Publication Details
Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup
Mikolov Tomáš, Ing., Ph.D.
automatic speech recognition, language modeling, recurrent neural networks
This paper is on Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup.
In this paper we use recurrent neural network (RNN) based language models to improve our 2009 English meeting recognizer originated from the AMI/AMIDA project, which to date was the most advanced speech recognition setup of the Speech@FIT. On the baseline setup using the original language models we decrease word error rate (WER) from 20.3% to 19.1%. When language models in the system are replaced by models trained on a tiny subset of the original language model data, WER drops from 22.2% to 20.4%. Adding data sampled from two RNN models for language model training improves the overall system, yielding the performance of the original baseline (20.2%).
@inproceedings{BUT91275,
author="Stefan {Kombrink} and Tomáš {Mikolov}",
title="Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup",
booktitle="Proceedings of the 17th Conference STUDENT EEICT 2011",
year="2011",
series="Volume 3",
pages="527--531",
publisher="Brno University of Technology",
address="Brno",
isbn="978-80-214-4273-3",
url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/kombrink_eeict2011_volume3_527.pdf"
}