Aarthi Reddy

My coordinates:
Rm 735 McConell Engineering Building
3480 Rue University
Montreal, H3A 2A7
Email: aarthi.reddy AT mail.mcgill.ca
Lab phone: 514-398-2002

    This is me on your left. I am a PhD student at McGill for what seems an interminably long time. I am currently writing my thesis and hope to graduate soon. If you would like to know more about my work, you are welcome to go through my resume (see below), and also browse through my papers. When not working, I have had the opportunity to represent McGill in rowing during the Fall 2009 season. Prior to this I used to do some rock climbing. I have since stopped climbing as I have been unable to find a non-day-dreaming motivating belayer, to replace my fantastic climbing partner who has gone off to live near steep mountains in Calgary.
    I have also been VP Social at the Electrical Engineers Graduate Student Society (EEGSS) for two years, and represented EEGSS at the Teaching Assistants Union for a year.

Education

• McGill University, Montreal, Canada
  Ph.D. Candidate (2005 - present), Dept of Electrical and Computer Engineering
  
  • Dissertation Topic: "Machine Aided Human Translation in a Document Translation Task"
  • Adviser: Richard C. Rose
• University at Buffalo, Buffalo, New York USA
  M.Sc. (2001 - 2004), Dept of Electrical Engineering
  • Adviser: P. C. Cheng
• Madras University, Madras, India
  B.Eng. (1997 - 2001), Dept of Electrical and Electronics Engineering

Publications

• Richard C. Rose, Atta Norouzian, Aarthi Reddy, Andre Coy, Vishwa Gupta and Martin Karafiat
  Subword-Based Spoken Term Detection in Audio Course Lectures
  to be presented at ICASSP, Dallas, USA 2010
• Aarthi Reddy and Richard C. Rose
  Integration of Statistical Models for Dictation of Document Translations in a Machine Aided Human Translation Task
  to appear in IEEE Trans. on Audio, Speech and Language Processing
• Aarthi Reddy, Richard C. Rose, Hani Safadi, Samuel Larkin and Gilles Boulianne
  Incorporating Knowledge of Source Language Text in a System for Dictation of Document Translations
  Machine Translation Summit XII, Ottawa, Canada, August 2010
• Alain Desilets, Marta Stojanovic, Jean-Francois Lapointe, Richard C. Rose and Aarthi Reddy
  Evaluating Productivity Gains of hybrid ASR-MT Systems for Translation Dictation
  Proceedings of IWSLT 2008, Hawaii, USA
• Aarthi Reddy and Richard C. Rose
  Towards domain independence in machine aided human translation
  Proceedings of InterSpeech 2008, Brisbane, Australia, September 2008
• Aarthi Reddy, Richard C. Rose and Alain Desilets
  Integration of ASR and machine translation models in a document translation task
  Proceedings of the International Conference on Spoken Language Processing, pages 2457-2460, August 2007
• Aarthi Reddy and Bhiksha Raj
  Soft Mask Methods for Single-Channel Speaker Separation
  IEEE Transactions on Audio, Speech and Language Processing, Vol 15, No 6, August 2007
• Aarthi Reddy and Bhiksha Raj
  A Minimum Mean Squared Error Estimator for Single Channel Speaker Separation,
  Proceedings of InterSpeech 2004, Jeju, Korea, 2004
• Aarthi Reddy and Bhiksha Raj
  Soft Mask estimation for single channel speaker separation
  ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio, Jeju, Korea, 2004.

Patent

• Separating Multiple Audio Signals Recorded as a Single Mixed Signal
  United States Patent 7454333

Professional Experience

• Mitsubishi Electric Research Labs, Boston, Massachusetts USA
  Intern
  Project: Single channel speaker separation       February, 2004 - June, 2004
• Indian Institute of Technology, Madras, India
  Research Officer
  Project: Speech Recognition for Indian Languages           July, 2004 - June, 2005

Reviewer

• IEEE Transactions in Audio, Speech and Language Processing
• International Conference on Acoustics, Speech and Signal Processing
Internation Speech Communication Association

Teaching Assistant

• Automatic Speech Recognition
• Signals and Systems - I (Continuous Time)
• Signals and Systems - II