One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10424483" target="_blank" >RIV/00216208:11320/20:10424483 - isvavai.cz</a>
Result on the web
<a href="https://www.isca-speech.org/archive/Interspeech_2020/abstracts/2679.html" target="_blank" >https://www.isca-speech.org/archive/Interspeech_2020/abstracts/2679.html</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Interspeech.2020-2679" target="_blank" >10.21437/Interspeech.2020-2679</a>
Alternative languages
Result language
angličtina
Original language name
One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech
Original language description
We introduce an approach to multilingual speech synthesis which uses the meta-learning concept of contextual parameter generation and produces natural-sounding multilingual speech using more languages and less training data than previous approaches. Our model is based on Tacotron 2 with a fully convolutional input text encoder whose weights are predicted by a separate parameter generator network. To boost voice cloning, the model uses an adversarial speaker classifier with a gradient reversal layer that removes speaker-specific information from the encoder. We arranged two experiments to compare our model with baselines using various levels of cross-lingual parameter sharing, in order to evaluate: (1) stability and performance when training on low amounts of data, (2) pronunciation accuracy and voice quality of code-switching synthesis. For training, we used the CSS10 dataset and our new small dataset based on Common Voice recordings in five languages. Our model is shown to effectively share informati
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 21st Annual Conference of the International Speech Communication Association
ISBN
—
ISSN
1990-9772
e-ISSN
—
Number of pages
5
Pages from-to
2972-2976
Publisher name
International Speech Communication Association
Place of publication
Baixas, France
Event location
Online
Event date
Oct 25, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—