Czech Speech Synthesis with Generative Neural Vocoder
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F19%3A43955905" target="_blank" >RIV/49777513:23520/19:43955905 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007%2F978-3-030-27947-9_26" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-030-27947-9_26</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-030-27947-9_26" target="_blank" >10.1007/978-3-030-27947-9_26</a>
Alternative languages
Result language
angličtina
Original language name
Czech Speech Synthesis with Generative Neural Vocoder
Original language description
In recent years, new neural architectures for generating high-quality synthetic speech on a per-sample basis were introduced. We describe our application of statistical parametric speech synthesis based on LSTM neural networks combined with a generative neural vocoder for the Czech language. We used a traditional LSTM architecture for generating vocoder parametrization from linguistic features. We replaced a standard vocoder with a WaveRNN neural network. We conducted a MUSHRA listening test to compare the proposed approach with the unit selection and LSTM-based parametric speech synthesis utilizing a standard vocoder. In contrast with our previous work, we managed to outperform a well-tuned unit selection TTS system by a great margin on both professional and amateur voices.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20205 - Automation and control systems
Result continuities
Project
<a href="/en/project/GA19-19324S" target="_blank" >GA19-19324S: Fully Trainable Deep Neural Network Based Czech Text-to-Speech Synthesis</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Text, Speech, and Dialogue 22nd International Conference, TSD 2019, Ljubljana,Slovenia, September 11-13, 2019, Proceedings
ISBN
978-3-030-27946-2
ISSN
0302-9743
e-ISSN
1611-3349
Number of pages
9
Pages from-to
307-315
Publisher name
Springer
Place of publication
Cham
Event location
Ljubljana, Slovenia
Event date
Sep 11, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—