Deena, S., Ng, R.W.M., Madhyashta, P. et al. (2 more authors) (2017) Semi-supervised adaptation of RNNLMs by fine-tuning with domain-specific auxiliary features. In: Proceedings of INTERSPEECH 2017: Conference of the International Speech Communication Association. INTERSPEECH 2017: Conference of the International Speech Communication Association, 20-24 Aug 2017, Stockholm. ISCA , pp. 2715-2719.
Abstract
Recurrent neural network language models (RNNLMs) can be augmented with auxiliary features, which can provide an extra modality on top of the words. It has been found that RNNLMs perform best when trained on a large corpus of generic text and then fine-tuned on text corresponding to the sub-domain for which it is to be applied. However, in many cases the auxiliary features are available for the sub-domain text but not for the generic text. In such cases, semi-supervised techniques can be used to infer such features for the generic text data such that the RNNLM can be trained and then fine-tuned on the available in-domain data with corresponding auxiliary features.
In this paper, several novel approaches are investigated for dealing with the semi-supervised adaptation of RNNLMs with auxiliary features as input. These approaches include: using zero features during training to mask the weights of the feature sub-network; adding the feature sub-network only at the time of fine-tuning; deriving the features using a parametric model and; back-propagating to infer the features on the generic text. These approaches are investigated and results are reported both in terms of PPL and WER on a multi-genre broadcast ASR task.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2017 ISCA. Reproduced in accordance with the publisher's self-archiving policy. |
Keywords: | RNNLM; Semi-supervised Adaptation; LDA topic models |
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: | 09 Jun 2017 11:10 |
Last Modified: | 19 Dec 2022 13:36 |
Published Version: | https://doi.org/10.21437/Interspeech.2017-1598 |
Status: | Published |
Publisher: | ISCA |
Refereed: | Yes |
Identification Number: | 10.21437/Interspeech.2017-1598 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:117472 |