Robust Hierarchical Linear Model Comparison for End-of-Utterance Detection under Noisy Environments

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F12%3A00197446" target="_blank" >RIV/68407700:21240/12:00197446 - isvavai.cz</a>
Result on the web
<a href="http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6189641" target="_blank" >http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6189641</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ISBAST.2012.26" target="_blank" >10.1109/ISBAST.2012.26</a>

Result language
angličtina
Original language name
Robust Hierarchical Linear Model Comparison for End-of-Utterance Detection under Noisy Environments
Original language description
A simple and efficient algorithm for robust end-of-utterance detection of speech signal in noisy environments is proposed in the paper. To detect speech-block end-points, we use entropy sequence of the input speech signal, and hierarchically compare thefit of two weighted linear models. The first model, M1, is very simple; it corresponds to a constant average entropy level for the speech signal in the entire window. The second model, M2, corresponds to a step-like entropy change from one constant levelto another, with a gradual transition between the levels. Model M2 is in fact a piecewise linear regression model with two horizontal lines connected by a third transitional line. We treat M1 as a linear model only to be able to describe it as a submodel of M2 and use methodology based on statistical submodel testing. The regression models are constructed so that their fit will differ the most near the speech-block end-points. The models are fitted in a interval of the entropy sequence,
Czech name
—
Czech description
—

Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

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

Article name in the collection
2012 International Symposium on Biometrics and Security Technologies (ISBAST 2012)
ISBN
978-0-7695-4696-4
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
126-133
Publisher name
IEEE Computer Society
Place of publication
Los Alamitos
Event location
Taipei
Event date
Mar 26, 2012
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)