Sorry, you need to enable JavaScript to visit this website.

CUED-RNNLM – An Open-Source Toolkit for Efficient Training and Evaluation of Recurrent Neural Network Language Models

Citation Author(s):
Xie Chen, Yanmin Qian, Xunying Liu, Mark Gales, Phil Woodland
Submitted by:
Xie Chen
Last updated:
1 April 2016 - 6:35am
Document Type:
Presentation Slides
Document Year:
2016
Event:
Presenters:
XIE CHEN
Paper Code:
ICASSP1601

Abstract

In recent years, recurrent neural network language models (RNNLMs) have become increasingly popular for a range of applications including speech recognition. However, the training of RNNLMs is computationally expensive, which limits the quantity of data, and size of network, that can be used. In order to fully exploit the power of RNNLMs, efficient training implementations are required. This paper introduces an open-source toolkit, the CUED-RNNLM toolkit, which supports efficient GPU-based training of RNNLMs. RNNLM training with a large number of word level output targets is supported, in contrast to existing tools which used class-based output-targets. Support fot N-best and lattice-based rescoring of both HTK and Kaldi format lattices is included. An example of building and evaluating RNNLMs with this toolkit is presented for a Kaldi based speech recognition system using the AMI corpus. All necessary resources including the source code, documentation and recipe are available online: http://mi.eng.cam.ac.uk/projects/cued-rnnlm/.

slides.pdf

PDF icon slides.pdf (695)
Media Folder: 
up
0 users have voted: