Emotions analysed by music theory.

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F10%3A00174420" target="_blank" >RIV/68407700:21230/10:00174420 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Emotions analysed by music theory.
Original language description
In the present contribution, I deal with the problem of improvement of synthetic speech prosody. My idea was try to possibility which classify speech signals which hold emotions for the prosody modelling. This my thought was based on the musical theory.The emotional speech analysis started treat my diploma students (see [1], [2]). We use the ANN topology, namely the multilayer neural network (MLNN) with the BPG learning algorithm and the supervised SOM (SSOM) topology for experiments. According to ourexperience the neural networks are able to achieve better results. The great advantage of NN is the robustness of the solution for real methods, in the area of noise signal processing especially. The first experiments are based on the idea of the musicalinterval.
Czech name
—
Czech description
—

Project
<a href="/en/project/GA102%2F09%2F0989" target="_blank" >GA102/09/0989: New innovative methods for high-quality synthesis of Czech speech</a><br>
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year
2010
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
20th Czech - German Workshop on Speech Processing
ISBN
978-80-86269-21-4
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
—
Publisher name
Institute of Photonics and Electronics AS CR
Place of publication
Prague
Event location
Prague
Event date
Sep 29, 2009
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)