{"id":"https://openalex.org/W4225322394","doi":"https://doi.org/10.1109/icassp43922.2022.9747625","title":"Disentangling Content and Fine-Grained Prosody Information Via Hybrid ASR Bottleneck Features for Voice Conversion","display_name":"Disentangling Content and Fine-Grained Prosody Information Via Hybrid ASR Bottleneck Features for Voice Conversion","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225322394","doi":"https://doi.org/10.1109/icassp43922.2022.9747625"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747625","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5080440096","display_name":"Xintao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xintao Zhao","raw_affiliation_strings":["Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610446","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0002-1074-2601"},"institutions":[{"id":"https://openalex.org/I4210167198","display_name":"CSSC Offshore & Marine Engineering Company (China)","ror":"https://ror.org/05phhyq88","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210167198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["Huya Inc,Guangzhou,China","Huya Inc, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc,Guangzhou,China","institution_ids":["https://openalex.org/I4210167198"]},{"raw_affiliation_string":"Huya Inc, Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048029954","display_name":"Changhe Song","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Changhe Song","raw_affiliation_strings":["Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667025","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-6527-5502"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[{"id":"https://openalex.org/I4210167198","display_name":"CSSC Offshore & Marine Engineering Company (China)","ror":"https://ror.org/05phhyq88","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210167198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Huya Inc,Guangzhou,China","Huya Inc, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc,Guangzhou,China","institution_ids":["https://openalex.org/I4210167198"]},{"raw_affiliation_string":"Huya Inc, Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043757154","display_name":"Deyi Tuo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167198","display_name":"CSSC Offshore & Marine Engineering Company (China)","ror":"https://ror.org/05phhyq88","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210167198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyi Tuo","raw_affiliation_strings":["Huya Inc,Guangzhou,China","Huya Inc, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc,Guangzhou,China","institution_ids":["https://openalex.org/I4210167198"]},{"raw_affiliation_string":"Huya Inc, Guangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0486,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95074491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7022","last_page":"7026"},"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":0.9977999925613403,"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":0.9962999820709229,"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":0.7495219707489014},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7360683679580688},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7262697815895081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6927300691604614},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4729692041873932},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.467338889837265},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42440733313560486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4174298644065857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495219707489014},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7360683679580688},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7262697815895081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6927300691604614},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4729692041873932},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.467338889837265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42440733313560486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4174298644065857},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747625","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1731081199","https://openalex.org/W2127141656","https://openalex.org/W2194775991","https://openalex.org/W2284628133","https://openalex.org/W2518172956","https://openalex.org/W2897353073","https://openalex.org/W2899663614","https://openalex.org/W2962896155","https://openalex.org/W2963242190","https://openalex.org/W2964243274","https://openalex.org/W2972659941","https://openalex.org/W2982223350","https://openalex.org/W2996414377","https://openalex.org/W3022876224","https://openalex.org/W3034794073","https://openalex.org/W3083423753","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3097001834","https://openalex.org/W3097777922","https://openalex.org/W3099078140","https://openalex.org/W3101689408","https://openalex.org/W3135654121","https://openalex.org/W3135774711","https://openalex.org/W3165478005","https://openalex.org/W3198082505","https://openalex.org/W6623517193","https://openalex.org/W6637618735","https://openalex.org/W6695553435","https://openalex.org/W6726528559","https://openalex.org/W6755977528","https://openalex.org/W6761580982","https://openalex.org/W6776390925","https://openalex.org/W6780226713","https://openalex.org/W6780493881","https://openalex.org/W6783867762","https://openalex.org/W6785090365"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W4387098302","https://openalex.org/W2626699140","https://openalex.org/W3165080709","https://openalex.org/W2948317131","https://openalex.org/W169399214","https://openalex.org/W3100825170"],"abstract_inverted_index":{"Non-parallel":[0],"data":[1],"voice":[2],"conversion":[3],"(VC)":[4],"have":[5,26,184],"achieved":[6],"considerable":[7],"breakthroughs":[8],"recently":[9],"through":[10],"introducing":[11],"bottleneck":[12,109],"features":[13,110],"(BNFs)":[14],"extracted":[15,68,111],"by":[16,90],"the":[17,56,78,81,91,168,171,181,186],"automatic":[18],"speech":[19,61,83],"recognition(ASR)":[20],"model.":[21],"However,":[22],"selection":[23],"of":[24,59,80,93],"BNFs":[25,37,66],"a":[27,53],"significant":[28],"impact":[29],"on":[30,185],"VC":[31,54,105],"result.":[32],"For":[33],"example,":[34],"when":[35],"extracting":[36],"from":[38,69,112,133,138],"ASR":[39,70],"trained":[40,71],"with":[41],"Cross":[42],"Entropy":[43],"loss":[44,76],"(CE-BNFs)":[45],"and":[46,114,124,135,142,166,176],"feeding":[47],"into":[48],"neural":[49],"network":[50],"to":[51,116,129,147],"train":[52],"system,":[55],"timbre":[57],"similarity":[58],"converted":[60,82,187],"is":[62,88],"significantly":[63],"degraded.":[64],"If":[65],"are":[67],"using":[72,107],"Connectionist":[73],"Temporal":[74],"Classification":[75],"(CTC-BNFs),":[77],"naturalness":[79],"may":[84],"decrease.":[85],"This":[86],"phenomenon":[87],"caused":[89],"difference":[92],"information":[94,132,137,172],"contained":[95,173],"in":[96,174],"BNFs.":[97],"In":[98],"this":[99],"paper,":[100],"we":[101],"proposed":[102,156],"an":[103],"any-to-one":[104],"method":[106,157,165],"hybrid":[108],"CTC-BNFs":[113,177],"CE-BNFs":[115,134,175],"complement":[117],"each":[118],"other":[119],"advantages.":[120],"Gradient":[121],"reversal":[122],"layer":[123],"instance":[125],"normalization":[126],"were":[127,145],"used":[128,146],"extract":[130],"prosody":[131],"content":[136],"CTC-BNFs.":[139],"Auto-regressive":[140],"decoder":[141],"Hifi-GAN":[143],"vocoder":[144],"generate":[148],"high-quality":[149],"waveform.":[150],"Experimental":[151],"results":[152],"show":[153],"that":[154],"our":[155],"achieves":[158],"higher":[159],"similarity,":[160],"naturalness,":[161],"quality":[162],"than":[163],"baseline":[164],"reveals":[167],"differences":[169],"between":[170],"as":[178,180],"well":[179],"influence":[182],"they":[183],"speech.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}