TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese
Speech provides a natural way for human-computer interaction. In particular, speech synthesis systems are popular in different applications, such as personal assistants, GPS applications, screen readers and accessibility tools. However, not all languages are on the same level when in terms of resour...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2022-01 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Casanova, Edresson Arnaldo Candido Junior Shulby, Christopher Santos de Oliveira, Frederico Teixeira, João Paulo Moacir Antonelli Ponti Aluisio, Sandra Maria |
| description | Speech provides a natural way for human-computer interaction. In particular, speech synthesis systems are popular in different applications, such as personal assistants, GPS applications, screen readers and accessibility tools. However, not all languages are on the same level when in terms of resources and systems for speech synthesis. This work consists of creating publicly available resources for Brazilian Portuguese in the form of a novel dataset along with deep learning models for end-to-end speech synthesis. Such dataset has 10.5 hours from a single speaker, from which a Tacotron 2 model with the RTISI-LA vocoder presented the best performance, achieving a 4.03 MOS value. The obtained results are comparable to related works covering English language and the state-of-the-art in Portuguese. |
| doi_str_mv | 10.48550/arxiv.2005.05144 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2005_05144</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2401516225</sourcerecordid><originalsourceid>FETCH-LOGICAL-a525-23655d3ace69157e6634326766062e20f75f6f40d0f5a8386746cb6aa3ee7f943</originalsourceid><addsrcrecordid>eNpFj01Lw0AQhhdBsNT-AE8ueE6czO5MUm8a_IKAgrmHNd21KTWJu4lYf72xFTy97-Gd4XmEOEsg1hkRXBr_1XzGCEAxUKL1kZihUkmUacQTsQhhAwDIKRKpmSjK8iV67vwwvo02WJl3vh_DlTSy3jfpOi9Db229lmHXDmsbmiCbVt54891sG9PK_-tTcezMNtjFX85FeXdb5g9R8XT_mF8XkSGkCBUTrZSpLS8TSi2z0moCYgZGi-BScuw0rMCRyVTGqeb6lY1R1qZuqdVcnB_e7lWr3jfvxu-qX-VqrzwtLg6L3ncfE9lQbbrRtxNThRoSShiR1A9Dd1g2</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2401516225</pqid></control><display><type>article</type><title>TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Casanova, Edresson ; Arnaldo Candido Junior ; Shulby, Christopher ; Santos de Oliveira, Frederico ; Teixeira, João Paulo ; Moacir Antonelli Ponti ; Aluisio, Sandra Maria</creator><creatorcontrib>Casanova, Edresson ; Arnaldo Candido Junior ; Shulby, Christopher ; Santos de Oliveira, Frederico ; Teixeira, João Paulo ; Moacir Antonelli Ponti ; Aluisio, Sandra Maria</creatorcontrib><description>Speech provides a natural way for human-computer interaction. In particular, speech synthesis systems are popular in different applications, such as personal assistants, GPS applications, screen readers and accessibility tools. However, not all languages are on the same level when in terms of resources and systems for speech synthesis. This work consists of creating publicly available resources for Brazilian Portuguese in the form of a novel dataset along with deep learning models for end-to-end speech synthesis. Such dataset has 10.5 hours from a single speaker, from which a Tacotron 2 model with the RTISI-LA vocoder presented the best performance, achieving a 4.03 MOS value. The obtained results are comparable to related works covering English language and the state-of-the-art in Portuguese.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2005.05144</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Computation and Language ; Computer Science - Learning ; Datasets ; Machine learning ; Noise reduction ; Phonetics ; Speech recognition ; Vocoders</subject><ispartof>arXiv.org, 2022-01</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2005.05144$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1007/s10579-021-09570-4$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Casanova, Edresson</creatorcontrib><creatorcontrib>Arnaldo Candido Junior</creatorcontrib><creatorcontrib>Shulby, Christopher</creatorcontrib><creatorcontrib>Santos de Oliveira, Frederico</creatorcontrib><creatorcontrib>Teixeira, João Paulo</creatorcontrib><creatorcontrib>Moacir Antonelli Ponti</creatorcontrib><creatorcontrib>Aluisio, Sandra Maria</creatorcontrib><title>TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese</title><title>arXiv.org</title><description>Speech provides a natural way for human-computer interaction. In particular, speech synthesis systems are popular in different applications, such as personal assistants, GPS applications, screen readers and accessibility tools. However, not all languages are on the same level when in terms of resources and systems for speech synthesis. This work consists of creating publicly available resources for Brazilian Portuguese in the form of a novel dataset along with deep learning models for end-to-end speech synthesis. Such dataset has 10.5 hours from a single speaker, from which a Tacotron 2 model with the RTISI-LA vocoder presented the best performance, achieving a 4.03 MOS value. The obtained results are comparable to related works covering English language and the state-of-the-art in Portuguese.