{"id":"https://openalex.org/W4319780299","doi":"https://doi.org/10.1109/iscslp57327.2022.10038075","title":"Mix-Guided VC: Any-to-many Voice Conversion by Combining ASR and TTS Bottleneck Features","display_name":"Mix-Guided VC: Any-to-many Voice Conversion by Combining ASR and TTS Bottleneck Features","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319780299","doi":"https://doi.org/10.1109/iscslp57327.2022.10038075"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038075","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5112880677","display_name":"Zeqing Zhao","orcid":null},"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,Beijing,China","AI Lab, Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"AI Lab, Lenovo Research, Beijing, 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,Beijing,China","AI Lab, Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"AI Lab, Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705677","display_name":"Yan Jia","orcid":"https://orcid.org/0000-0003-2857-0518"},"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,Beijing,China","AI Lab, Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"AI Lab, Lenovo Research, Beijing, 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,Beijing,China","AI Lab, Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"AI Lab, Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101475284","display_name":"Lin Yang","orcid":"https://orcid.org/0000-0002-6956-8177"},"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,Beijing,China","AI Lab, Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"AI Lab, Lenovo Research, Beijing, 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,Beijing,China","AI Lab, Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]},{"raw_affiliation_string":"AI Lab, Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112880677"],"corresponding_institution_ids":["https://openalex.org/I4210156165"],"apc_list":null,"apc_paid":null,"fwci":0.3137,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5469338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"100"},"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":0.9991000294685364,"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":0.9990000128746033,"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":0.8150711059570312},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8073222637176514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7548302412033081},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6755284070968628},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.657606303691864},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4873219430446625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3500593900680542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150711059570312},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8073222637176514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7548302412033081},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6755284070968628},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.657606303691864},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4873219430446625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3500593900680542},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/iscslp57327.2022.10038075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038075","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2187089797","https://openalex.org/W2518172956","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2889048668","https://openalex.org/W2897353073","https://openalex.org/W2908510526","https://openalex.org/W2946200149","https://openalex.org/W2964243274","https://openalex.org/W2972659941","https://openalex.org/W3024869864","https://openalex.org/W3092028330","https://openalex.org/W3095936335","https://openalex.org/W3097777922","https://openalex.org/W3099078140","https://openalex.org/W3135774711","https://openalex.org/W3143523927","https://openalex.org/W3144417991","https://openalex.org/W3154451338","https://openalex.org/W3162427973","https://openalex.org/W3196667132","https://openalex.org/W3198533616","https://openalex.org/W4224928197","https://openalex.org/W4225322394","https://openalex.org/W4245692952","https://openalex.org/W6754473786","https://openalex.org/W6757817989","https://openalex.org/W6762533536","https://openalex.org/W6763832098","https://openalex.org/W6783867762"],"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":{"Due":[0],"to":[1],"the":[2,90,94,109,113],"difficulty":[3],"of":[4],"obtaining":[5],"parallel":[6],"data,":[7],"there":[8],"are":[9,60,63,79],"many":[10],"works":[11],"focus":[12],"on":[13],"non-parallel":[14,44],"voice":[15,46],"conversion(VC)":[16],"recently.":[17],"Bottleneck":[18],"features(BNFs)":[19],"from":[20,72],"automatic":[21],"speech":[22,98],"recognition(ASR)":[23],"and":[24,52,58,102,120],"text-to-speech(TTS)":[25],"models":[26],"play":[27],"an":[28],"important":[29],"role":[30],"in":[31,67,97,112],"feature":[32],"disentangling":[33],"for":[34],"VC.":[35],"In":[36],"this":[37],"work,":[38],"we":[39],"propose":[40],"Mix-Guided":[41],"VC,":[42],"a":[43],"any-to-many":[45,68],"conversion":[47],"model":[48,92,115],"by":[49],"combining":[50],"ASR-BNFs":[51,57,62],"TTS-BNFs.":[53],"We":[54],"demonstrate":[55],"that":[56,89],"TTS-BNFs":[59,78],"complementary.":[61],"more":[64,122],"robust":[65],"especially":[66],"tasks,":[69],"but":[70,84],"suffer":[71],"leaking":[73],"source":[74],"speaker\u2019s":[75],"timbre":[76,100],"information;":[77],"closely":[80],"correlated":[81],"with":[82,105],"text,":[83],"lack":[85],"robustness.":[86],"Experiments":[87],"show":[88],"proposed":[91,114],"achieves":[93],"best":[95],"balance":[96],"quality,":[99],"similarity":[101],"robustness":[103],"compares":[104],"baseline":[106],"models.":[107],"Furthermore,":[108],"whole":[110],"modules":[111],"can":[116],"be":[117],"trained":[118],"jointly":[119],"no":[121],"pre-training":[123],"data":[124],"is":[125],"needed.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}