Deena, S., Hasan, M., Doulaty, M. et al. (2 more authors) (2016) Combining feature and model-based adaptation of RNNLMs for multi-genre broadcast speech recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Interspeech 2016, 08-12 Sep 2016, San Francisco, USA. , pp. 2343-2347.
Abstract
Recurrent neural network language models (RNNLMs) have consistently outperformed n-gram language models when used in automatic speech recognition (ASR). This is because RNNLMs provide robust parameter estimation through the use of a continuous-space representation of words, and can generally model longer context dependencies than n-grams. The adaptation of RNNLMs to new domains remains an active research area and the two main approaches are: feature-based adaptation, where the input to the RNNLM is augmented with auxiliary features; and model-based adaptation, which includes model fine-tuning and introduction of adaptation layer(s) in the network. This paper explores the properties of both types of adaptation on multi-genre broadcast speech recognition. Two hybrid adaptation techniques are proposed, namely the finetuning of feature-based RNNLMs and the use of a feature-based adaptation layer. A method for the semi-supervised adaptation of RNNLMs, using topic model-based genre classification, is also presented and investigated. The gains obtained with RNNLM adaptation on a system trained on 700h. of speech are consistent using both RNNLMs trained on a small (10Mwords) and large set (660M words), with 10% perplexity and 2% word error rate improvements on a 28:3h. test set.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2016 ISCA. This is an author produced version of a paper subsequently published in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | RNNLM; LM adaptation; multi-domain ASR |
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: | 14 Dec 2016 15:31 |
Last Modified: | 19 Dec 2022 13:35 |
Published Version: | http://doi.org/10.21437/Interspeech.2016-480 |
Status: | Published |
Refereed: | Yes |
Identification Number: | 10.21437/Interspeech.2016-480 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:109282 |