Conference paper

 
Mikolov, T., Deoras, A., Kombrink, S., Burget, L., Černocký, J.: Empirical Evaluation and Combination of Advanced Language Modeling Techniques, In: Proceedings of Interspeech 2011, Florence, IT, ISCA, 2011, p. 605-608, ISBN 978-1-61839-270-1, ISSN 1990-9772
Publication language:english
Original title:Empirical Evaluation and Combination of Advanced Language Modeling Techniques
Title (cs):Empirická evaluace a kombinace pokročilých technik jazykového modelování
Pages:605-608
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/mikolov_interspeech2011_666.pdf [PDF]
Keywords
language modeling, neural networks, model combination, speech recognition
Annotation
This paper is on Empirical Evaluation and Combination of Advanced Language Modeling Techniques. Our work is the first attempt to combine many advanced language modeling techniques.
Abstract
We present results obtained with several advanced language modeling techniques, including class based model, cache model, maximum entropy model, structured language model, random forest language model and several types of neural network based language models. We show results obtained after combining all these models by using linear interpolation. We conclude that for both small and moderately sized tasks, we obtain new state of the art results with combination of models, that is significantly better than performance of any individual model. Obtained perplexity reductions against Good-Turing trigram baseline are over 50% and against modified Kneser-Ney smoothed 5-gram over 40%.
BibTeX:
@INPROCEEDINGS{
   author = {Tomáš Mikolov and Anoop Deoras and Stefan Kombrink and Lukáš
	Burget and Jan Černocký},
   title = {Empirical Evaluation and Combination of Advanced Language
	Modeling Techniques},
   pages = {605--608},
   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=9759}
}