Gales, M.J.F., Ragni, A. orcid.org/0000-0003-0634-4456, AlDamarki, H. et al. (1 more author) (2010) Support vector machines for noise robust ASR. In: 2009 IEEE Workshop on Automatic Speech Recognition & Understanding. IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU), 13-17 Dec 2009, Merano, Italy. IEEE , pp. 205-210. ISBN 9781424454785
Abstract
Using discriminative classifiers, such as Support Vector Machines (SVMs) in combination with, or as an alternative to, Hidden Markov Models (HMMs) has a number of advantages for difficult speech recognition tasks. For example, the models can make use of additional dependencies in the observation sequences than HMMs provided the appropriate form of kernel is used. However standard SVMs are binary classifiers, and speech is a multi-class problem. Furthermore, to train SVMs to distinguish word pairs requires that each word appears in the training data. This paper examines both of these limitations. Tree-based reduction approaches for multiclass classification are described, as well as some of the issues in applying them to dynamic data, such as speech. To address the training data issues, a simplified version of HMM-based synthesis can be used, which allows data for any word-pair to be generated. These approaches are evaluated on two noise corrupted digit sequence tasks: AURORA 2.0; and actual in-car collected data.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2009 IEEE. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 21 Nov 2019 15:39 |
Last Modified: | 21 Nov 2019 15:39 |
Status: | Published |
Publisher: | IEEE |
Refereed: | Yes |
Identification Number: | 10.1109/ASRU.2009.5372913 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:152855 |