van Dalen, R.C., Yang, J., Wang, H. et al. (3 more authors) (2016) Structured discriminative models using deep neural-network features. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 13-17 Dec 2015, Scottsdale, AZ, USA. IEEE , pp. 160-166. ISBN 9781479972913
Abstract
State-of-the-art speech recognisers employ neural networks in various configurations. A standard (hybrid) speech recogniser computes the likelihood for one time frame and state, using only one out of thousands of possible neural-network outputs. However, the whole output vector carries information. In this paper, features from state-of-the-art speech recognisers are collected per phone given a particular context, and input to a discriminative log-linear model. The log-linear model is trained with conditional maximum likelihood or a large-margin criterion. A key element is the prior on the parameters of the log-linear model. The mean of the prior is set to the point where the performance of the original systems is attained. The log-linear model then provides an additional increase over the state-of-the-art performance of the individual systems.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2015 IEEE. |
Keywords: | automatic speech recognition; tandem HMM; hybrid HMM; discriminative log-linear models; structured support vector machines |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Funding Information: | Funder Grant number Engineering and Physical Sciences Research Council (EPSRC) EP/I006583/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 12 Nov 2019 13:53 |
Last Modified: | 12 Nov 2019 13:54 |
Published Version: | https://ieeexplore.ieee.org/document/7404789 |
Status: | Published |
Publisher: | IEEE |
Refereed: | Yes |
Identification Number: | 10.1109/ASRU.2015.7404789 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:152835 |