Publication Details

Recurrent Neural Network based Language Modeling in Meeting Recognition

KOMBRINK Stefan, MIKOLOV Tomáš, KARAFIÁT Martin and BURGET Lukáš. Recurrent Neural Network based Language Modeling in Meeting Recognition. In: Proceedings of Interspeech 2011. Florence: International Speech Communication Association, 2011, pp. 2877-2880. ISBN 978-1-61839-270-1. ISSN 1990-9772.
Czech title
Jazykový model založený na rekurentních neuronových sítích pro rozpoznávání řeči z meetingů
Type
conference paper
Language
english
Authors
URL
Keywords
automatic speech recognition, language modeling, recurrent neural networks, rescoring, adaptation
Abstract
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.
Annotation
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.
Published
2011
Pages
2877-2880
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{FITPUB9760,
   author = "Stefan Kombrink and Tom\'{a}\v{s} Mikolov and Martin Karafi\'{a}t and Luk\'{a}\v{s} 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 = "https://www.fit.vut.cz/research/publication/9760"
}
Back to top