Doulaty Bashkand, M., Saz, O. and Hain, T. (2015) Unsupervised Domain Discovery Using Latent Dirichlet Allocation for Acoustic Modelling in Speech Recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 16th Annual Conference of the International Speech Communication Association, 06-10 Sep 2015, Dresden, Germany. ISCA (International Speech Communication Association) , pp. 3640-3644.
Abstract
Speech recognition systems are often highly domain dependent, a fact widely reported in the literature. However the concept of domain is complex and not bound to clear criteria. Hence it is often not evident if data should be considered to be out-of-domain. While both acoustic and language models can be domain specific, work in this paper concentrates on acoustic modelling. We present a novel method to perform unsupervised discovery of domains using Latent Dirichlet Allocation (LDA) modelling. Here a set of hidden domains is assumed to exist in the data, whereby each audio segment can be considered to be a weighted mixture of domain properties. The classification of audio segments into domains allows the creation of domain specific acoustic models for automatic speech recognition. Experiments are conducted on a dataset of diverse speech data covering speech from radio and TV broadcasts, telephone conversations, meetings, lectures and read speech, with a joint training set of 60 hours and a test set of 6 hours. Maximum A Posteriori (MAP) adaptation to LDA based domains was shown to yield relative Word Error Rate (WER) improvements of up to 16% relative, compared to pooled training, and up to 10%, compared with models adapted with human-labelled prior domain knowledge.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2015 ISCA. Reproduced in accordance with the publisher's self-archiving policy. |
Keywords: | domain discovery; latent dirichlet allocation; adaptation; speech recognition |
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: | 04 Mar 2016 15:15 |
Last Modified: | 19 Dec 2022 13:32 |
Published Version: | http://www.isca-speech.org/archive/interspeech_201... |
Status: | Published |
Publisher: | ISCA (International Speech Communication Association) |
Refereed: | Yes |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:92452 |