Skip to content

Automatic Speech Processing for Voice AI

Photo of Karun Japhet
Hosted By
Karun J. and Naman C.
Automatic Speech Processing for Voice AI

Details

Abstract of the talk:
Speech is the most natural form of human communication. So it only makes sense for AI to have evolved to communicate with humans using voice. This talk will focus on the pillars of voice AI - automatic speech recognition (ASR) and speech synthesis. While automatic speech recognition enables AI to understand messages from users, text-to-speech (TTS) synthesis facilitates the AI to speak in response to user messages. Machine learning techniques and signal processing strategies catering to speech signals are keys to build and maintain efficient voice AI. Our focus for this talk will be the fundamentals of speech processing, problem definition of statistical ASR and corresponding state-of-the-art solutions, basics of TTS synthesis, and generation of natural-sounding AI voices.

About the speaker:
Karthika Vijayan works as a Solution Consultant at Sahaj Software focussing on voice & text-based AI and data science applications. Karthika holds Bachelor’s and Master’s degrees in Electronics and Communication Engineering, and a Ph.D. in Speech Processing from the Indian Institute of Technology, Hyderabad. She has worked as a post-doctoral research associate at the Indian Institute of Science, Bangalore, and as a research fellow at the National University of Singapore. She has extensive experience working on several projects related to automatic speech recognition, speech synthesis, automatic speaker recognition, and singing voice processing. Her research interests include speech processing and natural language processing for AI, pattern recognition and machine learning, deep learning, etc.

Photo of DevDay - Bangalore group
DevDay - Bangalore
See more events
Online event
This event has passed