Autocorrelation-domain method for noise robust speech recognition
Hajer Rahali, Zied Hajaiej, Noureddine Ellouze · International journal of tomography and simulation · 2016
The goal of robust feature extraction is to improve the performance of speech recognition in adverse conditions. This paper introduces a novel representation of speech for the cases where the speech signal is corrupted by additive noises. In this method, the speech features are computed by reducing additive noise effects via filtering stage that is based on an adaptive filtering in the spectral domain followed by filtering with gammachirp filter. A task of isolated word recognition was used to demonstrate the efficiency of these robust features. To improve the robustness of speech we introduce, in this paper, a new set of PLP vector. The above-mentioned technique was tested with white noise and colored noise such as airport, exhibition and babble noises under various noisy conditions within TIMIT and AURORA database. Experimental results show significant improvement in comparison to the results obtained using traditional features extraction techniques.