ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Non-Linear Filtering for Feature Enhancement of Reverberant Speech

Verma, Amit Kumar and Tomar, Hemendra and Chetupalli, Srikanth Raj and Sreenivas, TV (2017) Non-Linear Filtering for Feature Enhancement of Reverberant Speech. In: TENCON IEEE Region 10 Conference Proceedings, NOV 05-08, 2017, MALAYSIA, pp. 1800-1805.

[img] PDF
IEEE_Reg_Con_1805_2017.pdf - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy
Official URL: http://dx.doi.org/10.1109/TENCON.2017.8228150


Speaker identification implemented on a mobile robot is a challenging problem because of varying reverberant environments which the robot encounters while in motion. The performance of a typical speaker identification system degrades significantly in reverberant environments. The degradation in performance is mainly due to the conventional feature being not robust to change in reverberant condition. In this paper, we present a non-linear filter based mel frequency cepstral coefficient (MFCC) feature extraction, which is more robust to changes in reverberant conditions. This feature extraction method is a two stage operation and is applied on the spectrogram of the speech signal. The first stage suppresses the frequency spread due to reverberation within each frame and in the second stage, reverberation effect across the frames is suppressed. The performance is evaluated by the GMM-UBM based identifier built and tested with conventional MFCC feature vectors and with the non-linear filter based MFCC feature vectors. We show that, the identification accuracy of GMM-UBM based identifier with non-linear filter based MFCC feature vectors is better than that of conventional MFCC feature vectors.

Item Type: Conference Proceedings
Series.: TENCON IEEE Region 10 Conference Proceedings
Publisher: IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA
Additional Information: IEEE Region 10 Conference (TENCON), MALAYSIA, NOV 05-08, 2017 copyright belongs to the IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA
Department/Centre: Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited: 28 Mar 2018 16:18
Last Modified: 28 Mar 2018 16:18
URI: http://eprints.iisc.ac.in/id/eprint/59430

Actions (login required)

View Item View Item