Improving the noise-robustness of mel-frequency cepstral coefficients for speech processing.
Sourabh Ravindran, David V. Anderson, Malcolm Slaney · 2006
In this paper we study the noise-robustness of mel-frequency cepstral coefficients (MFCCs) and explore ways to improve their performance in noisy conditions. Improvements based on a more accurate model of the early auditory system are suggested to make the MFCC features more robust to noise while preserving their class discrimination ability. Speech versus non-speech classification and speech recognition are chosen to evaluate the performance gains afforded by the modifications.