Noise-Robust Speech Features Based on Cepstral Time Coefficients

In this paper, we investigate the noise-robustness of features based on the cepstral time coefficients (CTC). By cepstral time coefficients, we mean the coefficients obtained from applying the discrete cosine transform to the commonly used mel-frequency cepstral coefficients (MFCC). Furthermore, we apply temporal filters used for computing delta and acceleration dynamic features to the CTC, resulting in delta and acceleration features in the frequency domain. We experiment with five different variations of such CTC-based features. The evaluation is done on the Aurora 3 noisy digit recognition tasks with four different languages. The results show all but one such feature set performance gain, the other feature sets actually lead to performance gains. The best feature set achieves an improvement of 25% over the baseline feature set of MFCC.