Quantization of Speech Features: Source Coding


In this chapter, we describe various schemes for quantizing speech features to be used in distributed speech recognition (DSR) systems. We have analyzed the statistical properties of 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… (More)


20 Figures and Tables

Cite this paper

@inproceedings{So2014QuantizationOS, title={Quantization of Speech Features: Source Coding}, author={Stephen So and Kuldip K. Paliwal}, year={2014} }