Noisy word recognition using a feature based on ternarized spectral slope

In previous paper, we proposed a feature FTTSS (Fourier Tranform of Ternarized Spectral Slope) based on power spectrum derivatives with regard to frequency to develop a robust word recognition system under noisy enviroments, and we confirmed noise robustness of the feature compared with MFCC by applying it to word recognition with HMM. Generally, word recognition with HMM is improved by adding features that may express temporal variations, such as ΔMFCC or ΔFTTSS, because HMM can deal with only piecewise stationary signals. Actually, we have examined effectiveness of using ΔFTTSS in word recognition. It is supposed that features showing raw temporal variations of spectral power are effective in speech recognition and ternary conversion of features may decrease deteriorations of recognition performance by noise corruption. Therefore in this research, we propose a new feature FTTTS (Fourier Transform of Ternalized Temporal Slope) instead of ΔFTTSS. The FTTTS is defined by Fourier Transform along frequency of smoothed Ternalized Temporal variations of Spectral power at specific frequency. As a result, we have confirmed experimentally that the proposed feature FTTTS have noise robustness for SNR 0–20 dB compared with FTTSS+ΔFTTSS or the conventional feature MFCC+ΔMFCC by applying them to word recognition with HMM.