Speech is the basic form of language and thus speech technology (a branch of language technology) lies in the intersection of linguistics and computer science. The language technology or Natural Language Processing (NLP) has its own place in artificial intelligence to enable machines interact with human intelligently. Speech technology involves three primary tasks namely, speech synthesis, speech recognition, and speaker recognition. Speech synthesis has its scope of use wherever there is a digital text and a need to read this. For Indian languages other than Sanskrit, there have many TTS developed and are being developed. The author is developing a speech synthesis system (also known as Text-to-Speech or TTS) for Sanskrit as a part of his PhD thesis. In this presentation, he will also give demo of ready components of the TTS system.
Speaker: Diwakar Mishra, PhD scholar, SCSS, JNU
Venue: Committee Room, JNU Central Library
Date and Time: 12th January 2013 (Saturday), 3:00 pm
For PowerPoint Presentation click here