An efficient front-end for automatic speech recognition

This paper deals with the introduction of an efficient speech front-end for automatic speech recognition. This front-end not only performs well, in comparison to the traditional and widely used MFCC, but is also efficiently implemented in a low-resource system. Furthermore, due to its desirable characteristics that allow near-perfect reconstruction of the speech signal, this front-end can directly be used for speech enhancement purposes before the recognition is carried out. Experimental results show that the new front-end is capable of speech recognition with comparable or superior results to MFCC both in clean and noisy conditions. Similar results were also obtained in sub-band speech recognition experiments.