Title :
Pattern recognition using discriminative feature extraction
Author :
Biem, Alain ; Katagiri, Shigeru ; Juang, Biing-hwang
Author_Institution :
ATR Human Inf. Process. Res. Labs., Kyoto, Japan
fDate :
2/1/1997 12:00:00 AM
Abstract :
We propose a new design method, called discriminative feature extraction for practical modular pattern recognizers. A key concept of discriminative feature extraction is the design of an overall recognizer in a manner consistent with recognition error minimization. The utility of the method is demonstrated in a Japanese vowel recognition task
Keywords :
cepstral analysis; feature extraction; multilayer perceptrons; pattern classification; speech recognition; Japanese vowel recognition task; cepstrum vector; discriminative feature extraction; liftering-based feature extraction; modular pattern recognizers; pattern recognition; recognition error minimization; speech recognition; three-layer perceptron classifier; Cepstrum; Character recognition; Design methodology; Design optimization; Feature extraction; Humans; Information processing; Laboratories; Pattern recognition; Speech recognition;
Journal_Title :
Signal Processing, IEEE Transactions on
