Conference paper

 
Kombrink, S., Mikolov, T., Karafiát, M., Burget, L.: Recurrent Neural Network based Language Modeling in Meeting Recognition, In: Proceedings of Interspeech 2011, Florence, IT, ISCA, 2011, p. 2877-2880, ISBN 978-1-61839-270-1, ISSN 1990-9772
Publication language:english
Original title:Recurrent Neural Network based Language Modeling in Meeting Recognition
Title (cs):Jazykový model založený na rekurentních neuronových sítích pro rozpoznávání řeči z meetingů
Pages:2877-2880
Proceedings:Proceedings of Interspeech 2011
Conference:Interspeech 2011
Place:Florence, IT
Year:2011
ISBN:978-1-61839-270-1
Journal:Proceedings of Interspeech, Vol. 2011, No. 8, FR
ISSN:1990-9772
Publisher:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/kombrink_interspeech2011_792.pdf [PDF]
Keywords
automatic speech recognition, language modeling, recurrent neural networks, rescoring, adaptation
Annotation
In this paper we recommend the use of RNN language models as easy mean to improve an existing LVCSR system, either by improving ngram models using data sampled from an RNN or by performing the proposed rescoring and adaptation postprocessing steps.
Abstract
We use recurrent neural network (RNN) based language models to improve the BUT English meeting recognizer. On the baseline setup using the original language models we decrease word error rate (WER) more than 1% absolute by n-best list rescoring and language model adaptation. When n-gram language models are trained on the same moderately sized data set as the RNN models, improvements are higher yielding a system which performs comparable to the baseline. A noticeable improvement was observed with unsupervised adaptation of RNN models. Furthermore, we examine the influence of word history on WER and show how to speed-up rescoring by caching common prefix strings.
BibTeX:
@INPROCEEDINGS{
   author = {Stefan Kombrink and Tomáš Mikolov and Martin Karafiát and
	Lukáš Burget},
   title = {Recurrent Neural Network based Language Modeling in Meeting
	Recognition},
   pages = {2877--2880},
   booktitle = {Proceedings of Interspeech 2011},
   journal = {Proceedings of Interspeech},
   volume = {2011},
   number = {8},
   year = {2011},
   location = {Florence, IT},
   publisher = {International Speech Communication Association},
   ISBN = {978-1-61839-270-1},
   ISSN = {1990-9772},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9760}
}