Faculty of Information Technology, BUT

Publication Details

Empirical Evaluation and Combination of Advanced Language Modeling Techniques

MIKOLOV Tomáš, DEORAS Anoop, KOMBRINK Stefan, BURGET Lukáš and ČERNOCKÝ Jan. Empirical Evaluation and Combination of Advanced Language Modeling Techniques. In: Proceedings of Interspeech 2011. Florence: International Speech Communication Association, 2011, pp. 605-608. ISBN 978-1-61839-270-1. ISSN 1990-9772.
Czech title
Empirická evaluace a kombinace pokročilých technik jazykového modelování
Type
conference paper
Language
english
Authors
Mikolov Tomáš, Ing. (DCGM FIT BUT)
Deoras Anoop (JHU)
Kombrink Stefan, Dipl.-Inf -Ling (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, doc. Dr. Ing. (DCGM FIT BUT)
URL
Keywords
language modeling, neural networks, model combination, speech recognition
Abstract
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.
Annotation
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%.
Published
2011
Pages
605-608
Journal
Proceedings of Interspeech, vol. 2011, no. 8, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2011
Conference
Interspeech 2011, Florence Italy, IT
ISBN
978-1-61839-270-1
Publisher
International Speech Communication Association
Place
Florence, IT
BibTeX
@INPROCEEDINGS{FITPUB9759,
   author = "Tom\'{a}\v{s} Mikolov and Anoop Deoras and Stefan Kombrink and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   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 = "https://www.fit.vut.cz/research/publication/9759"
}
Back to top