Contemporary Methods for Speech Parameterization

Contemporary Methods for Speech Parameterization offers a general view of short-time cepstrum-based speech parameterization and provides a common ground for further in-depth studies on the subject. Specifically, it offers a comprehensive description, comparative analysis, and empirical performance evaluation of eleven contemporary speech parameterization methods, which compute short-time cepstrum-based speech features.

Among these are five discrete wavelet packet transform (DWPT)-based, six discrete Fourier transform (DFT)-based speech features and some of their variants which have been used on the speech recognition, speaker recognition, and other related speech processing tasks. The main similarities and differences in their computation are discussed and empirical results from performance evaluation in common experimental conditions are presented. The recognition accuracy obtained on the monophone recognition, continuous speech recognition and speaker recognition tasks is contrasted against the one obtained for the well-known and widely used Mel Frequency Cepstral Coefficients (MFCC).

It is shown that many of these methods lead to speech features that do offer competitive performance on a certain speech processing setup when compared to the venerable MFCC. The last does not target the promotion of certain speech features but instead aims to enhance the common understanding about the advantages and disadvantages of the various speech parameterization techniques available today and to provide the basis for selection of an appropriate speech parameterization in each particular case.

Analysis of Speech Parameterization compares traditional and contemporary speech parameterization techniques used in speech and speaker recognition tasks. The author offers a comprehensive description and comparative evaluation of the ten most widely used frame-based short-term spectrum analysis techniques, among which are a number traditional and recent Fourier transform- and some competitive wavelet packets transform- based schemes. The influence and the proper choice of a basic function for the wavelet packets -based speech parameterizations is discussed and illustrated through a comparative evaluation of nine different basis wavelet functions on the speaker verification task. The book intends to serve the large community of speech processing researchers and practitioners, working in the field of speech and speaker recognition, in order to familiarize them with the wide range of available speech parameterization techniques.