{"id":"https://openalex.org/W4396747569","doi":"https://doi.org/10.1007/s11063-024-11613-0","title":"WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion","display_name":"WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4396747569","doi":"https://doi.org/10.1007/s11063-024-11613-0"},"language":"en","primary_location":{"id":"doi:10.1007/s11063-024-11613-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11613-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11613-0.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11613-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038484959","display_name":"Kyungdeuk Ko","orcid":"https://orcid.org/0000-0003-3461-8645"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyungdeuk Ko","raw_affiliation_strings":["School of Electrical Engineering, Korea University, 02841, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, 02841, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334099","display_name":"Donghyeon Kim","orcid":"https://orcid.org/0000-0002-8224-8354"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghyeon Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea University, 02841, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, 02841, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114158478","display_name":"Kyungseok Oh","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungseok Oh","raw_affiliation_strings":["School of Electrical Engineering, Korea University, 02841, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, 02841, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026204977","display_name":"Hanseok Ko","orcid":"https://orcid.org/0000-0002-8744-4514"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanseok Ko","raw_affiliation_strings":["School of Electrical Engineering, Korea University, 02841, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, 02841, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038484959"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.8185,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86666045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"56","issue":"3","first_page":null,"last_page":null},"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":0.9995999932289124,"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":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.7724166512489319},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7312431931495667},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6471669673919678},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5540835857391357},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4607895314693451},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4180944561958313},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40082770586013794},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20841124653816223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724166512489319},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7312431931495667},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6471669673919678},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5540835857391357},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4607895314693451},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4180944561958313},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40082770586013794},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20841124653816223},{"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:10.1007/s11063-024-11613-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11613-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11613-0.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11063-024-11613-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11613-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11613-0.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396747569.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2022125261","https://openalex.org/W2104604339","https://openalex.org/W2471520273","https://openalex.org/W2526425061","https://openalex.org/W2603777577","https://openalex.org/W2904459034","https://openalex.org/W2932319787","https://openalex.org/W2962788625","https://openalex.org/W2963411216","https://openalex.org/W2963539064","https://openalex.org/W2963609956","https://openalex.org/W2963767194","https://openalex.org/W2969985801","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W2972812066","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3015356564","https://openalex.org/W3015434413","https://openalex.org/W3015805741","https://openalex.org/W3095173472","https://openalex.org/W3095361818","https://openalex.org/W3096524539","https://openalex.org/W3096831136","https://openalex.org/W3161558238","https://openalex.org/W3161627112","https://openalex.org/W3163475957","https://openalex.org/W3168719651","https://openalex.org/W3196667132","https://openalex.org/W3197659778","https://openalex.org/W3205878676","https://openalex.org/W4221146610","https://openalex.org/W4242185151","https://openalex.org/W4294982498","https://openalex.org/W4375868976","https://openalex.org/W6632668414","https://openalex.org/W6776948474"],"related_works":["https://openalex.org/W4214896311","https://openalex.org/W2998781440","https://openalex.org/W2064065729","https://openalex.org/W1840351222","https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2550171623","https://openalex.org/W596245619"],"abstract_inverted_index":{"Abstract":[0],"Voice":[1],"conversion":[2,87],"(VC)":[3],"is":[4,43,157,181],"a":[5,12,40,78,98,184],"task":[6],"for":[7],"changing":[8],"the":[9,16,24,51,57,115,122,126,129,141,144,153,171,174,178,190,194,199],"speech":[10,62,79,134,146,151,166,180,192],"of":[11,23,117,125,143,159,177,198],"source":[13,25,145,179,200],"speaker":[14],"to":[15,45,67,139,188],"target":[17],"voice":[18,86],"while":[19,162],"preserving":[20],"linguistic":[21],"information":[22],"speech.":[26,201],"The":[27,216],"existing":[28],"VC":[29,52,104,212],"methods":[30,208],"typically":[31],"use":[32],"mel-spectrogram":[33,47],"as":[34,70],"both":[35,210],"input":[36],"and":[37,60,80,101,136,147,167,213],"output,":[38],"so":[39],"separate":[41,99],"vocoder":[42,58,100],"required":[44],"transform":[46],"into":[48],"waveform.":[49],"Therefore,":[50],"performance":[53,118],"varies":[54],"depending":[55],"on":[56,106],"performance,":[59],"noisy":[61],"can":[63,102],"be":[64],"generated":[65],"due":[66],"problems":[68],"such":[69],"train-test":[71,123],"mismatch.":[72],"In":[73,128,170],"this":[74],"paper,":[75],"we":[76],"propose":[77],"fundamental":[81,168,195],"frequency":[82,196],"consistent":[83,150],"raw":[84,107],"audio":[85,108],"method":[88],"called":[89],"WaveVC.":[90],"Unlike":[91],"other":[92],"methods,":[93],"WaveVC":[94,132,156,202],"does":[95],"not":[96],"require":[97],"perform":[103],"directly":[105],"waveform":[109],"using":[110,152],"1D":[111],"convolution.":[112],"This":[113],"eliminates":[114],"issue":[116],"degradation":[119],"caused":[120],"by":[121],"mismatch":[124],"vocoder.":[127],"training":[130],"phase,":[131,173],"employs":[133],"loss":[135,138],"F0":[137,149,175],"preserve":[140],"content":[142,185],"generate":[148],"pre-trained":[154],"networks.":[155],"capable":[158],"converting":[160],"voices":[161],"maintaining":[163],"consistency":[164],"in":[165,209],"frequency.":[169],"test":[172],"feature":[176],"concatenated":[182],"with":[183],"embedding":[186],"vector":[187],"ensure":[189],"converted":[191,217],"follows":[193],"flow":[197],"achieves":[203],"higher":[204],"performances":[205],"than":[206],"baseline":[207],"many-to-many":[211],"any-to-any":[214],"VC.":[215],"samples":[218],"are":[219],"available":[220],"online.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-20T23:13:51.555489","created_date":"2025-10-10T00:00:00"}