Comparative Evaluation of Speech Parameterizations for Speech Recognition

In this work, we present comparative evaluation of the practical value of some recently proposed speech parameterizations on the speech recognition task. Specifically, in a common experimental setup we evaluate recent discrete wavelet-packet transform (DWPT)-based speech features against traditional techniques, such as the Mel-frequency cepstral coefficients (MFCC) and perceptual linear predictive (PLP) cepstral coefficients that presently dominate the speech recognition field. The relative ranking of eleven sets of speech features is presented.

• Type: Conference
• Year: 2007
• Where: ICTAI
• Authors: Iosif Mporas, Todor Ganchev, Mihalis Siafarikas, Theodoros Kostoulas
• Keywords: Artificial Intelligence, Cepstral Coefficients, ICTAI 2007, Speech Recognition, Speech Recognition Task