Effects of Training Strategies and the Amount of Speech Data on the Quality of Speech Synthesis

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43973159" target="_blank" >RIV/49777513:23520/24:43973159 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007/978-3-031-70566-3_9" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-70566-3_9</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-70566-3_9" target="_blank" >10.1007/978-3-031-70566-3_9</a>

Result language
angličtina
Original language name
Effects of Training Strategies and the Amount of Speech Data on the Quality of Speech Synthesis
Original language description
During the development of a speech synthesizer, we often face a lack of training data. This paper describes how the amount of data used to train a speech synthesizer affects the quality of the final synthetic speech. To answer this question, we trained multiple VITS synthesizers using different amounts of training data and we compared them using listening tests and the MCD objective measure. Furthermore, we compared three training strategies: training a speech synthesizer from scratch, fine-tuning a single-speaker model and fine-tuning a multi-speaker model.
Czech name
—
Czech description
—

Project
<a href="/en/project/GA22-27800S" target="_blank" >GA22-27800S: Transformers of multiple modalities for more natural spoken dialog</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Text, Speech, and Dialogue. Lecture Notes in Computer Science
ISBN
978-3-031-70565-6
ISSN
0302-9743
e-ISSN
1611-3349
Number of pages
11
Pages from-to
94-104
Publisher name
Springer International Publishing
Place of publication
Cham
Event location
Brno, Czech Republic
Event date
Sep 9, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001307848400009

Similar results(10)