{"id":"https://openalex.org/W7225332840","doi":"https://doi.org/10.1146/annurev-linguistics-033125-112552","title":"Voice Conversion, Voice Morphing, and Speech Style Modification","display_name":"Voice Conversion, Voice Morphing, and Speech Style Modification","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225332840","doi":"https://doi.org/10.1146/annurev-linguistics-033125-112552"},"language":"en","primary_location":{"id":"doi:10.1146/annurev-linguistics-033125-112552","doi":"https://doi.org/10.1146/annurev-linguistics-033125-112552","is_oa":false,"landing_page_url":"https://doi.org/10.1146/annurev-linguistics-033125-112552","pdf_url":null,"source":{"id":"https://openalex.org/S4210191548","display_name":"Annual Review of Linguistics","issn_l":"2333-9683","issn":["2333-9683","2333-9691"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doyens","erih-plus","jufo-1","norway-1","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320373","host_organization_name":"Annual Reviews","host_organization_lineage":["https://openalex.org/P4310320373"],"host_organization_lineage_names":["Annual Reviews"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual Review of Linguistics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893","observed_orcids":["https://orcid.org/0000-0002-5631-2893"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["1Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, Illinois, USA; email:\u00a0jhasegaw@illinois.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, Illinois, USA; email:\u00a0jhasegaw@illinois.edu","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072749858","display_name":"Hideki Kawahara","orcid":"https://orcid.org/0000-0001-9360-5700","observed_orcids":["https://orcid.org/0000-0001-9360-5700"]},"institutions":[{"id":"https://openalex.org/I75198481","display_name":"Wakayama University","ror":"https://ror.org/05wr49d48","country_code":"JP","type":"education","lineage":["https://openalex.org/I75198481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Kawahara","raw_affiliation_strings":["2Center for Innovative Research and Liaison, Wakayama University, Wakayama, Japan; email:\u00a0kawahara@wakayama-u.ac.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2Center for Innovative Research and Liaison, Wakayama University, Wakayama, Japan; email:\u00a0kawahara@wakayama-u.ac.jp","institution_ids":["https://openalex.org/I75198481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9907000064849854,"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":0.9907000064849854,"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":0.007300000172108412,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.9929999709129333},{"id":"https://openalex.org/keywords/voice-morphing","display_name":"voice morphing","score":0.9480000138282776},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.5419999957084656},{"id":"https://openalex.org/keywords/speech-perception","display_name":"speech perception","score":0.7789999842643738},{"id":"https://openalex.org/keywords/voice-over","display_name":"voice-over","score":0.9120000004768372},{"id":"https://openalex.org/keywords/emotion-in-speech","display_name":"emotion in speech","score":0.6660000085830688},{"id":"https://openalex.org/keywords/foreign-accent","display_name":"foreign accent","score":0.9679999947547913},{"id":"https://openalex.org/keywords/speaker-anonymization","display_name":"speaker anonymization","score":0.8240000009536743},{"id":"https://openalex.org/keywords/speech-recognition-training","display_name":"speech recognition training","score":0.8109999895095825}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7400000095367432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6851000189781189},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3885999917984009},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30869999527931213},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2554999887943268},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1146/annurev-linguistics-033125-112552","doi":"https://doi.org/10.1146/annurev-linguistics-033125-112552","is_oa":false,"landing_page_url":"https://doi.org/10.1146/annurev-linguistics-033125-112552","pdf_url":null,"source":{"id":"https://openalex.org/S4210191548","display_name":"Annual Review of Linguistics","issn_l":"2333-9683","issn":["2333-9683","2333-9691"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doyens","erih-plus","jufo-1","norway-1","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320373","host_organization_name":"Annual Reviews","host_organization_lineage":["https://openalex.org/P4310320373"],"host_organization_lineage_names":["Annual Reviews"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual Review of Linguistics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1947917047","https://openalex.org/W4236375010","https://openalex.org/W4249937474","https://openalex.org/W162989454","https://openalex.org/W2124331435","https://openalex.org/W149567537","https://openalex.org/W2122627441","https://openalex.org/W111057040","https://openalex.org/W4383218451","https://openalex.org/W2113998251"],"abstract_inverted_index":{"A":[0],"speech":[1,40,60,90],"sample":[2],"can":[3],"be":[4],"morphed":[5],"from":[6],"one":[7],"voice":[8],"to":[9,83],"another":[10],"by":[11],"computing":[12],"a":[13,39],"sufficiently":[14],"detailed":[15],"time-frequency":[16,50],"parameterization":[17,32],"of":[18,49,59,73,89],"the":[19,31,44,56,87],"signal,":[20],"optionally":[21],"decomposing":[22],"it":[23],"into":[24],"speaker-dependent":[25],"and":[26,36,62,69,77,92],"speaker-independent":[27],"signal":[28,34,41],"components,":[29,35],"editing":[30],"or":[33],"then":[37],"generating":[38],"based":[42],"on":[43],"edited":[45],"parameterization.":[46],"Fine-grained":[47],"control":[48,72],"parameters":[51],"has":[52],"found":[53],"applications":[54,65],"in":[55,63],"scientific":[57],"study":[58],"perception":[61],"artistic":[64],"such":[66],"as":[67],"voiceover":[68],"music.":[70],"Coarse-grained":[71],"speaker":[74,93],"identity,":[75],"emotion,":[76],"second-language":[78],"accent":[79],"have":[80],"been":[81],"applied":[82],"various":[84],"tasks,":[85],"including":[86],"training":[88],"recognizers":[91],"anonymization.":[94]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-11-06T00:00:00"}