Sameer Badaskar Graduate Student Language Technologies Institute School of Computer Science Carnegie Mellon University Pittsburgh, PA, 15213.

The goal of my research is to enable the rapid development of Speech to Speech Translation systems in new languages. We endeavor to achieve this through the SPICE project. Currently, I develop the components used for training acoustic models for Automatic Speech Recognition and am advised by Prof. Tanja Schultz. My academic and research interests include Information Retrieval and Machine Learning.

Prior to joining CMU, I was at HP Labs India where I worked on Speech Synthesis and Document Image Processing. I did my Master's at the Indian Institute of Science in Bangalore.

• Spring 2008
  • Optimization
  • Multimedia Databases and Data Mining
• Fall 2007
  • Analysis of Social Media (my annotations page)
  • Language and Statistics - II
  • Software Engineering for Information Technology - I
• Spring 2007
  • Language and Statistics
  • Information Retrieval
  • Multilingual Speech-to-Speech Translation Lab
• Fall 2006
  • Speech Recognition and Understanding
  • Algorithms for NLP

• Identifying Real or Fake Articles: Towards better Language Modeling (PDF)
  Sameer Badaskar, Sachin Agarwal, Shilpa Arora
  Proceedings of IJCNLP 2008, Hyderabad, India.
• SPICE: Web-based Tools for Rapid Language Adaptation in Speech Processing Systems (PDF)
  Tanja Schultz, Alan Black, Sameer Badaskar, Matthew Hornyak, John Kominek
  Proceedings of Interspeech 2007, Antwerp, Belgium.

• Consolidated collection of Wikipedia articles. Useful database for Text Categorization and Information Dynamics.
• Best so far on the Netflix Prize.