SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model
In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker text-to-speech model that improves similarity for speakers unseen during training. We propose a speaker-conditional architecture that explores a flow-based decoder that works in a zero-shot scenario. As text encoders, we expl...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Casanova, Edresson Shulby, Christopher Gölge, Eren Müller, Nicolas Michael de Oliveira, Frederico Santos Junior, Arnaldo Candido Soares, Anderson da Silva Aluisio, Sandra Maria Ponti, Moacir Antonelli |
| description | In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker
text-to-speech model that improves similarity for speakers unseen during
training. We propose a speaker-conditional architecture that explores a
flow-based decoder that works in a zero-shot scenario. As text encoders, we
explore a dilated residual convolutional-based encoder, gated
convolutional-based encoder, and transformer-based encoder. Additionally, we
have shown that adjusting a GAN-based vocoder for the spectrograms predicted by
the TTS model on the training dataset can significantly improve the similarity
and speech quality for new speakers. Our model converges using only 11
speakers, reaching state-of-the-art results for similarity with new speakers,
as well as high speech quality. |
| doi_str_mv | 10.48550/arxiv.2104.05557 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2104_05557</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2104_05557</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-30c20208a6426ec13b52f9dcfad740811f7ea7c1dfd40f7e30ce78fcdf1935d43</originalsourceid><addsrcrecordid>eNotj71OwzAUhb0woMIDMOEXcPBvnHZDUShIrRjiiSUy9r2q1VBXJkB5e9rS6ZwjfTrSR8id4JVujOEPvhzSdyUF1xU3xthr0vUtW475x7l-Qf2OdogpJNhN9A1KZv0mT3T9NU6J9XvwWyjUwWFiLp82hA1d5wjjDblCP37C7SVnxD11rn1mq9flS_u4Yr62likeJJe88bWWNQSh3o3EeQzoo9W8EQIteBtExKj5sR95sA2GiGKuTNRqRu7_b88ew76kD19-h5PPcPZRf5QQRHY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model</title><source>arXiv.org</source><creator>Casanova, Edresson ; Shulby, Christopher ; Gölge, Eren ; Müller, Nicolas Michael ; de Oliveira, Frederico Santos ; Junior, Arnaldo Candido ; Soares, Anderson da Silva ; Aluisio, Sandra Maria ; Ponti, Moacir Antonelli</creator><creatorcontrib>Casanova, Edresson ; Shulby, Christopher ; Gölge, Eren ; Müller, Nicolas Michael ; de Oliveira, Frederico Santos ; Junior, Arnaldo Candido ; Soares, Anderson da Silva ; Aluisio, Sandra Maria ; Ponti, Moacir Antonelli</creatorcontrib><description>In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker
text-to-speech model that improves similarity for speakers unseen during
training. We propose a speaker-conditional architecture that explores a
flow-based decoder that works in a zero-shot scenario. As text encoders, we
explore a dilated residual convolutional-based encoder, gated
convolutional-based encoder, and transformer-based encoder. Additionally, we
have shown that adjusting a GAN-based vocoder for the spectrograms predicted by
the TTS model on the training dataset can significantly improve the similarity
and speech quality for new speakers. Our model converges using only 11
speakers, reaching state-of-the-art results for similarity with new speakers,
as well as high speech quality.</description><identifier>DOI: 10.48550/arxiv.2104.05557</identifier><language>eng</language><subject>Computer Science - Sound</subject><creationdate>2021-04</creationdate><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2104.05557$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2104.05557$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Casanova, Edresson</creatorcontrib><creatorcontrib>Shulby, Christopher</creatorcontrib><creatorcontrib>Gölge, Eren</creatorcontrib><creatorcontrib>Müller, Nicolas Michael</creatorcontrib><creatorcontrib>de Oliveira, Frederico Santos</creatorcontrib><creatorcontrib>Junior, Arnaldo Candido</creatorcontrib><creatorcontrib>Soares, Anderson da Silva</creatorcontrib><creatorcontrib>Aluisio, Sandra Maria</creatorcontrib><creatorcontrib>Ponti, Moacir Antonelli</creatorcontrib><title>SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model</title><description>In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker
