Enhancement of speech intelligibility using transients extracted by wavelet packets

Speech transients have been shown to be important cues for identifying and discriminating speech sounds. We previously described a wavelet packet-based method for extracting transient speech (Rasetshwane et al. WASPAA 2007, pp. 179-182). The algorithm uses a ldquotransitivity functionrdquo to characterize the rate of change of wavelet coefficients, and it can be implemented in real-time to process continuous speech. Psycho-acoustic experiments to select parameters for and to evaluate this method are presented. Results show that modified speech created by amplifying transient speech and adding it to original speech has higher percent word recognition scores than original speech in the presence of background noise.