Yang, J., Zhang, C., Ragni, A. orcid.org/0000-0003-0634-4456 et al. (2 more authors) (2016) System combination with log-linear models. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 20-25 Mar 2016, Shanghai, China. IEEE ISBN 9781479999880
Abstract
Improved speech recognition performance can often be obtained by combining multiple systems together. Joint decoding, where scores from multiple systems are combined during decoding rather than combining hypotheses, is one efficient approach for system combination. In standard joint decoding the frame log-likelihoods from each system are used as the scores. These scores are then weighted and summed to yield the final score for a frame. The system combination weights for this process are usually empirically set. In this paper, a recently proposed scheme for learning these system weights is investigated for a standard noise-robust speech recognition task, AURORA 4. High performance tandem and hybrid systems for this task are described. By applying state-of-the-art training approaches and configurations for the bottleneck features of the tandem system, the difference in performance between the tandem and hybrid systems is significantly smaller than usually observed on this task. A log-linear model is then used to estimate system weights between these systems. Training the system weights yields additional gains over empirically set system weights when used for decoding. Furthermore, when used in a lattice rescoring fashion, further gains can be obtained.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2016 IEEE. |
Keywords: | Joint decoding; tandem system; hybrid system; log-linear model; structured SVM |
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; EP/I031022/1 Department of Defense U.S. Army Research Laboratory (DoD/ARL) W911NF-12- C-0012 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 12 Nov 2019 11:58 |
Last Modified: | 12 Nov 2019 11:58 |
Status: | Published |
Publisher: | IEEE |
Refereed: | Yes |
Identification Number: | 10.1109/icassp.2016.7472764 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:152831 |