text-to-speech model that improves similarity for speakers unseen during
training. We propose a speaker-conditional architecture that explores a
flow-based decoder that works in a zero-shot scenario. As text encoders, we
explore a dilated residual convolutional-based encoder, gated
convolutional-based encoder, and transformer-based encoder. Additionally, we
have shown that adjusting a GAN-based vocoder for the spectrograms predicted by
the TTS model on the training dataset can significantly improve the similarity
and speech quality for new speakers. Our model converges using only 11
speakers, reaching state-of-the-art results for similarity with new speakers,
as well as high speech quality.</description><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71OwzAUhb0woMIDMOEXcPBvnHZDUShIrRjiiSUy9r2q1VBXJkB5e9rS6ZwjfTrSR8id4JVujOEPvhzSdyUF1xU3xthr0vUtW475x7l-Qf2OdogpJNhN9A1KZv0mT3T9NU6J9XvwWyjUwWFiLp82hA1d5wjjDblCP37C7SVnxD11rn1mq9flS_u4Yr62likeJJe88bWWNQSh3o3EeQzoo9W8EQIteBtExKj5sR95sA2GiGKuTNRqRu7_b88ew76kD19-h5PPcPZRf5QQRHY</recordid><startdate>20210402</startdate><enddate>20210402</enddate><creator>Casanova, Edresson</creator><creator>Shulby, Christopher</creator><creator>Gölge, Eren</creator><creator>Müller, Nicolas Michael</creator><creator>de Oliveira, Frederico Santos</creator><creator>Junior, Arnaldo Candido</creator><creator>Soares, Anderson da Silva</creator><creator>Aluisio, Sandra Maria</creator><creator>Ponti, Moacir Antonelli</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210402</creationdate><title>SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model</title><author>Casanova, Edresson ; Shulby, Christopher ; Gölge, Eren ; Müller, Nicolas Michael ; de Oliveira, Frederico Santos ; Junior, Arnaldo Candido ; Soares, Anderson da Silva ; Aluisio, Sandra Maria ; Ponti, Moacir Antonelli</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-30c20208a6426ec13b52f9dcfad740811f7ea7c1dfd40f7e30ce78fcdf1935d43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Casanova, Edresson</creatorcontrib><creatorcontrib>Shulby, Christopher</creatorcontrib><creatorcontrib>Gölge, Eren</creatorcontrib><creatorcontrib>Müller, Nicolas Michael</creatorcontrib><creatorcontrib>de Oliveira, Frederico Santos</creatorcontrib><creatorcontrib>Junior, Arnaldo Candido</creatorcontrib><creatorcontrib>Soares, Anderson da Silva</creatorcontrib><creatorcontrib>Aluisio, Sandra Maria</creatorcontrib><creatorcontrib>Ponti, Moacir Antonelli</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Casanova, Edresson</au><au>Shulby, Christopher</au><au>Gölge, Eren</au><au>Müller, Nicolas Michael</au><au>de Oliveira, Frederico Santos</au><au>Junior, Arnaldo Candido</au><au>Soares, Anderson da Silva</au><au>Aluisio, Sandra Maria</au><au>Ponti, Moacir Antonelli</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model</atitle><date>2021-04-02</date><risdate>2021</risdate><abstract>In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker
text-to-speech model that improves similarity for speakers unseen during
training. We propose a speaker-conditional architecture that explores a
flow-based decoder that works in a zero-shot scenario. As text encoders, we
explore a dilated residual convolutional-based encoder, gated
convolutional-based encoder, and transformer-based encoder. Additionally, we
have shown that adjusting a GAN-based vocoder for the spectrograms predicted by
the TTS model on the training dataset can significantly improve the similarity
and speech quality for new speakers. Our model converges using only 11
speakers, reaching state-of-the-art results for similarity with new speakers,
as well as high speech quality.</abstract><doi>10.48550/arxiv.2104.05557</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2104.05557 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2104_05557 |
| source | arXiv.org |
| subjects | Computer Science - Sound |
| title | SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T23%3A19%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=SC-GlowTTS:%20an%20Efficient%20Zero-Shot%20Multi-Speaker%20Text-To-Speech%20Model&rft.au=Casanova,%20Edresson&rft.date=2021-04-02&rft_id=info:doi/10.48550/arxiv.2104.05557&rft_dat=%3Carxiv_GOX%3E2104_05557%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |