Influence of variable-length speech units on quality of synthetic speech signal

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F02%3A00071530" target="_blank" >RIV/49777513:23520/02:00071530 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Influence of variable-length speech units on quality of synthetic speech signal
Original language description
This paper examines variable-length speech units in the context of a single unit instance text-to-speech system. Experiments described here were intended as a preparation for our future multiple unit instance system. Subphoneme, phoneme and word units were studied to find out the influence of variable-length units on the synthetic speech in a fully working TTS system. Statistical approach was applied to build variable-length speech unit databases automatically. Longer units were shown to be superior because the synthetic speech contained less spectral discontinuities in comparison with shorter units. Our attention was also paid to a level of clustering speech context in the process of automatic speech unit modeling. Model-level clustering was shown tooutperform state-level clustering.
Czech name
—
Czech description
—

Project
<a href="/en/project/GP102%2F02%2FP134" target="_blank" >GP102/02/P134: Statistical approach to automatic speech segment database construction for synthesis of Czech</a><br>
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year
2002
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Influence of variable-length speech units on quality of synthetic speech signal
ISBN
8299315840
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
1
Publisher name
SuviSoft
Place of publication
Tampere
Event location
Tampere
Event date
Jan 1, 2002
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)