Kotha : the first to speech synthesis for Bangla language

Abstract

In this Thesis paper, we represent Text to Speech (কথা) synthesis system for Bangla language and how can we develop it using phonology, prosodic rules, G2P conversion including prosodic information in the Festival [1] framework. Since Festival does not provide complete language processing support for all languages, it needs to be augmented to facilitate the development of TTS Systems (কথা) in certain new language Bangla. A new language needs inputs for resolving language specific issues requiring close collaboration between linguists and technologists. Large amount of annotated data is required for developing language-processing modules like text normalization, graphemeto- phoneme (G2P), intonation, and time duration models. We propose how these modules can be develop and integrate it with Festival.