Improvement of naturalness for an HMM-based Vietnamese speech synthesis using the prosodic information

Abstract

Natural-sounding synthesized speech is goal of HMM-based Text-to-Speech systems. Besides using context dependent tri-phone units from a large corpus speech database, many prosody features have been used in full-context labels to improve naturalness of HMM-based Vietnamese synthesizer. In the prosodic specification, tone, part-of-speech (POS) and intonation… (More)
DOI: 10.1109/RIVF.2013.6719907

Topics

11 Figures and Tables

Slides referencing similar topics