An improvement in audio-visual voice activity detection for automatic speech recognition

摘要

Abstract. Noise-robust Automatic Speech Recognition (ASR) is essential for robots which are expected to communicate with humans in a daily environment. In such an environment, Voice Activity Detection (VAD) strongly affects the performance of ASR because there are many acoustically and visually noises. In this paper, we improved Audio-Visual VAD for our two-layered audio visual integration framework for ASR by using hangover processing based on erosion and dilation. We implemented proposed method to our audio-visual speech recognition system for robot. Empirical results show the effectiveness of our proposed method in terms of VAD.