Quantization of Speech Features: Source Coding

There are no files associated with this record.

Title Quantization of Speech Features: Source Coding
Author So, Stephen; Paliwal, Kuldip Kumar
Book Title Automatic Speech Recognition on Mobile Devices and over Communication Networks
Editor Tan, Zheng-Hua; Lindberg, Børge
Year Published 2008
Place of publication London
Publisher Springer
Abstract In this chapter, we describe various schemes for quantizing speech features to be used in distributed speech recognition (DSR) systems. We analyze the statistical properties of Mel frequency-warped cepstral coefficients (MFCCs) that are most relevant to quantization, namely the correlation and probability density function shape, in order to determine the type of quantization scheme that would be most suitable for quantizing them efficiently. We also determine empirically the relationship between mean squared error and recognition accuracy in order to verify that quantization schemes, which minimize mean squared error, are also guaranteed to improve the recognition performance. Furthermore, we highlight the importance of noise robustness in DSR and describe the use of a perceptually weighted distance measure to enhance spectral peaks in vector quantization. Finally, we present some experimental results on the quantization schemes in a DSR framework and compare their relative recognition performances.
Peer Reviewed Yes
Published Yes
Publisher URI http://www.springerlink.com/
Alternative URI http://dx.doi.org/10.1007/978-1-84800-143-5_7
Chapter Number 7
Page from 131
Page to 161
ISBN 978-1-84800-142-8
Date Accessioned 2008-09-23
Date Available 2011-05-13T06:54:58Z
Language en_AU
Research Centre Institute for Integrated and Intelligent Systems
Faculty Faculty of Science, Environment, Engineering and Technology
Subject PRE2009-Signal Processing; PRE2009-Speech Recognition
URI http://hdl.handle.net/10072/21968
Publication Type Book Chapters
Publication Type Code b1

Brief Record

Griffith University copyright notice