Computation of TRAP Speech Features Using MATLAB and QuickNet Toolkit

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00195401" target="_blank" >RIV/68407700:21230/12:00195401 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Computation of TRAP Speech Features Using MATLAB and QuickNet Toolkit
Original language description
This paper describes the computation of TRAP speech features in MATLAB environment. Two basic approaches of TRAP features are discussed, commonly with its implementation as MATLAB functions. As TRAP features are based on computation of aposterior probabilities of particular phones using artifficial nerual networks, the possible usage of available MATLAB Neural Network Toolbox is presented. The classification phase of ANN can be impemented without serious problems, however, the training of used ANN is out of computational abilities of MATLAB Neural Network Toolbox. To overcome this problem, the usage of external QuickNet toolkit (realizing the implementation of ANNs) is introduced commonly with possible combinations with MATLAB functions. Finally, basicexperiments with TRAP features computation working as simple phone classifier are presented.
Czech name
—
Czech description
—

Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
POSTER 2012 - 16th International Student Conference on Electrical Engineering
ISBN
978-80-01-05043-9
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
1-4
Publisher name
Czech Technical University in Prague
Place of publication
Praha
Event location
Prague
Event date
May 17, 2012
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)