Spectral subband centroids as features for speech recognition

Cepstral coefficients derived either through linear prediction (LP) analysis or from filter banks are perhaps the most commonly used features in currently available speech recognition systems. We propose spectral subband centroids as new features and use them as supplements to cepstral features for speech recognition. We show that these features have properties similar to formant frequencies and are quite robust to noise. Recognition results are reported in the paper justifying the usefulness of these features as supplementary features