Recurrent neural network language models for keyword search

Conference Object
Change log
Chen, X 
Ragni, A 
Vasilakes, J 
Liu, X 

Recurrent neural network language models (RNNLMs) have becoming increasingly popular in many applications such as automatic speech recognition (ASR). Significant performance improvements in both perplexity and word error rate over standard n-gram LMs have been widely reported on ASR tasks. In contrast, published research on using RNNLMs for keyword search systems has been relatively limited. In this paper the application of RNNLMs for the IARPA Babel keyword search task is investigated. In order to supplement the limited acoustic transcription data, large amounts of web texts are also used in large vocabulary design and LM training. Various training criteria were then explored to improved RNNLMs' efficiency in both training and evaluation. Significant and consistent improvements on both keyword search and ASR tasks were obtained across all languages.

speech recognition, keyword search, language model, recurrent neural network
Journal Title
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Conference Name
The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing
Journal ISSN
Volume Title
IARPA (4912046943)
Xie Chen is supported by Toshiba Research Europe Ltd, Cambridge Research Lab. This work was supported by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Defense U. S. Army Research Laboratory (DoD/ARL) contract number W911NF-12-C-0012. The U. S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA, DoD/ARL, or the U. S. Government.