MMSE estimation of log-filterbank energies for robust speech recognition

There are no files associated with this record.

Title MMSE estimation of log-filterbank energies for robust speech recognition
Author Stark, Anthony Phillip; Paliwal, Kuldip Kumar
Journal Name Speech Communication
Year Published 2011
Place of publication Netherlands
Publisher Elsevier BV * North-Holland
Abstract In this paper, we derive a minimum mean square error log-filterbank energy estimator for environment-robust automatic speech recognition. While several such estimators exist within the literature, most involve trade-offs between simplifications of the log-filterbank noise distortion model and analytical tractability. To avoid this limitation, we extend a well known spectral domain noise distortion model for use in the log-filterbank energy domain. To do this, several mathematical transformations are developed to transform spectral domain models into filterbank and log-filterbank energy models. As a result, a new estimator is developed that allows for robust estimation of both log-filterbank energies and subsequent Mel-frequency cepstral coefficients. The proposed estimator is evaluated over the Aurora2, and RM speech recognition tasks, with results showing a significant reduction in word recognition error over both baseline results and several competing estimators.
Peer Reviewed Yes
Published Yes
Alternative URI http://dx.doi.org/10.1016/j.specom.2010.11.004
Volume 53
Issue Number 3
Page from 403
Page to 416
ISSN 0167-6393
Date Accessioned 2012-03-20; 2012-04-10T23:50:26Z
Date Available 2012-04-10T23:50:26Z
Research Centre Institute for Integrated and Intelligent Systems
Faculty Faculty of Science, Environment, Engineering and Technology
Subject Artificial Intelligence and Image Processing
URI http://hdl.handle.net/10072/44400
Publication Type Journal Articles (Refereed Article)
Publication Type Code c1

Brief Record

Griffith University copyright notice