Associate Professor, International Institute of Information Technology, Hyderabad.
Office: A3-120 (Vindhya Block). Tel: +91-40-66531177
Email: kishore AT iiit.ac.in, URL: http://www.iiit.ac.in/~kishore
________________________________________________________________________________________________
Talks/Workshops/Conferences Organized:
Expert talk, Speech Technology and applications, NLP Workshop, Thapar University, Dec 7, 2013.
Tutorial, Clustering of static and temporal datasets, WiSSAP, IIT Madras, Feb 22, 2013.
A tutorial review on text-to-speech conversion, WISP, IIIT Hyderabad, Dec 17, 2012.
Expert talk, Recent trends in speech synthesis, Research and training unit for navigational electronics, Osmania Univ., Nov 10, 2012.
Invited talk, Dealing with untranscribed speech, SPCOM, IISc Bangalore, July 24, 2012.
Invited talk, Spoken dialog Systems, Vasavi college of eng., Hyderabad, Feb 28, 2012.
Seminar, Automatic building of synthetic voices from audio books, SERC, IISc Bangalore, May 30, 2011.
Winter school on speech technology, information retrieval, data mining, IIIT Hyderabad, Dec 8-21, 2010.
Invited talk on text-to-speech using audio books, JNTU Hyderabad, Nov 2010.
Winter school on speech technology, information retrieval, computer games, IIIT Hyderabad, Dec 2009.
Invited Talk, An overview of text-to-speech systems, IIT Kharagpur, Mar 4-5, 2009.
Short term course on automatic speech recognition, IIIT Hyderabad, May 2008.
Short term course on building synthetic voices, IIIT Hyderabad, June 2008.
W3C’s speech synthesis markup language (SSML), Workshop III, IIIT Hyderabad Jan 2007.
Tutorial, Building synthetic voices, International conference on natural language processing (ICON), Hyderabad, Dec 2004.
Lecture/Course Slides:
4. Spectrogram, Cepstrum and Mel Frequency: pdf, video
Reference for 2-4 Lectures: Huang, Xuedong, et al. Spoken language processing: A guide to theory, algorithm, and system development. Prentice Hall PTR, 2001.
Reports:
Kishore Prahallad, Automatic Building of Synthetic Voices from Audio Books, PhD Thesis, Language Technologies Institute, School of Computer Science, Carnegie Mellon University, 2010. PDF
Kishore Prahallad, A Direct Approach for Speech to Speech Translation, A Project Report in Machine Translation Course, LTI-CMU, Spring 2005. PDF
Kishore Prahallad, Vamshi Krishna and B. Yegnanarayana, Formant Extraction using Difference Spectrum, (not accepted in ICASSP 2004). PDF
Kishore Prahallad, High Performance Acoustic Boundary Detection Using a New Architecture of Neural Network Classifiers,A Project Report in Machine Learning course, LTI-CMU, Fall 2003. PDF
Kishore Prahallad, Identification of Pose and Expression from Facial Images, A Project Report in Machine Learning course, LTI-CMU, Fall 2003. PDF
Kishore Prahallad, Speaker Verification Using Autoassociative Neural Networks, Masters Thesis, Dept. of Computer Sc. & Engg., Indian Institute of Technology, Madras, 2001. PDF