Power Spectral Deviation-Based Voice Activity Detection Incorporating Teager Energy for Speech Enhancement
Sang‐Kyun Kim, Sang-Ick Kang, Young‐Jin Park, Sanghyuk Lee, Sangmin Lee · Symmetry · 2016
In this paper, we propose a robust voice activity detection (VAD) algorithm to effectively distinguish speech from non-speech in various noisy environments. The proposed VAD utilizes power spectral deviation (PSD), using Teager energy (TE) to provide a better representation of the PSD, resulting in improved decision performance for speech segments. In addition, the TE-based likelihood ratio and speech absence probability are derived in each frame to modify the PSD for further VAD. We evaluate the performance of the proposed VAD algorithm by objective testing in various environments and obtain better results that those attained by of the conventional methods.