Coopération entre méthodes locales et globales pour la segmentation automatique de corpus dédiés à la synthèse vocale
Safaa JARIFI, Olivier ROSEC, Dominique PASTOR.
This paper introduces a new approach for the automatic segmentation of corpora dedicated to speech synthesis.
The main idea behind this approach is to merge the outputs of three segmentation algorithms.
The first one is the standard HMM-based (Hidden Markov Model) approach.
The second algorithm uses a phone boundaries model, namely a GMM (Gaussian Mixture Model).
The third method is based on Brandt's GLR (Generalized Likelihood Ratio) and aims to detect signal discontinuities in the vicinity of the HMM boundaries.
Different fusion strategies are considered for each phonetic class.
The experiments presented in this paper show that the proposed approach yields better accuracy than existing methods.