{"id":"https://openalex.org/W3163568691","doi":"https://doi.org/10.1109/icassp39728.2021.9414137","title":"PPG-Based Singing Voice Conversion with Adversarial Representation Learning","display_name":"PPG-Based Singing Voice Conversion with Adversarial Representation Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163568691","doi":"https://doi.org/10.1109/icassp39728.2021.9414137","mag":"3163568691"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414137","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":"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/A5100678759","display_name":"Zhonghao Li","orcid":"https://orcid.org/0000-0003-4200-8126"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhonghao Li","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031898944","display_name":"Benlai Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benlai Tang","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101874107","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-0741-4831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101137823","display_name":"Yuan Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Wan","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112433056","display_name":"Ling Xu","orcid":"https://orcid.org/0000-0003-2553-225X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling Xu","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022877637","display_name":"Chen Shen","orcid":"https://orcid.org/0000-0002-7534-0830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Shen","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100678759"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6711,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94091113,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7073","last_page":"7077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/naturalness","display_name":"Naturalness","score":0.8340343236923218},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8120467662811279},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7573002576828003},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7361366748809814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7251027822494507},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7216566205024719},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.6417331099510193},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5247963666915894},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4864030182361603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37452012300491333},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.2307938039302826},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15548336505889893},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1325337290763855}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8340343236923218},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8120467662811279},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7573002576828003},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7361366748809814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251027822494507},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7216566205024719},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.6417331099510193},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5247963666915894},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4864030182361603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37452012300491333},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2307938039302826},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15548336505889893},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1325337290763855},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414137","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"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":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1590808459","https://openalex.org/W1731081199","https://openalex.org/W1810943226","https://openalex.org/W2127141656","https://openalex.org/W2294038178","https://openalex.org/W2471520273","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2921857201","https://openalex.org/W2939131199","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2963308316","https://openalex.org/W2963609956","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972812066","https://openalex.org/W3012498027","https://openalex.org/W3015922793","https://openalex.org/W3016007107","https://openalex.org/W3016243847","https://openalex.org/W3047855478","https://openalex.org/W3048084370","https://openalex.org/W3095948607","https://openalex.org/W3097152652","https://openalex.org/W4287776895","https://openalex.org/W4298580827","https://openalex.org/W6631190155","https://openalex.org/W6637618735","https://openalex.org/W6638273328","https://openalex.org/W6697024540","https://openalex.org/W6748409065","https://openalex.org/W6762533536","https://openalex.org/W6772037278","https://openalex.org/W6777327638","https://openalex.org/W6781547035","https://openalex.org/W6782110587"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W2623414262","https://openalex.org/W1998721440","https://openalex.org/W2500371832","https://openalex.org/W1995691490","https://openalex.org/W2535215250","https://openalex.org/W1524071955"],"abstract_inverted_index":{"Singing":[0],"voice":[1,8,28,138],"conversion":[2,29,130],"(SVC)":[3],"aims":[4],"to":[5,12,36,78,146],"convert":[6,38],"the":[7,19,73,86,106,122,129],"of":[9,14,26,134],"one":[10,67],"singer":[11,94],"that":[13],"other":[15,74],"singers":[16],"while":[17,40],"keeping":[18,41],"singing":[20,118],"content":[21],"and":[22,44,57,72,81,90,97,109,137],"melody.":[23],"On":[24],"top":[25],"recent":[27],"works,":[30],"we":[31,62],"propose":[32],"a":[33,98],"novel":[34],"model":[35],"steadily":[37],"songs":[39],"their":[42],"naturalness":[43],"intonation.":[45],"We":[46],"build":[47],"an":[48,92],"end-to-end":[49],"architecture,":[50],"taking":[51],"phonetic":[52],"posteriorgrams":[53],"(PPGs)":[54],"as":[55,70],"inputs":[56],"generating":[58],"mel":[59,76],"spectrograms.":[60],"Specifically,":[61],"implement":[63],"two":[64],"separate":[65],"encoders:":[66],"encodes":[68],"PPGs":[69],"content,":[71],"compresses":[75],"spectrograms":[77],"supply":[79],"acoustic":[80],"musical":[82],"information.":[83],"To":[84],"improve":[85,128],"performance":[87,131],"on":[88,114],"timbre":[89],"melody,":[91,136],"adversarial":[93],"confusion":[95],"module":[96,102],"mel-regressive":[99],"representation":[100],"learning":[101],"are":[103,112],"designed":[104],"for":[105,149],"model.":[107],"Objective":[108],"subjective":[110],"experiments":[111],"conducted":[113],"our":[115,124,141],"private":[116],"Chinese":[117],"corpus.":[119],"Comparing":[120],"with":[121],"baselines,":[123],"methods":[125],"can":[126],"significantly":[127],"in":[132],"terms":[133],"naturalness,":[135],"similarity.":[139],"Moreover,":[140],"PPG-based":[142],"method":[143],"is":[144],"proved":[145],"be":[147],"robust":[148],"noisy":[150],"sources.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}