An evaluation of using mutual information for selection of acoustic-features representation of phonemes for speech recognition

Keyphrases

• Mutual Information 100%
• Speech Recognition 100%
• Acoustic Features 100%
• Phoneme 100%
• Feature Representation 100%
• Maximum mutual Information 50%
• Correlation Coefficient 50%
• Recognition Accuracy 50%
• Phoneme Recognition 50%
• Feature Space 25%
• Information Approach 25%
• Kullback-Leibler Divergence 25%
• Mutual Information Criterion 25%
• FFT-based 25%
• Criteria-based 25%
• Set-based 25%
• Feature Vector 25%
• Clear Speech 25%
• Mel Frequency Cepstral Coefficients 25%
• Speech Recognition System 25%
• Phoneme Set 25%
• Feature Select 25%

Engineering

• Mutual Information 100%
• Acoustic Feature 100%
• Recognition Accuracy 50%
• Feature Space 25%
• Feature Vector 25%