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Learning</subject><subject>Datasets</subject><subject>Machine learning</subject><subject>Noise reduction</subject><subject>Phonetics</subject><subject>Speech recognition</subject><subject>Vocoders</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNpFj01Lw0AQhhdBsNT-AE8ueE6czO5MUm8a_IKAgrmHNd21KTWJu4lYf72xFTy97-Gd4XmEOEsg1hkRXBr_1XzGCEAxUKL1kZihUkmUacQTsQhhAwDIKRKpmSjK8iV67vwwvo02WJl3vh_DlTSy3jfpOi9Db229lmHXDmsbmiCbVt54891sG9PK_-tTcezMNtjFX85FeXdb5g9R8XT_mF8XkSGkCBUTrZSpLS8TSi2z0moCYgZGi-BScuw0rMCRyVTGqeb6lY1R1qZuqdVcnB_e7lWr3jfvxu-qX-VqrzwtLg6L3ncfE9lQbbrRtxNThRoSShiR1A9Dd1g2</recordid><startdate>20220129</startdate><enddate>20220129</enddate><creator>Casanova, Edresson</creator><creator>Arnaldo Candido Junior</creator><creator>Shulby, Christopher</creator><creator>Santos de Oliveira, Frederico</creator><creator>Teixeira, João Paulo</creator><creator>Moacir Antonelli Ponti</creator><creator>Aluisio, Sandra Maria</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220129</creationdate><title>TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese</title><author>Casanova, Edresson ; Arnaldo Candido Junior ; Shulby, Christopher ; Santos de Oliveira, Frederico ; Teixeira, João Paulo ; Moacir Antonelli Ponti ; Aluisio, Sandra Maria</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a525-23655d3ace69157e6634326766062e20f75f6f40d0f5a8386746cb6aa3ee7f943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Learning</topic><topic>Datasets</topic><topic>Machine learning</topic><topic>Noise reduction</topic><topic>Phonetics</topic><topic>Speech recognition</topic><topic>Vocoders</topic><toplevel>online_resources</toplevel><creatorcontrib>Casanova, Edresson</creatorcontrib><creatorcontrib>Arnaldo Candido Junior</creatorcontrib><creatorcontrib>Shulby, Christopher</creatorcontrib><creatorcontrib>Santos de Oliveira, Frederico</creatorcontrib><creatorcontrib>Teixeira, João Paulo</creatorcontrib><creatorcontrib>Moacir Antonelli Ponti</creatorcontrib><creatorcontrib>Aluisio, Sandra Maria</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Casanova, Edresson</au><au>Arnaldo Candido Junior</au><au>Shulby, Christopher</au><au>Santos de Oliveira, Frederico</au><au>Teixeira, João Paulo</au><au>Moacir Antonelli Ponti</au><au>Aluisio, Sandra Maria</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese</atitle><jtitle>arXiv.org</jtitle><date>2022-01-29</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Speech provides a natural way for human-computer interaction. In particular, speech synthesis systems are popular in different applications, such as personal assistants, GPS applications, screen readers and accessibility tools. However, not all languages are on the same level when in terms of resources and systems for speech synthesis. This work consists of creating publicly available resources for Brazilian Portuguese in the form of a novel dataset along with deep learning models for end-to-end speech synthesis. Such dataset has 10.5 hours from a single speaker, from which a Tacotron 2 model with the RTISI-LA vocoder presented the best performance, achieving a 4.03 MOS value. The obtained results are comparable to related works covering English language and the state-of-the-art in Portuguese.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2005.05144</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2022-01 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2005_05144 |
| source | arXiv.org; Free E- Journals |
| subjects | Computer Science - Computation and Language Computer Science - Learning Datasets Machine learning Noise reduction Phonetics Speech recognition Vocoders |
| title | TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T05%3A39%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=TTS-Portuguese%20Corpus:%20a%20corpus%20for%20speech%20synthesis%20in%20Brazilian%20Portuguese&rft.jtitle=arXiv.org&rft.au=Casanova,%20Edresson&rft.date=2022-01-29&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2005.05144&rft_dat=%3Cproquest_arxiv%3E2401516225%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2401516225&rft_id=info:pmid/&rfr_iscdi=true |