test Browse by Author Names Browse by Titles of Works Browse by Subjects of Works Browse by Issue Dates of Works

Advanced Search
& Collections
Issue Date   
Sign on to:   
Receive email
My Account
authorized users
Edit Profile   
About T-Space   

T-Space at The University of Toronto Libraries >
School of Graduate Studies - Theses >
Doctoral >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1807/11253

Title: Graphical Models for Robust Speech Recognition in Adverse Environments
Authors: Rennie, Steven J.
Advisor: Aarabi, Parham
Frey, Brendan J.
Department: Electrical and Computer Engineering
Keywords: Robust Speech Recognition
Graphical Models
Speech Separation
Dynamic Noise Adaptation
Variational Expectation-Maximization (GEM)
Super-human Automatic Speech Recognition (ASR)
Issue Date: 1-Aug-2008
Abstract: Robust speech recognition in acoustic environments that contain multiple speech sources and/or complex non-stationary noise is a difficult problem, but one of great practical interest. The formalism of probabilistic graphical models constitutes a relatively new and very powerful tool for better understanding and extending existing models, learning, and inference algorithms; and a bedrock for the creative, quasi-systematic development of new ones. In this thesis a collection of new graphical models and inference algorithms for robust speech recognition are presented. The problem of speech separation using multiple microphones is first treated. A family of variational algorithms for tractably combining multiple acoustic models of speech with observed sensor likelihoods is presented. The algorithms recover high quality estimates of the speech sources even when there are more sources than microphones, and have improved upon the state-of-the-art in terms of SNR gain by over 10 dB. Next the problem of background compensation in non-stationary acoustic environments is treated. A new dynamic noise adaptation (DNA) algorithm for robust noise compensation is presented, and shown to outperform several existing state-of-the-art front-end denoising systems on the new DNA + Aurora II and Aurora II-M extensions of the Aurora II task. Finally, the problem of speech recognition in speech using a single microphone is treated. The Iroquois system for multi-talker speech separation and recognition is presented. The system won the 2006 Pascal International Speech Separation Challenge, and amazingly, achieved super-human recognition performance on a majority of test cases in the task. The result marks a significant first in automatic speech recognition, and a milestone in computing.
URI: http://hdl.handle.net/1807/11253
Appears in Collections:Doctoral
The Edward S. Rogers Sr. Department of Electrical & Computer Engineering - Doctoral theses

Files in This Item:

File Description SizeFormat
Rennie_Steven_J_200806_PhD_thesis.pdf2.54 MBAdobe PDF

This item is licensed under a Creative Commons License
Creative Commons

Items in T-Space are protected by copyright, with all rights reserved, unless otherwise indicated.