{"id":"https://openalex.org/W4416800054","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249417","title":"Investigation of the Effectiveness of Converted Speech Auditory Feedback in Low-Latency Real-Time Voice Conversion","display_name":"Investigation of the Effectiveness of Converted Speech Auditory Feedback in Low-Latency Real-Time Voice Conversion","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800054","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249417"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Kiseki Niwa","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiseki Niwa","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088792710","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-5047-4165"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17314584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"753","last_page":"758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5008000135421753,"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":0.5008000135421753,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.12939999997615814,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.07509999722242355,"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/auditory-feedback","display_name":"Auditory feedback","score":0.8101999759674072},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7498000264167786},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6141999959945679},{"id":"https://openalex.org/keywords/subconscious","display_name":"Subconscious","score":0.3896999955177307},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3727000057697296},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.3684999942779541},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.36329999566078186},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3398999869823456},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.3361999988555908}],"concepts":[{"id":"https://openalex.org/C2779864741","wikidata":"https://www.wikidata.org/wiki/Q4820027","display_name":"Auditory feedback","level":2,"score":0.8101999759674072},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7498000264167786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.722000002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6277999877929688},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C96851999","wikidata":"https://www.wikidata.org/wiki/Q848369","display_name":"Subconscious","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3398999869823456},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33070001006126404},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.266400009393692}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2025700375","https://openalex.org/W2085439636","https://openalex.org/W2406654659","https://openalex.org/W2532494225","https://openalex.org/W2897353073","https://openalex.org/W2946555236","https://openalex.org/W2972544500","https://openalex.org/W2973216307","https://openalex.org/W2996414377","https://openalex.org/W3002433751","https://openalex.org/W3024869864","https://openalex.org/W3162517041","https://openalex.org/W3170751106","https://openalex.org/W3193566630","https://openalex.org/W3197763626","https://openalex.org/W3204974011","https://openalex.org/W3207300132","https://openalex.org/W4225956675","https://openalex.org/W4226039367","https://openalex.org/W4372266901"],"related_works":[],"abstract_inverted_index":{"Low-latency":[0],"real-time":[1,92,102],"voice":[2,7],"conversion":[3],"(VC)":[4],"technique":[5,23],"transforming":[6],"characteristics":[8],"while":[9,165],"preserving":[10],"linguistic":[11],"content":[12],"allows":[13],"users":[14,151],"to":[15,33,38,42,67,159],"freely":[16],"speak":[17],"with":[18,95,113],"desired":[19],"target":[20],"voices.":[21],"This":[22],"can":[24],"instantaneously":[25],"present":[26],"auditory":[27,57,72,85,133],"feedback":[28,58,73,86,104,116,134],"of":[29,82],"the":[30,34,43,47,55,80,83,131,162],"converted":[31,56,84,109,122,132],"speech":[32,110,123,141],"users,":[35],"enabling":[36],"them":[37],"adapt":[39],"their":[40,121,154],"vocalization":[41],"VC":[44,93,163],"system.":[45],"On":[46],"other":[48],"hand,":[49],"it":[50],"is":[51],"also":[52],"possible":[53],"that":[54,130,150],"causes":[59],"any":[60],"adverse":[61,173],"effects,":[62],"such":[63],"as":[64],"stuttering,":[65],"similar":[66],"those":[68],"caused":[69],"by":[70],"delayed":[71],"(DAF).":[74],"In":[75],"this":[76],"study,":[77],"we":[78],"investigate":[79],"effectiveness":[81],"using":[87],"eight":[88],"participants":[89,107,119],"in":[90,139],"a":[91],"system":[94],"77":[96],"ms":[97],"end-to-end":[98],"latency.":[99],"We":[100],"compare":[101],"(RT)":[103],"conditions":[105,117],"where":[106,118],"hear":[108,120],"during":[111],"utterance":[112,125],"recording":[114],"(Rec)":[115],"after":[124],"completion.":[126],"Experimental":[127],"results":[128],"demonstrate":[129],"yields":[135],"statistically":[136],"significant":[137],"improvements":[138],"both":[140],"naturalness":[142],"(UT-MOS)":[143],"and":[144],"speaker":[145],"similarity.":[146],"Objective":[147],"analysis":[148,170],"reveals":[149],"subconsciously":[152],"increase":[153],"fundamental":[155],"frequency":[156],"(F0)":[157],"variability":[158],"better":[160],"match":[161],"model,":[164],"Character":[166],"Error":[167],"Rate":[168],"(CER)":[169],"confirms":[171],"no":[172],"DAF-like":[174],"effects.":[175]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}