Joint Learning using Denoising Variational Autoencoders for Voice Activity Detection

Abstract

Voice activity detection (VAD) is a challenging task in very low signal-to-noise ratio (SNR) environments. To address this issue, a promising approach is to map noisy speech features to corresponding clean features and to perform VAD using the generated clean features. This can be implemented by concatenating a speech enhancement (SE) and a VAD network, whose parameters are jointly updated. In this paper, we propose denoising variational autoencoder-based (DVAE) speech enhancement in the joint learning framework. Moreover, we feed not only the enhanced feature but also the latent code from the DVAE into the VAD network. We show that the proposed joint learning approach outperforms conventional denoising autoencoder-based joint learning approach.