Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

Global variance in speech synthesis with linear dynamical models

Tsiaras Vasileios, Maia Ranniery S., Diakoloukas Vasilis, Stylianou, Yannis, Digalakis Vasilis

Πλήρης Εγγραφή


URI: http://purl.tuc.gr/dl/dias/11F707E0-A2FA-44DE-B583-E5AC763D629F
Έτος 2016
Τύπος Δημοσίευση σε Περιοδικό με Κριτές
Άδεια Χρήσης
Λεπτομέρειες
Βιβλιογραφική Αναφορά V. Tsiaras, R. Maia, V. Diakoloukas, Y. Stylianou and V. Digalakis, "Global variance in speech synthesis with linear dynamical models," IEEE Signal Proc. Let., vol. 23, no. 8, pp. 1057-1061, Aug. 2016. doi: 10.1109/LSP.2016.2580672 https://doi.org/10.1109/LSP.2016.2580672
Εμφανίζεται στις Συλλογές

Περίληψη

Linear Dynamical Models (LDMs) have been used in speech synthesis recently as an alternative to hidden Markov models (HMMs). Among the advantages of LDMs are the ability to capture the dynamics of speech and the achievement of synthesized speech quality similar to HMM-based speech systems on a smaller footprint. However, such as in the HMM case, LDMs produce over-smoothed trajectories of speech parameters, resulting in muffled quality of synthetic speech. Inspired by a similar problem found in HMM-based speech synthesis, where the naturalness of the synthesized speech is greatly improved when the global variance (GV) is compensated, this paper proposes a novel speech parameter generation algorithm that considers GV in LDM-based speech synthesis. Experimental results show that the application of GV during parameter generation significantly improves speech quality.

Υπηρεσίες

Στατιστικά