Information-theoretic distortion measures for speech recognition
- 1 January 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 39 (2) , 330-335
- https://doi.org/10.1109/78.80815
Abstract
A wide variety of speech recognition distortion measures have been proposed and tested, including some especially effective ones. It is shown that there is a general framework, based on the concepts of information theory, linking most of these measures. The distortion measure between any two speech spectra can be defined in terms of the distortions between the associated probability distributions. This general framework defines three broad families of distortion measures for speech recognition and provides a consistent way of combining the energy and the spectral information of a phonetic event. In addition, the cepstral-domain representation for several distortion measures is derived, allowing comparison of these measures in a domain that also yields convenient equations for their practical implementationKeywords
This publication has 14 references indexed in Scilit:
- Spectral slope based distortion measures for all-pole models of speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Optimal and suboptimal training strategies for automatic speech recognition in noise, and the effects of adaptation on performancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Distance measure for speech recognition based on the smoothed group delay spectrumPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Prediction of perceived phonetic distance from critical-band spectra: A first stepPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A weighted cepstral distance measure for speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- On the use of bandpass liftering in speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- Comparative study of several distortion measures for speech recognitionSpeech Communication, 1985
- Some experiments in discrete utterance recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1982
- On information and distance measures, error bounds, and feature selectionInformation Sciences, 1976
- The Divergence and Bhattacharyya Distance Measures in Signal SelectionIEEE Transactions on Communications, 1967