Abstract
Within the context of robust acoustic features for automatic speech recognition (ASR), we evaluated mel-frequency cepstral coefficients (MFCCs) derived from two spectral representation techniques, i.e. the fast Fourier transform (FFT) and linear pre dictive coding (LPC). ASR systems based on the two feature types were tested on a digit recognition task using continuous density hidden Markov phone models. System performance was determined in clean acoustic conditions as well as in differ ent simulations of adverse acoustic conditions. The LPC-based MFCCs outperformed their FFT counterparts in most of the ad verse acoustic conditions that were investigated in this study. A tentative explanation for this difference in recognition perfor mance is given.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have