An application of discriminative feature extraction to filter-bank-based speech recognition.

A pattern recognizer is usually a modular system which consists of a feature extractor module and a classifier module. Traditionally, these two modules have been designed separately, which may not result in an optimal recognition accuracy. To alleviate this fundamental problem, the authors have deve...

Full description

Bibliographic Details

Published in:	IEEE Transactions on speech and audio processing 9, 2 (2001).
Main Author:	Biem, A.
Format:	Article
Language:	English
Subjects:	Classifier module. Discriminative feature extraction. Feature extractor module. Filter-bank-based speech recognition. Modular system. Multi-prototype distance classifier. Pattern recognizer. Recognition errors minimisation. Recognition-oriented analysis.