He did BE in computer science and engineering (CSE) from Deccan College of Eng. & Tech., Osmania University in 1998, MS (by Research) in 2001 from Dept. of CSE, Indian Institute of Technology (IIT) Madras, and PhD in 2010 from Language Technologies Institute, School of Computer Science, Carnegie Mellon University (CMU), USA. His research interests are in speech and language processing, specifically in text-to-speech synthesis and speech recognition. His current projects include building text-to-speech systems for Indian languages, collection of speech corpora in Indian languages, automatic annotation of speech data at phonetic and prosodic level, voice conversion, pronunciation modeling of non-native speech, spoken dialog systems, audio/music information retrieval and summarization, learning from examples and by doing. |