Fifth ISCA ITRW on Speech Synthesis June 14-16, 2004 Pittsburgh, PA, USA

Tools for the Development of a Hindi Speech Synthesis System

Kalika Bali (1), Partha Pratim Talukdar (1), N. Sridhar Krishna (1), A.G. Ramakrishnan (2)

(1) HP Labs India, Bangalore, India
(2) Department of Electrical Engineering, Indian Institute of Science, Bangalore, India

We describe in detail a Grapheme-to-Phoneme (G2P) converter required for the development of a good quality Hindi Text-to-Speech (TTS) system. The Festival framework is chosen for developing the Hindi TTS system. Since Festival does not provide complete language processing support specific to various languages, it needs to be augmented to facilitate the development of TTS systems in certain new languages. Because of this, a generic G2P converter has been developed. In the customized Hindi G2P converter, we have handled schwa deletion and compound word extraction. In the experiments carried out to test the Hindi G2P on a text segment of 3485 words, 97.67% word phonetisation accuracy is obtained. This Hindi G2P has been used for phonetising large text corpora which in turn is used in designing an inventory of coverage of the phonetically valid diphones using only 0.3% of the complete text corpora.

Full Paper

Bibliographic reference.  Bali, Kalika / Talukdar, Partha Pratim / Krishna, N. Sridhar / Ramakrishnan, A.G. (2004): "Tools for the development of a Hindi speech synthesis system", In SSW5-2004, 109-114.