Voice Activity Detector (VAD) Based on Long-Term Mel Frequency Band Features

摘要

We propose a VAD using long-term 200 ms Mel frequency band statistics, auditory masking, and a pre-trained two level decision tree ensemble based classifier, which allows capturing syllable level structure of speech and discriminating it from common noises. Proposed algorithm demonstrates on the test dataset almost 100% acceptance of clear voice for English, Chinese, Russian, and Polish speech and 100% rejection of stationary noises independently of loudness. The algorithm is aimed to be used as a trigger for ASR. It reuses short-term FFT analysis (STFFT) from ASR frontend with additional 2KB memory and 15% complexity overhead.