We present a method that determines the optimal configuration of a bilinear vocal tract length normalization function to transform the frequency axis of one voice according to a specific target voice. Given a number of parallel utterances of the involved speakers, the single parameter of this function can be calculated through an iterative procedure by minimizing an objective error measure defi...

This paper presents one method for designing all-pass filters which approximates a desired all band group delay. The method is based on the relation between the complex Cepstrum and a stable minimum-phase sequence. Given the desired group delay, the design procedure consists of the computation of the complex Cepstral coefficients in such a way that the denominator group delay is approximated in...

Smoothing selected cepstral coefficients over time has been recently shown to be a powerful method in the enhancement of noisy speech signals. A difficulty that arises in this context is that averaging a random variable in the log-domain changes its mean in the linear domain. The knowledge of this bias is indispensable for most temporal cepstrum smoothing applications. To date, the bias is know...

In this paper, we propose a formant weighted cepstral feature for LSP-based speech recognition system. The proposed weighting scheme is based on the well-known property of LSPs that the speech spectrum has a peak when adjacent LSFs come close. By applying this scheme to pseudo-cepstrum (PCEP) conversion process [1], we can obtain formant weighted or peak enhanced cepstral feature. Results of sp...

The goal is to improve recognition rate by optimisation of Mel Frequency Cepstral Coe cients (MFCCs): modi cations concern the time-frequency representations used to estimate these coe cients. There are many ways to obtain a spectrum out of a signal which di er in the method itself (Fourier, Wavelets,...), and in the normalisation. We show here that we can obtain noise resistant cepstral coe ci...