Talk: September 8, 2014 : Time-Frequency Modulation Analysis of Autoregressive Spectrogram Models

IEEE Signal Processing Society, Bangalore Chapter, IEEE Bangalore Section and
Department of Electrical Engineering, IISc

invite you to a talk by
Dr. Sriram Ganapathy
IBM T.J. Watson Research Center,
Yorktown Heights, USA

Time-Frequency Modulation Analysis of Autoregressive Spectrogram Models

Time & Date: 4:00pm; Monday September 8, 2014
Venue: Multimedia Classroom (PE 217), Department of Electrical Engineering, IISc.

Even with several advancements in the practical application of speech technology, the performance of speech systems remain fragile in high levels of noise and other environmental distortions. On the other hand, various studies on the human auditory system have shown good resilience of the system to high levels of noise and degradations. This information shielding property of the auditory system may be largely attributed to the signal peak preserving functions performed by the cochlea and the spectro-temporal modulation filtering
performed by the cortical stages. In this talk, I will discuss how these steps can be efficiently emulated in the front-end signal processing of automatic speech systems. A spectrographic representation that emphasizes the high energy regions is derived using time-frequency
autoregressive modeling followed by a modulation filtering step to preserve only the key spectro-temporal modulations. This talk will conclude with experimental results from several interesting speech applications.

Biography of the Speaker
Sriram Ganapathy is a research staff member at the IBM T.J. Watson Research Center, Yorktown Heights, USA, where he is working on signal analysis methods for radio communication speech in highly degraded environments. He received his Doctor of Philosophy from the Center for Language and Speech Processing, Johns Hopkins University in 2011 with Prof. Hynek Hermansky. He obtained his Bachelor of Technology from College of Engineering, Trivandrum, India in 2004 and Master of Engineering from the Indian Institute of Science, Bangalore in 2006. In the past, he has also been part of the Idiap Research Institute in Martigny, Switzerland from 2006 to 2008 contributing to various speech and Audio projects. His research interests include signal processing, machine learning and robust methodologies for speech and speaker recognition. He has secured over 50 publications in leading international journals and conferences in speech and audio processing along with several patents.

Leave a Reply