Nepali Text to Speech Synthesis System using ESNOLA Method of Concatenation

Abstract

This paper confer the tools and methodology used in developing a Nepali Text to Speech Synthesis System, which is based on concatenative approach employing Epoch Synchronous Non Overlap Add Method (ESNOLA), which uses signal dictionary having raw sound signal representing parts of phonemes as a speech database. The developed system is an unintonated (flat) TTS system where the pitch of the pre-recorded speech signal remains same throughout, while taking care of aspects such as naturalness, personality, platform independence and quality assessments. Some of the applications and problems encountered with TTS systems are also discussed.