Phonetic segmentation using multiple speech features

In this paper we propose a method for improving the performance of the segmentation of speech waveforms to phonetic segments. The proposed method is based on the well known Viterbi timealignment algorithm and utilizes the phonetic boundary predictions from multiple speech parameterization techniques. Specifically, we utilize the best, with respect to boundary type, phone transition position prediction as initial point to start Viterbi time-alignment, for the prediction of the successor phonetic boundary. The method was evaluated on the TIMIT database, with the exploitation of several, well known in the area of speech processing, Fourier-based and wavelet-based speech parameterization algorithms. The results for the tolerance of 20 milliseconds indicated an improvement of the absolute segmentation accuracy by approximately 0.70%, when compared to the baseline speech segmentation scheme.