|
Descripción
|
|
|---|---|
| This presents a robust voice activity detector (V AD) based on Hidden Markov Models (HMM) in stationary and non-stationary noise environments: inside motor vehicles (like cars or planes) or inside buDdings close to high traffic places (like in a control tower for air tramc control (ATC». In these environments, there is a high stationary noise level caused by vehicle motors and additionally, there could be people speaking at certain distance from the main speaker producing non-stationary noise. The V AD presented herein Is characterized by a new front-end and a noise level adaptation process that increases significantly the V AD robustness for different signal to noise ratios (SNRs). The feature vector used by the V AD includes the most relevant Mel Frequency Cepstral Coefficients (MFCC), normalized log energy, and delta log energy. The proposed V AD has been evaluated and compared to other weD-known V ADs using three databases containing different noise conditions: speech in clean environments (SNRs > 20 dB), speech recorded in stationary noise environments (inside or close to motor vehicles), and finally, speech in non-stationary environments (including noise from bars, television, and far-field speakers). In the three cases, the detection error obtained with the proposed V AD is the lowest for all SNRs compared to Acero's V AD | |
|
Internacional
|
Si |
|
JCR del ISI
|
Si |
|
Título de la revista
|
Ieee Aerospace And Electronic Systems Magazine |
|
ISSN
|
0885-8985 |
|
Factor de impacto JCR
|
0,179 |
|
Información de impacto
|
|
|
Volumen
|
26 |
|
DOI
|
|
|
Número de revista
|
11 |
|
Desde la página
|
16 |
|
Hasta la página
|
23 |
|
Mes
|
SIN MES |
|
Ranking
|
|