The contribution of differential cepstral coefficients within AF estimation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00219499" target="_blank" >RIV/68407700:21230/14:00219499 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
The contribution of differential cepstral coefficients within AF estimation
Original language description
The paper deals with the contribution of the various dynamic features such as delta, double-delta and tripledelta coefficients in the task of neural network based estimation of articulatory features (AFs) for the Czech language. The analyses of relativeimprovement of AF estimation accuracy using the dynamic features were performed and best results were achieved for Perceptual Linear Prediction Coefficients (PLP) with the triple-delta coefficients. The estimated articulatory features are supposed to beapplied within automatic phonetic segmentation, generally also in spontaneous speech recognition. The temporal derivatives of static parameters were implemented in the CtuCopy tool.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JA - Electronics and optoelectronics
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
POSTER 2014 - 18th International Student Conference on Electrical Engineering
ISBN
978-80-01-05499-4
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
1-4
Publisher name
Czech Technical University
Place of publication
Prague
Event location
Praha
Event date
May 15, 2014
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—