Robust Voice Activity Detection Using a Masked Auditory Encoder Based Convolutional Neural Network

Voice activity detection (VAD) based on deep learning has achieved remarkable success. However, when the traditional features (e.g., raw waveforms and MFCCs) are directly fed to the deep neural network model, the performance decreases because of noise interference. Here, we propose a robust VAD approach using a masked auditory encoder based convolutional neural network (M-AECNN). First, we analyze the effectiveness of using auditory features as deep learning encoder. These features can roughly simulate the transmission of sound to human inner-ear hair cells; thus, they are more robust than the raw waveform and frequency domain features designed as encoders. Second, similar to the human ear’s masking effect for different speech frequencies, the proposed auditory encoder can further improve the robustness of VAD by increasing the gain for cleaner speech frequencies. Extensive experimental results demonstrate that this approach achieves about 10.5% absolute improvement in the area under the curve on the AURORA-2J dataset compared with a VAD method based on a CNN and MFCCs.

1. INTRODUCTION

Voice activity detection (VAD) is a technique to detect whether a sound signal belongs to speech or non-speech based on the statistical distribution of acoustic features. It plays an important role in front-end processing for various speech applications such as speech enhancement, robust speech recognition systems, and speaker recognition.