{"id":"https://openalex.org/W4391021405","doi":"https://doi.org/10.1109/asru57964.2023.10389707","title":"Improving Severity Preservation of Healthy-to-Pathological Voice Conversion With Global Style Tokens","display_name":"Improving Severity Preservation of Healthy-to-Pathological Voice Conversion With Global Style Tokens","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021405","doi":"https://doi.org/10.1109/asru57964.2023.10389707"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5019343311","display_name":"Bence Mark Halpern","orcid":"https://orcid.org/0000-0001-8787-359X"},"institutions":[{"id":"https://openalex.org/I2898336195","display_name":"The Netherlands Cancer Institute","ror":"https://ror.org/03xqtf034","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2898336195"]},{"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","NL"],"is_corresponding":false,"raw_author_name":"Bence Mark Halpern","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan","Netherlands Cancer Institute, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Netherlands Cancer Institute, The Netherlands","institution_ids":["https://openalex.org/I2898336195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"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":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013549148","display_name":"Lester Phillip Violeta","orcid":"https://orcid.org/0000-0001-9118-2994"},"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":"Lester Phillip Violeta","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043585751","display_name":"R.J.J.H. van Son","orcid":"https://orcid.org/0000-0001-6321-7635"},"institutions":[{"id":"https://openalex.org/I2898336195","display_name":"The Netherlands Cancer Institute","ror":"https://ror.org/03xqtf034","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2898336195"]},{"id":"https://openalex.org/I4210111138","display_name":"Oncode Institute","ror":"https://ror.org/01n92vv28","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210111138"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"R.J.J.H. van Son","raw_affiliation_strings":["Netherlands Cancer Institute,The Netherlands","Netherlands Cancer Institute, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netherlands Cancer Institute,The Netherlands","institution_ids":["https://openalex.org/I4210111138"]},{"raw_affiliation_string":"Netherlands Cancer Institute, The Netherlands","institution_ids":["https://openalex.org/I2898336195"]}]},{"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","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9891999959945679,"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/style","display_name":"Style (visual arts)","score":0.6493406295776367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.619033932685852},{"id":"https://openalex.org/keywords/pathological","display_name":"Pathological","score":0.4679003953933716},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4180909991264343},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.18306106328964233},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.0918218195438385}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6493406295776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.619033932685852},{"id":"https://openalex.org/C207886595","wikidata":"https://www.wikidata.org/wiki/Q1456138","display_name":"Pathological","level":2,"score":0.4679003953933716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4180909991264343},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.18306106328964233},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0918218195438385},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W2046299281","https://openalex.org/W2141869696","https://openalex.org/W2149768999","https://openalex.org/W2752796333","https://openalex.org/W2936417594","https://openalex.org/W2952218014","https://openalex.org/W2963799213","https://openalex.org/W2972818416","https://openalex.org/W2973053330","https://openalex.org/W3007328579","https://openalex.org/W3010916717","https://openalex.org/W3015645837","https://openalex.org/W3030437843","https://openalex.org/W3082130377","https://openalex.org/W3092028330","https://openalex.org/W3094635600","https://openalex.org/W3096567388","https://openalex.org/W3099330747","https://openalex.org/W3162879338","https://openalex.org/W3163725792","https://openalex.org/W3163793923","https://openalex.org/W3167533889","https://openalex.org/W3195423934","https://openalex.org/W3207300132","https://openalex.org/W3207399576","https://openalex.org/W4200300291","https://openalex.org/W4200429098","https://openalex.org/W4226418302","https://openalex.org/W4385822966","https://openalex.org/W4388903318","https://openalex.org/W6750489868","https://openalex.org/W6771467084","https://openalex.org/W6783867762","https://openalex.org/W6796720528","https://openalex.org/W6811405417"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2365243064","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"In":[0],"healthy-to-pathological":[1],"voice":[2,42],"conversion":[3],"(H2P-VC),":[4],"healthy":[5,81],"speech":[6,27],"is":[7,28,43,125,136],"converted":[8,44],"into":[9],"pathological":[10,79],"while":[11,45,107],"preserving":[12,46],"the":[13,32,37,41,47,50,84,99,104],"identity.":[14],"The":[15],"paper":[16],"improves":[17],"on":[18,132],"previous":[19],"two-stage":[20],"approach":[21],"to":[22,56],"H2":[23],"P-VC":[24],"where":[25],"(1)":[26],"created":[29],"first":[30],"with":[31,83],"appropriate":[33],"severity,":[34],"(2)":[35,57],"then":[36],"speaker":[38,123],"identity":[39,86],"of":[40,49,78,103],"severity":[48,102,133],"voice.":[51,111],"Specifically,":[52],"we":[53,69],"propose":[54],"improvements":[55],"by":[58,94],"using":[59],"phonetic":[60],"posteriorgrams":[61],"(PPG)":[62],"and":[63,80],"global":[64],"style":[65],"tokens":[66],"(GST).":[67],"Furthermore,":[68],"present":[70],"a":[71],"new":[72],"dataset":[73],"that":[74,98,115],"contains":[75],"parallel":[76],"recordings":[77],"speakers":[82,130],"same":[85],"which":[87],"allows":[88],"more":[89],"precise":[90],"evaluation.":[91],"Listening":[92],"tests":[93],"expert":[95],"listeners":[96],"show":[97,114],"framework":[100],"preserves":[101],"source":[105,129],"sample,":[106],"modelling":[108],"target":[109],"speaker\u2019s":[110],"We":[112],"also":[113],"(a)":[116],"pathology":[117],"impacts":[118],"x-vectors":[119],"but":[120],"not":[121],"all":[122],"information":[124],"lost,":[126],"(b)":[127],"choosing":[128],"based":[131],"labels":[134],"alone":[135],"insufficient.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}