Abstract :
Two techniques are described for efficient encoding of features in pattern recognition. It is shown that the number of binary digits needed to represent patterns can be greatly reduced using efficient feature encoding. Four-thousand utterances based on a 40-word vocabulary are used to evaluate the techniques.
Keywords :
Efficient feature representation, feature encoding, feature selection, isolated word recognition, pattern recognition, rate distortion, speech recognition.; Encoding; Feature extraction; Maintenance; Mutual information; Pattern recognition; Rate-distortion; Signal to noise ratio; Speech recognition; Target recognition; Vocabulary; Efficient feature representation, feature encoding, feature selection, isolated word recognition, pattern recognition, rate distortion, speech recognition.;
