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

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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,

Název v anglickém jazyce

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

Popis výsledku anglicky

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,

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

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

Rok uplatnění

2012

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2012 International Symposium on Biometrics and Security Technologies (ISBAST 2012)

ISBN

978-0-7695-4696-4

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

126-133

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Taipei

Datum konání akce

26. 3. 2012

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—