Kishore S. Prahallad (Lectures/Reports)

Associate Professor, International Institute of Information Technology, Hyderabad.
Office: A3-120 (Vindhya Block).  Tel: +91-40-66531177
Email: kishore AT, URL: 

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:
  • 1. Classification of Speech Sounds - pdfvideo
  • 2. Feature in Time Domain  - pdfvideo
  • 3. Features in Frequency Domain - pdfvideo
  • 4. Spectrogram, Cepstrum and Mel Frequency:  pdfvideo
    • Reference for 2-4 Lectures: Huang, Xuedong, et al. Spoken language processing: A guide to theory, algorithm, and system development. Prentice Hall PTR, 2001.
  • 5. Overview of text-to-speech (TTS) system - ppt  video
  • 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