Conference paper

KOMBRINK, S. and MIKOLOV, T.. Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup. In: Proceedings of the 17th Conference STUDENT EEICT 2011. Brno: Brno University of Technology, 2011, pp. 527-531. ISBN 978-80-214-4273-3.
Publication language:english
Original title:Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup
Title (cs):Jazykové modelování založené na rekurentních neuronových sítích aplikované na Brno AMI/AMIDA 2009 setup pro rozpoznávání meetingů
Pages:527-531
Proceedings:Proceedings of the 17th Conference STUDENT EEICT 2011
Conference:Student EEICT 2011
Series:Volume 3
Place:Brno, CZ
Year:2011
ISBN:978-80-214-4273-3
Publisher:Brno University of Technology
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/kombrink_eeict2011_volume3_527.pdf [PDF]
Keywords
automatic speech recognition, language modeling, recurrent neural networks
Annotation
This paper is on Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup.
Abstract
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%).
BibTeX:
@INPROCEEDINGS{
   author = {Stefan Kombrink and Tomáš Mikolov},
   title = {Recurrent Neural Network Language Modeling Applied to the
	Brno AMI/AMIDA 2009 Meeting Recognizer Setup},
   pages = {527--531},
   booktitle = {Proceedings of the 17th Conference STUDENT EEICT 2011},
   series = {Volume 3},
   year = {2011},
   location = {Brno, CZ},
   publisher = {Brno University of Technology},
   ISBN = {978-80-214-4273-3},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en?id=9691}
}

Your IPv4 address: 54.161.192.61
Switch to IPv6 connection

DNSSEC [dnssec]