{"id":"https://openalex.org/W4372263461","doi":"https://doi.org/10.1109/icassp49357.2023.10097264","title":"Performance Comparison of TTS Models for Brazilian Portuguese to Establish a Baseline","display_name":"Performance Comparison of TTS Models for Brazilian Portuguese to Establish a Baseline","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263461","doi":"https://doi.org/10.1109/icassp49357.2023.10097264"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097264","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":"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":"https://openalex.org/A5064454384","display_name":"Wilmer Lobato","orcid":"https://orcid.org/0000-0002-3929-1218"},"institutions":[{"id":"https://openalex.org/I4210151383","display_name":"Alana's Foundation","ror":"https://ror.org/05aaaax52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151383"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wilmer Lobato","raw_affiliation_strings":["Alana AI Research,Brazil","Alana AI Research, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alana AI Research,Brazil","institution_ids":["https://openalex.org/I4210151383"]},{"raw_affiliation_string":"Alana AI Research, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033050828","display_name":"Felipe Farias","orcid":"https://orcid.org/0000-0001-7411-5562"},"institutions":[{"id":"https://openalex.org/I4210151383","display_name":"Alana's Foundation","ror":"https://ror.org/05aaaax52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151383"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felipe Farias","raw_affiliation_strings":["Alana AI Research,Brazil","Alana AI Research, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alana AI Research,Brazil","institution_ids":["https://openalex.org/I4210151383"]},{"raw_affiliation_string":"Alana AI Research, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081867747","display_name":"William Alberto Cruz Casta\u00f1eda","orcid":"https://orcid.org/0000-0002-9803-1387"},"institutions":[{"id":"https://openalex.org/I4210151383","display_name":"Alana's Foundation","ror":"https://ror.org/05aaaax52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151383"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Cruz","raw_affiliation_strings":["Alana AI Research,Brazil","Alana AI Research, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alana AI Research,Brazil","institution_ids":["https://openalex.org/I4210151383"]},{"raw_affiliation_string":"Alana AI Research, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058612982","display_name":"Marcellus Amadeus","orcid":"https://orcid.org/0009-0002-7777-2562"},"institutions":[{"id":"https://openalex.org/I4210151383","display_name":"Alana's Foundation","ror":"https://ror.org/05aaaax52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151383"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcellus Amadeus","raw_affiliation_strings":["Alana AI Research,Brazil","Alana AI Research, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alana AI Research,Brazil","institution_ids":["https://openalex.org/I4210151383"]},{"raw_affiliation_string":"Alana AI Research, Brazil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69427846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9423328638076782},{"id":"https://openalex.org/keywords/brazilian-portuguese","display_name":"Brazilian Portuguese","score":0.757533073425293},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.7374284267425537},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7253111004829407},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7006394267082214},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6627612709999084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6268398761749268},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.564858078956604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4851168394088745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36554959416389465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3522224426269531},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17972731590270996},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14545121788978577},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.059777677059173584}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9423328638076782},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.757533073425293},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.7374284267425537},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7253111004829407},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7006394267082214},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6627612709999084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6268398761749268},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.564858078956604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4851168394088745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36554959416389465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3522224426269531},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17972731590270996},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14545121788978577},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.059777677059173584},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097264","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W1901129140","https://openalex.org/W2120847449","https://openalex.org/W2135234058","https://openalex.org/W2319891691","https://openalex.org/W2519091744","https://openalex.org/W2759491482","https://openalex.org/W2767052532","https://openalex.org/W2964243274","https://openalex.org/W3092028330","https://openalex.org/W3169905056","https://openalex.org/W3172148458","https://openalex.org/W3174758275","https://openalex.org/W3197287223","https://openalex.org/W4226396073","https://openalex.org/W6639824700","https://openalex.org/W6783867762","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6796730497"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W4400309480","https://openalex.org/W2549308614","https://openalex.org/W2081919107"],"abstract_inverted_index":{"This":[0],"paper":[1],"compares":[2],"the":[3,43,71,79],"performance":[4,96],"of":[5,91,97],"three":[6],"text-to-speech":[7],"(TTS)":[8],"models":[9,27,54],"released":[10],"from":[11],"June":[12],"2021":[13],"to":[14,19,41,95],"January":[15],"2022":[16],"in":[17],"order":[18],"establish":[20],"a":[21],"baseline":[22],"for":[23,32],"Brazilian":[24,33],"Portuguese.":[25,34],"Those":[26],"were":[28],"trained":[29],"using":[30,56],"dataset":[31,40],"The":[35],"experimental":[36],"setup":[37],"considers":[38],"tts-portuguese":[39],"fine-tune":[42],"following":[44],"TTS":[45],"models:":[46],"VITS":[47],"end-to-end":[48],"model;":[49],"glowtts":[50],"and":[51,65,73],"gradtts":[52],"acoustic":[53],"both":[55],"hifigan":[57],"vocoder.":[58],"Performance":[59],"metrics":[60],"are":[61,75],"arranged":[62],"into":[63],"objective":[64],"subjective":[66,69],"metrics.":[67],"As":[68],"metrics,":[70],"naturalness":[72,90],"intelligibility":[74],"measured":[76],"based":[77],"on":[78],"mean":[80],"opinion":[81],"score":[82],"(MOS).":[83],"Results":[84],"shows":[85],"that":[86],"gradtts+hifigan":[87],"model":[88],"achieved":[89],"4.07":[92],"MOS,":[93],"close":[94],"current":[98],"commercial":[99],"models.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
