Ragni, A. orcid.org/0000-0003-0634-4456, Wu, C., Gales, M.J.F. et al. (2 more authors) (2017) Stimulated training for automatic speech recognition and keyword search in limited resource conditions. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 05-09 Mar 2017, New Orleans, LA, USA. IEEE , pp. 4830-4834. ISBN 9781509041183
Abstract
Training neural network acoustic models on limited quantities of data is a challenging task. A number of techniques have been proposed to improve generalisation. This paper investigates one such technique called stimulated training. It enables standard criteria such as cross-entropy to enforce spatial constraints on activations originating from different units. Having different regions being active depending on the input unit may help network to discriminate better and as a consequence yield lower error rates. This paper investigates stimulated training for automatic speech recognition of a number of languages representing different families, alphabets, phone sets and vocabulary sizes. In particular, it looks at ensembles of stimulated networks to ensure that improved generalisation will withstand system combination effects. In order to assess stimulated training beyond 1-best transcription accuracy, this paper looks at keyword search as a proxy for assessing quality of lattices. Experiments are conducted on IARPA Babel program languages including the surprise language of OpenKWS 2016 competition.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2017 IEEE. |
Keywords: | limited resources; stimulated training; joint decoding; keyword search |
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: | 12 Nov 2019 16:01 |
Last Modified: | 12 Nov 2019 16:01 |
Published Version: | https://ieeexplore.ieee.org/abstract/document/7953... |
Status: | Published |
Publisher: | IEEE |
Refereed: | Yes |
Identification Number: | 10.1109/icassp.2017.7953074 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:152766 |