{"id":"https://openalex.org/W4372260171","doi":"https://doi.org/10.1109/icassp49357.2023.10096279","title":"High-Acoustic Fidelity Text To Speech Synthesis With Fine-Grained Control Of Speech Attributes","display_name":"High-Acoustic Fidelity Text To Speech Synthesis With Fine-Grained Control Of Speech Attributes","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260171","doi":"https://doi.org/10.1109/icassp49357.2023.10096279"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096279","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5113576287","display_name":"Rafael Valle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafael Valle","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068457267","display_name":"Jo\u00e3o Felipe Santos","orcid":"https://orcid.org/0000-0003-3934-3943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Felipe Santos","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016107863","display_name":"Kevin J. Shih","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin J. Shih","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058296176","display_name":"Rohan Badlani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Badlani","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9994000196456909,"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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7301677465438843},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7238248586654663},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7198709845542908},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.7046813368797302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6767826080322266},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6533971428871155},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5998024940490723},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5243344902992249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3529127538204193},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21822389960289001},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07928666472434998}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7301677465438843},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7238248586654663},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7198709845542908},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.7046813368797302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6767826080322266},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6533971428871155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5998024940490723},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5243344902992249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3529127538204193},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21822389960289001},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07928666472434998},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096279","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W198589515","https://openalex.org/W2118774185","https://openalex.org/W2130086727","https://openalex.org/W2760103357","https://openalex.org/W2795109282","https://openalex.org/W2946200149","https://openalex.org/W2963300588","https://openalex.org/W3015645837","https://openalex.org/W3025528898","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3150572638","https://openalex.org/W3169905056","https://openalex.org/W3194000401","https://openalex.org/W3196001064","https://openalex.org/W4221149906","https://openalex.org/W4226332109","https://openalex.org/W4295731579","https://openalex.org/W4297798428","https://openalex.org/W6714644935","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778083308","https://openalex.org/W6778823374","https://openalex.org/W6796464841","https://openalex.org/W6800393981","https://openalex.org/W6810435298","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"Recently":[0],"developed":[1],"neural-based":[2],"TTS":[3],"models":[4,73],"have":[5,27],"focused":[6],"on":[7,93],"robustness":[8],"and":[9,20],"finer":[10],"control":[11,31,62,68],"over":[12,32],"acoustic":[13,52],"features":[14],"such":[15],"as":[16,74],"phoneme":[17],"duration,":[18],"energy,":[19],"F<inf":[21],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[22,79],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>,":[23],"allowing":[24],"users":[25],"to":[26,61,106],"some":[28],"degree":[29],"of":[30,35,55,112],"the":[33,36,56,67,91,107],"prosody":[34],"generated":[37],"speech.":[38],"We":[39],"propose":[40],"a":[41],"model":[42,86],"with":[43],"fine":[44],"grained":[45],"attribute":[46],"control,":[47],"which":[48,58],"also":[49],"has":[50],"better":[51],"fidelity":[53],"(attributes":[54],"output":[57],"we":[59],"want":[60],"do":[63],"not":[64,88],"deviate":[65],"from":[66],"signals)":[69],"than":[70,110],"previously":[71],"proposed":[72,85],"shown":[75],"in":[76],"our":[77,84],"experiments<sup":[78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[80],"Unlike":[81],"other":[82,113],"models,":[83],"does":[87],"require":[89],"fine-tuning":[90],"vocoder":[92],"its":[94],"outputs,":[95],"indicating":[96],"that":[97,103,111],"it":[98],"generates":[99],"higher":[100],"quality":[101],"mel-spectrograms":[102],"are":[104],"closer":[105],"ground-truth":[108],"distribution":[109],"models.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}