Cooperation between global and local methods for automatic segmentation of speech synthesis corpora - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Cooperation between global and local methods for automatic segmentation of speech synthesis corpora

Résumé

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 boundary 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.
Fichier principal
Vignette du fichier
ICSLP06DP.pdf (69.23 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02136893 , version 1 (22-05-2019)

Identifiants

  • HAL Id : hal-02136893 , version 1

Citer

Safaa Jarifi, Dominique Pastor, Olivier Rosec. Cooperation between global and local methods for automatic segmentation of speech synthesis corpora. Interspeech - ICSLP 2006 : International Conference on Spoken Language Processing, Sep 2006, Pittsburgh, United States. ⟨hal-02136893⟩
27 Consultations
31 Téléchargements

Partager

Gmail Facebook X LinkedIn More