Speaker: Sourabh Ravindran

Title: Perceptual Audio Classification

Date: March 26, 2004

Time: 3:00 pm

Location: GCATT Room 325

Abstract: People are very skilled at interpreting the environment around them
through sounds that they hear. For example, it is easy for a person to identify water running in the sink, and its amount, by the sound it makes. Auditory scene classification system based on advanced models of the human auditory system will provide gains in robustness and performance. Combining features extracted from such models with physiologically motivated classification structures would further enhance the classification performance.

Biography:

Sourabh Ravindran completed his Masters from Georgia Tech in Fall 2002. His
research interests include, mathematical modelling of the auditory system,
developing efficient classification algorithms, speaker identification, speech
recognition and analog VLSI implementation of signal processing algorithms.

Slides:

Speaker:	Sourabh Ravindran
Title:	Perceptual Audio Classification
Date:	March 26, 2004
Time:	3:00 pm
Location:	GCATT Room 325
Abstract:	People are very skilled at interpreting the environment around them through sounds that they hear. For example, it is easy for a person to identify water running in the sink, and its amount, by the sound it makes. Auditory scene classification system based on advanced models of the human auditory system will provide gains in robustness and performance. Combining features extracted from such models with physiologically motivated classification structures would further enhance the classification performance.
Biography:	Sourabh Ravindran completed his Masters from Georgia Tech in Fall 2002. His research interests include, mathematical modelling of the auditory system, developing efficient classification algorithms, speaker identification, speech recognition and analog VLSI implementation of signal processing algorithms.
Slides: