CUED Publications database

Investigating bidirectional recurrent neural network language models for speech recognition

Chen, X and Ragni, A and Liu, X and Gales, MJF (2017) Investigating bidirectional recurrent neural network language models for speech recognition. In: UNSPECIFIED pp. 269-273..

Full text not available from this repository.

Abstract

Recurrent neural network language models (RNNLMs) are powerful language modeling techniques. Significant performance improvements have been reported in a range of tasks including speech recognition compared to n-gram language models. Conventional n-gram and neural network language models are trained to predict the probability of the next word given its preceding context history. In contrast, bidirectional recurrent neural network based language models consider the context from future words as well. This complicates the inference process, but has theoretical benefits for tasks such as speech recognition as additional context information can be used. However to date, very limited or no gains in speech recognition performance have been reported with this form of model. This paper examines the issues of training bidirectional recurrent neural network language models (bi-RNNLMs) for speech recognition. A bi-RNNLM probability smoothing technique is proposed, that addresses the very sharp posteriors that are often observed in these models. The performance of the bi-RNNLMs is evaluated on three speech recognition tasks: broadcast news; meeting transcription (AMI); and low-resource systems (Babel data). On all tasks gains are observed by applying the smoothing technique to the bi-RNNLM. In addition consistent performance gains can be obtained by combining bi-RNNLMs with n-gram and uni-directional RNNLMs.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 19 Jan 2018 20:14
Last Modified: 13 Apr 2021 10:34
DOI: doi:10.21437/Interspeech.2017-513