Cepstral Domain Talker Stress Compensation for Robust Speech Recognition

摘要

Automatic speech recognition algorithms generally rely on the assumption that for the distance measure used, intraword variabilities are smaller than interword variabilities so that appropriate separation in the measured space is possible. As evidenced by degradation of recognition performance, the validity of such an assumption decreases from simple tasks to complex tasks, from cooperative talkers to casual talkers, and from laboratory talking environments to practical talking environments. This paper presents a study of talker-stress-induced intraword variability, and an algorithm that compensates for the systematic changes observed. The study is based on hidden Markov models trained by speech tokens spoken in various talking styles. The talking styles include normal speech, fast speech, loud speech, soft speech, and talking with noise injected through earphones; the styles are designed to simulate speech produced under real, stressful conditions. Cepstral coefficients are used as the parameters in the hidden Markov models. Substantial reduction of error rates had been achieved when the cepstral domain compensation techniques were tested on the 'simulated stress' speech database.