Mel Frequency Teager Energy Features for Isolate Word Recognition in Noisy Environment

This paper introduces a robust feature extraction algorithm for speech recognition. A feature extraction algorithm is motivated by the enhanced discrimination capability of Teager Energy Operator (TEO) that estimates the true energy of the source of a resonance. The robust features are computed from the speech signal of given frame through the following steps. First, the short time spectrum of each frame of speech signal is calculated. Second, the frame spectrum is passed through a Mel scaled triangular filter bank. Then, the mean of absolute values of sequence obtained after applying TEO on each filter output is estimated. Finally, the cepstral coefficients are extracted by applying discrete cosine transform on the estimated means. The estimated features are denoted as Mel Frequency Teager Energy Cepstral Coefficients (MFTECC). The effectiveness of this technique has been tested on TI-20 isolated word database and its noisy part created by adding various additive noises like white, babble, train and street noise. The experimental results show the superiority of the proposed technique over conventional MFCC.