ORVAE: One-Class Residual Variational Autoencoder for Voice Activity Detection in Noisy Environment

2022 ◽  
Author(s):  
Hasam Khalid ◽  
Shahroz Tariq ◽  
TaeSoo Kim ◽  
Jong Hwan Ko ◽  
Simon S. Woo
Keyword(s):  
Voice Activity Detection ◽  
Activity Detection ◽  
Noisy Environment ◽  
Variational Autoencoder ◽  
Voice Activity

scholarly journals Voice Activity Detection for Speech Enhancement Applications

10.14311/1251 ◽  
2010 ◽  
Vol 50 (4) ◽  
Author(s):  
E. Verteletskaya ◽  
K. Sakhnov
Keyword(s):  
Background Noise ◽  
Voice Activity Detection ◽  
Energy Ratio ◽  
Activity Detection ◽  
Noisy Environment ◽  
Signal Energy ◽  
Low Snr ◽  
Noise Robust ◽  
Voice Activity ◽  
Band Signal

This paper describes a study of noise-robust voice activity detection (VAD) utilizing the periodicity of the signal, full band signal energy and high band to low band signal energy ratio. Conventional VADs are sensitive to a variably noisy environment especially with low SNR, and also result in cutting off unvoiced regions of speech as well as random oscillating of output VAD decisions. To overcome these problems, the proposed algorithm first identifies voiced regions of speech and then differentiates unvoiced regions from silence or background noise using the energy ratio and total signal energy. The performance of the proposed VAD algorithm is tested on real speech signals. Comparisons confirm that the proposed VAD algorithm outperforms the conventional VAD algorithms, especially in the presence of background noise.

Sign in / Sign up

Export Citation Format

Share Document