Home Research Courses Contact

Research Interests

My interests broadly cover

· Computational Auditory Scene Analysis (CASA)

· Robust automatic speech recognition

· Machine learning

· Computational perception in general (vision/audition)

· Brain theory and neural networks

My current research focuses on improving robust automatic speech recognition using CASA techniques. I am primarily focusing on the use of time-frequency binary masks in robust ASR.

Publications

Narayanan A. and Wang D.L., "On the use of Ideal Binary Masks for Improving Phonetic Classification," in Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Prague, May 2011, pp. 5212-5215.

Narayanan A., Zhao X., Wang D.L., and Fosler-Lussier E., "Robust Speech Recognition using Multiple Prior Models for Speech Reconstruction," in Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Prague, May 2011, pp 4800-4803.

Narayanan A. and Wang D.L., "Robust Speech Recognition from Binary Masks," Journal of the Acoustical Society of America, vol. 128, Nov 2010, pp. EL217-222.