Brandt's GLR method & refined HMM segmentation for TTS synthesis application

In comparison with standard HMM (Hidden Markov Model) with forced alignment, this paper discusses two automatic segmentation algorithms from different points of view: the probabilities of insertion and omission, and the accuracy. The first algorithm, hereafter named the refined HMM algorithm, aims at refining the segmentation performed by standard HMM via a GMM (Gaussian Mixture Model) of each boundary. The second is the Brandt's GLR (Generalized Likelihood Ratio) method. Its goal is to detect signal discontinuities. Provided that the sequence of speech units is known, the experimental results presented in this paper suggest in combining the refined HMM algorithm with Brandt's GLR method and other algorithms adapted to the detection of boundaries between known acoustic classes.