Recent Advances in Robust Speech Recognition Technology

Author(s): Chang-Wen Hsu and Lin-Shan Lee

DOI: 10.2174/978160805172411101010175

Higher Order Cepstral Moment Normalization for Improved Robust Speech Recognition

Pp: 175-189 (15)

Buy Chapters

* (Excluding Mailing and Handling)

  • * (Excluding Mailing and Handling)

Abstract

SHS investigation development is considered from the geographical and historical viewpoint. 3 stages are described. Within Stage 1 the work was carried out in the Department of the Institute of Chemical Physics in Chernogolovka where the scientific discovery had been made. At Stage 2 the interest to SHS arose in different cities and towns of the former USSR. Within Stage 3 SHS entered the international scene. Now SHS processes and products are being studied in more than 50 countries.

Abstract

Cepstral normalization has widely been used as a powerful approach to produce robust features for speech recognition. Good examples of this approach include Cepstral Mean Subtraction, and Cepstral Mean and Variance Normalization, in which either the first or both the first and the second moments of the Mel-frequency Cepstral Coefficients (MFCCs) are normalized. In this chapter, we propose the family of Higher Order Cepstral Moment Normalization, in which the MFCC parameters are normalized with respect to a few moments of orders higher than 1 or 2. The basic idea is that the higher order moments are more dominated by samples with larger values, which are very likely the primary sources of the asymmetry and abnormal flatness or tail size of the parameter distributions. Normalization with respect to these moments therefore puts more emphasis on these signal components and constrains the distributions to be more symmetric with more reasonable flatness and tail size. The fundamental principles behind this approach are also analyzed and discussed based on the statistical properties of the distributions of the MFCC parameters. Experimental results based on the AURORA 2, AURORA 3, AURORA 4 testing environments show that with the proposed approach, recognition accuracy can be significantly and consistently improved for all types of noise and all SNR conditions.

Recommended Chapters

We recommend

Favorable 70-S: Investigation Branching Arrow

Authors:Bentham Science Books