Kishore S. Prahallad

Assistant 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 / Tutorials: 

Lecture/Course Slides:

  • Classification of Speech Sounds - pdfvideo
  • Feature in Time Domain  - pdfvideo
  • Features in Frequency Domain - pdfvideo
  • Spectrogram, Cepstrum and Mel Frequency:  pdfvideo
  • Overview of text-to-speech (TTS) system - ppt  video

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