Estimation des instants de fermeture basée sur un coût d'adéquation du modèle LF à la source glottique
Damien Vincent, Olivier Rosec, Thierry Chonavel.
An algorithm for GCI (Glottal Closure Instants) estimation is presented in this paper. It relies on a source-filter model of speech production using a LF model for the source component. From this source-filter decomposition, a ratio which measures the goodness of fit of the LF source model is introduced in the GCI estimation procedure together with fundamental frequency constraints.
Then, a Viterbi algorithm is applied to extract the most likely GCI sequence. Experiments performed on a real speech database show that the proposed method outperforms existing approaches.