{"id":"https://openalex.org/W4386000151","doi":"https://doi.org/10.1142/s271755452350011x","title":"Disentangling Content Information by Combining ASR and TTS Bottleneck Features for Voice Conversion","display_name":"Disentangling Content Information by Combining ASR and TTS Bottleneck Features for Voice Conversion","publication_year":2023,"publication_date":"2023-03-01","ids":{"openalex":"https://openalex.org/W4386000151","doi":"https://doi.org/10.1142/s271755452350011x"},"language":"en","primary_location":{"id":"doi:10.1142/s271755452350011x","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s271755452350011x","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-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/A5027131702","display_name":"Zeqing Zhao","orcid":"https://orcid.org/0000-0002-9868-306X"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zeqing Zhao","raw_affiliation_strings":["AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-9868-306X","affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014318166","display_name":"Sifan Ma","orcid":"https://orcid.org/0000-0003-4716-5622"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifan Ma","raw_affiliation_strings":["AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-4716-5622","affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101605745","display_name":"Yan Jia","orcid":"https://orcid.org/0000-0001-6632-2131"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Jia","raw_affiliation_strings":["AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China"],"raw_orcid":"https://orcid.org/0000-0001-6632-2131","affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040030708","display_name":"Jingyu Hou","orcid":"https://orcid.org/0000-0002-7288-3717"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyu Hou","raw_affiliation_strings":["AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-7288-3717","affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505673","display_name":"Lin Yang","orcid":"https://orcid.org/0009-0009-5570-6063"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Yang","raw_affiliation_strings":["AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China"],"raw_orcid":"https://orcid.org/0009-0009-5570-6063","affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395810","display_name":"Junjie Wang","orcid":"https://orcid.org/0000-0002-9374-9699"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wang","raw_affiliation_strings":["AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-9374-9699","affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research, Haidian District, Beijing 100094, P. R. China","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027131702"],"corresponding_institution_ids":["https://openalex.org/I4210156165"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09932593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","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":0.9991000294685364,"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":0.9991000294685364,"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":0.9943000078201294,"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":0.9937999844551086,"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":0.7899628281593323},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7696256637573242},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.737289547920227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7336721420288086},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5840346217155457},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4264529347419739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35356903076171875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899628281593323},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7696256637573242},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.737289547920227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7336721420288086},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5840346217155457},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4264529347419739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35356903076171875},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s271755452350011x","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s271755452350011x","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2518172956","https://openalex.org/W2612690371","https://openalex.org/W2897353073","https://openalex.org/W2937579788","https://openalex.org/W2964243274","https://openalex.org/W2990138404","https://openalex.org/W3099078140","https://openalex.org/W3135774711","https://openalex.org/W3144417991","https://openalex.org/W3154451338","https://openalex.org/W3162427973","https://openalex.org/W4224928197","https://openalex.org/W4225322394","https://openalex.org/W4319780299"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W2406877384","https://openalex.org/W2595839522"],"abstract_inverted_index":{"With":[0],"the":[1,27,40,46,98,122,126],"development":[2],"of":[3,63],"deep":[4],"learning,":[5],"nonparallel":[6,82],"voice":[7,84],"conversion":[8,85],"(VC)":[9],"has":[10],"achieved":[11],"a":[12,81,113],"significant":[13],"progress":[14],"recently.":[15],"Automatic":[16],"speech":[17,130],"recognition":[18],"(ASR)":[19],"and":[20,92,134],"text-to-speech":[21],"(TTS)":[22],"for":[23],"leveraging":[24],"knowledge":[25],"are":[26,49,52,69,110],"two":[28,41],"mainstream":[29],"methods":[30,48],"in":[31,45,56,97,129],"VC":[32],"research.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"demonstrate":[38],"that":[39,121],"bottleneck":[42],"features":[43],"(BNFs)":[44],"above":[47],"complementary.":[50],"ASR-BNFs":[51,91],"more":[53],"robust":[54],"especially":[55],"any-to-many":[57,83],"tasks,":[58],"but":[59,77],"suffer":[60],"from":[61],"leakage":[62],"source":[64],"speaker\u2019s":[65,74],"timbre":[66,75,132],"information;":[67],"TTS-BNFs":[68],"less":[70],"likely":[71],"to":[72,137],"reveal":[73],"information,":[76],"lack":[78],"robustness.":[79],"Therefore,":[80],"model":[86,100,124],"is":[87,119],"proposed":[88,99,123],"by":[89],"combining":[90],"TTS-BNFs.":[93],"The":[94],"whole":[95],"modules":[96],"can":[101],"be":[102],"trained":[103],"jointly":[104],"without":[105],"any":[106],"pre-trained":[107],"models.":[108,139],"Experiments":[109],"conducted":[111],"on":[112],"private":[114],"multi-speaker":[115],"TTS":[116],"dataset.":[117],"It":[118],"demonstrated":[120],"achieves":[125],"best":[127],"balance":[128],"quality,":[131],"similarity":[133],"robustness":[135],"compared":[136],"baseline":[138]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}