Auditory front-ends for noise-robust automatic speech recognition

摘要

In this paper we investigate a noise-robust feature extraction method, which is based on the auditory masking effect, for automatic speech recognition systems. We physically model the basilar membrane as a cascade system of simple harmonic oscillators, and mathematically analyze the motion of the basilar membrane due to speech signals. Based on the analysis, we can identify a correlational factor for the coupled motion of the oscillators, which can be used to partially explain the masking effect. Accordingly, we insert an auditory module in the speech feature extraction process. The proposed methodology is evaluated on the Aurora 2.0 noisy-digit speech database, and it achieves significant improvements.