Filter-bank design based on dependencies between frequency components and phoneme characteristics

Mel-frequency Cepstral coefficients are widely used for feature extraction in speech recognition systems. These features use Mel-scaled filters. A new filter-bank based on dependencies between frequency components and phoneme characteristics is proposed. F-ratio and mutual information are used for this purpose. A new filter-bank is designed in which frequency resolution of sub-band filters is inversely proportional to the computed dependency values. These new filter-bank is used instead of Mel-scaled filters for feature extraction. A phoneme recognition experiment on FARSDAT Persian language database showed that features extracted using the proposed filter-bank reach higher accuracy (63.92%) compared to Mel-scaled filter-bank (62.37%).