CUED Publications database

Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition

Chen, X and Liu, X and Wang, Y and Gales, MJF and Woodland, PC (2016) Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition. IEEE/ACM Transactions on Audio Speech and Language Processing, 24. pp. 2146-2157. ISSN 2329-9290

Full text not available from this repository.

Abstract

© 2014 IEEE. Recurrent neural network language models (RNNLMs) are becoming increasingly popular for a range of applications including automatic speech recognition. An important issue that limits their possible application areas is the computational cost incurred in training and evaluation. This paper describes a series of new efficiency improving approaches that allows RNNLMs to be more efficiently trained on graphics processing units (GPUs) and evaluated on CPUs. First, a modified RNNLM architecture with a nonclass-based, full output layer structure (F-RNNLM) is proposed. This modified architecture facilitates a novel spliced sentence bunch mode parallelization of F-RNNLM training using large quantities of data on a GPU. Second, two efficient RNNLM training criteria based on variance regularization and noise contrastive estimation are explored to specifically reduce the computation associated with the RNNLM output layer softmax normalisation term. Finally, a pipelined training algorithm utilizing multiple GPUs is also used to further improve the training speed. Initially, RNNLMs were trained on a moderate dataset with 20M words from a large vocabulary conversational telephone speech recognition task. The training time of RNNLM is reduced by up to a factor of 53 on a single GPU over the standard CPU-based RNNLM toolkit. A 56 times speed up in test time evaluation on a CPU was obtained over the baseline F-RNNLMs. Consistent improvements in both recognition accuracy and perplexity were also obtained over C-RNNLMs. Experiments on Google's one billion corpus also reveals that the training of RNNLM scales well.

Item Type: Article
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:00
Last Modified: 21 Sep 2017 01:38
DOI: