","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.14150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14150","pdf_url":"https://arxiv.org/pdf/2010.14150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095953768.pdf","grobid_xml":"https://content.openalex.org/works/W3095953768.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W75668230","https://openalex.org/W95152782","https://openalex.org/W1494198834","https://openalex.org/W1901129140","https://openalex.org/W2017425464","https://openalex.org/W2126143605","https://openalex.org/W2150658333","https://openalex.org/W2156142001","https://openalex.org/W2402356521","https://openalex.org/W2527729766","https://openalex.org/W2899877258","https://openalex.org/W2902070858","https://openalex.org/W2908510526","https://openalex.org/W2949281321","https://openalex.org/W2954386831","https://openalex.org/W2962788625","https://openalex.org/W2963403868","https://openalex.org/W2963432880","https://openalex.org/W2963539064","https://openalex.org/W2963830550","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972659941","https://openalex.org/W2994715919","https://openalex.org/W3015719750","https://openalex.org/W3099782249","https://openalex.org/W6603100307","https://openalex.org/W6603838645","https://openalex.org/W6739901393","https://openalex.org/W6752888775","https://openalex.org/W6757817989","https://openalex.org/W6762533536","https://openalex.org/W6771070734","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W3161627112","https://openalex.org/W2937343983","https://openalex.org/W2795409001","https://openalex.org/W2887894196","https://openalex.org/W2584329820","https://openalex.org/W2098403941","https://openalex.org/W2993859014","https://openalex.org/W2122968425","https://openalex.org/W2563906718","https://openalex.org/W3163929126","https://openalex.org/W3197659778","https://openalex.org/W3097815667","https://openalex.org/W2898654681","https://openalex.org/W81036719","https://openalex.org/W3024476726","https://openalex.org/W100511780","https://openalex.org/W3087422378","https://openalex.org/W2765233562","https://openalex.org/W2916104401","https://openalex.org/W3158457675"],"abstract_inverted_index":{"Any-to-any":[0],"voice":[1,7,97],"conversion":[2],"aims":[3],"to":[4,10,23,94],"convert":[5],"the":[6,43,48,51,60,64,67,77,81,100,108,114],"from":[8,50,56,66,72,99],"and":[9,104,126,144,147,158,174],"any":[11,139],"speakers":[12],"even":[13],"unseen":[14],"during":[15],"training,":[16],"which":[17,42],"is":[18,54,92,127,132],"much":[19,29],"more":[20,30],"challenging":[21],"compared":[22],"one-to-one":[24],"or":[25],"many-to-many":[26],"tasks,":[27],"but":[28],"attractive":[31],"in":[32,41],"real-world":[33],"scenarios.":[34],"In":[35],"this":[36,166],"paper":[37],"we":[38],"proposed":[39],"FragmentVC,":[40],"latent":[44],"phonetic":[45],"structure":[46],"of":[47,63,80,117],"utterance":[49],"source":[52],"speaker":[53,69,102,145,156],"obtained":[55,71],"Wav2Vec":[57],"2.0,":[58],"while":[59],"spectral":[61],"features":[62],"utterance(s)":[65,103],"target":[68,101],"are":[70],"log":[73],"mel-spectrograms.":[74],"By":[75],"aligning":[76],"hidden":[78],"structures":[79],"two":[82],"different":[83],"feature":[84],"spaces":[85],"with":[86,121,134,161],"a":[87],"two-stage":[88],"training":[89],"process,":[90],"FragmentVC":[91],"able":[93],"extract":[95],"fine-grained":[96],"fragments":[98],"fuse":[105],"them":[106],"into":[107],"desired":[109],"utterance,":[110],"all":[111],"based":[112,154],"on":[113,123,155],"attention":[115,124],"mechanism":[116],"Transformer":[118],"as":[119,172],"verified":[120],"analysis":[122],"maps,":[125],"accomplished":[128],"end-to-end.":[129],"This":[130],"approach":[131,167],"trained":[133],"reconstruction":[135],"loss":[136],"only":[137],"without":[138],"disentanglement":[140],"considerations":[141],"between":[142],"content":[143],"information":[146],"doesn't":[148],"require":[149],"parallel":[150],"data.":[151],"Objective":[152],"evaluation":[153,160],"verification":[157],"subjective":[159],"MOS":[162],"both":[163],"showed":[164],"that":[165],"outperformed":[168],"SOTA":[169],"approaches,":[170],"such":[171],"AdaIN-VC":[173],"AutoVC.":[175]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-25T00:00:00"}
