Kishore S Prahallad

Kishore S Prahallad

Dr. Kishore S Prahallad has joined as an associate professor at the International Institute of Information Technology IIIT Hyderabad. He started the speech activities in Language Technologies Research Center (LTRC) at IIIT-H in March 2001 and led a team of researcher scholars and students to build speech systems (on mobile devices) specifically in Indian languages. He served as a research scientist from 2001-2008, senior research scientist from 2008-2010, assistant professor from 2010-2013 and as an associated professor from 2013-2014.

Education

Prof Kishore Prahallad received the B.E. degree from the Deccan College of Engineering and Technology, Osmania University, Hyderabad, India, in 1998, the M.S. (by Research) degree from the Indian Institute of Technology Madras, in 2001 and the Ph.D. degree from the Language Technologies Institute, School of Computer Science, Carnegie Mellon University (CMU), Pittsburgh, USA, in 2010.

Research & Publications

His research interests are Speech systems including text-to-speech, voice conversion, speaker recognition and text processing for Indian languages.

1. Unit-selection text-to-speech synthesis based on predicted concatenation parameters in 2018.
2. Siri on-device deep learning-guided unit selection text-to-speech system in 2017.
3. A common attribute based unified HTS framework for speech synthesis in Indian languages in 2013.
4. Query-by-example spoken term detection using frequency domain linear prediction and non-segmental dynamic time warping in 2014.
5. A syllable-based framework for unit selection synthesis in 13 Indian languages in 2013.
6. Segmentation of monologues in audio books for building synthetic voices in 2010.
7. Text processing for text-to-speech systems in Indian languages in 2007.
8. Fundamental frequency generation for whisper-to-audible speech conversion in 2014.
9. Online text-independent speaker verification system using autoassociative neural network models in 2001.
10. Speaker verification: Minimizing the channel effects using autoassociative neural network models in 2000.