Detection of fricatives using S -transform
Hari Krishna Vydana, Anil Kumar Vuppala · The Journal of the Acoustical Society of America · 2016
Two prime acoustic characteristics of fricatives are the concentration of spectral energy above 3 kHz and having noisy nature. Spectral domain approaches for detecting fricatives rely on capturing the information from spectral energy distribution. In this work, S-transform based time-frequency representation is explored for detecting fricatives from continuous speech. S-transform based time-frequency representation exhibits a progressive resolution which is tailored for localizing the high frequency events (i.e., onset and offset of fricative regions) with time. Spectral evidence computed from S-transform based time-frequency representation is observed to perform better compared to the spectral evidence computed from short time Fourier transform. The existing predictability measure based approach relies on capturing the noisy nature of fricatives. A phone level comparative analysis is carried out between S-transform and predictability measure based approaches and the phone distribution of the detected fricatives is observed to be complimentary. In this work, a combination of S-transform and predictability based approaches is put forth for detecting fricatives from continuous speech. Apart from detecting the presence of a fricative, the proposed S-transform based approach and combined approach exhibit better accuracy in detecting the boundaries of fricatives, i.e., extracting the durational information of fricatives.