{"id":"https://openalex.org/W4210774711","doi":"https://doi.org/10.1109/asru51503.2021.9688010","title":"On Prosody Modeling for ASR+TTS Based Voice Conversion","display_name":"On Prosody Modeling for ASR+TTS Based Voice Conversion","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210774711","doi":"https://doi.org/10.1109/asru51503.2021.9688010"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688010","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 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/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/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"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 Hayashi","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/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinjian Li","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"642","last_page":"649"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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":0.9921000003814697,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9145814180374146},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8812566995620728},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7630658745765686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7073498368263245},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6032701134681702},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6006960272789001},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5537423491477966},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4998641014099121},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45366838574409485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41254308819770813}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9145814180374146},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8812566995620728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630658745765686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7073498368263245},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6032701134681702},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6006960272789001},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5537423491477966},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4998641014099121},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45366838574409485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41254308819770813},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688010","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":52,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2120605154","https://openalex.org/W2156142001","https://openalex.org/W2187089797","https://openalex.org/W2471520273","https://openalex.org/W2518172956","https://openalex.org/W2766219058","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2885800352","https://openalex.org/W2888867175","https://openalex.org/W2890964092","https://openalex.org/W2892009249","https://openalex.org/W2897353073","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2933138175","https://openalex.org/W2948238043","https://openalex.org/W2962780374","https://openalex.org/W2964138190","https://openalex.org/W2972359262","https://openalex.org/W2972389417","https://openalex.org/W2972802841","https://openalex.org/W2973158936","https://openalex.org/W2979476256","https://openalex.org/W3015338123","https://openalex.org/W3015853838","https://openalex.org/W3016160783","https://openalex.org/W3025844872","https://openalex.org/W3081565196","https://openalex.org/W3083776549","https://openalex.org/W3091890228","https://openalex.org/W3092368332","https://openalex.org/W3094635600","https://openalex.org/W3096567388","https://openalex.org/W3099078140","https://openalex.org/W3118753411","https://openalex.org/W3134921434","https://openalex.org/W3161627112","https://openalex.org/W3161695192","https://openalex.org/W4244543785","https://openalex.org/W4247587863","https://openalex.org/W4289383906","https://openalex.org/W4295731579","https://openalex.org/W4385245566","https://openalex.org/W4390912423","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6763316926","https://openalex.org/W6769196770","https://openalex.org/W6840412704"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W3100825170","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W3149582125","https://openalex.org/W2077992636"],"abstract_inverted_index":{"In":[0],"voice":[1,12],"conversion":[2,13,74],"(VC),":[3],"an":[4,21,67],"approach":[5],"showing":[6],"promising":[7],"results":[8,139],"in":[9,70,101,114,145],"the":[10,29,33,50,61,85,111,130,141],"latest":[11],"challenge":[14],"(VCC)":[15],"2020":[16],"is":[17],"to":[18,27,48,57,106,119],"first":[19],"use":[20],"automatic":[22],"speech":[23,31,71],"recognition":[24],"(ASR)":[25],"model":[26],"transcribe":[28],"source":[30,86],"into":[32],"underlying":[34],"linguistic":[35,112,136],"contents;":[36],"these":[37],"are":[38],"then":[39],"used":[40],"as":[41,58,120],"input":[42],"by":[43],"a":[44,54,90,115],"text-to-speech":[45],"(TTS)":[46],"system":[47],"generate":[49],"converted":[51],"speech.":[52],"Such":[53],"paradigm,":[55],"referred":[56,118],"ASR+TTS,":[59],"overlooks":[60],"modeling":[62],"of":[63,143],"prosody,":[64],"which":[65],"plays":[66],"important":[68],"role":[69],"naturalness":[72],"and":[73,95,133,148],"similarity.":[75],"Although":[76],"some":[77],"researchers":[78],"have":[79],"considered":[80],"transferring":[81],"prosodic":[82],"clues":[83],"from":[84,110],"speech,":[87],"there":[88],"arises":[89],"speaker":[91],"mismatch":[92],"during":[93],"training":[94],"conversion.":[96],"To":[97],"address":[98],"this":[99,102],"issue,":[100],"work,":[103],"we":[104],"propose":[105],"directly":[107],"predict":[108],"prosody":[109],"representation":[113],"target-speaker-dependent":[116],"manner,":[117],"target":[121],"text":[122],"prediction":[123],"(TTP).":[124],"We":[125],"evaluate":[126],"both":[127,146],"methods":[128],"on":[129],"VCC2020":[131],"benchmark":[132],"consider":[134],"different":[135],"representations.":[137],"The":[138],"demonstrate":[140],"effectiveness":[142],"TTP":[144],"objective":[147],"subjective":[149],"evaluations.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}