Skip to content

Publications

Detail of publication

Citation

Soutner, D. and Loose, Z. and Müller, L. and Pražák, A. : Neural Network Language Model with Cache . Lecture Notes in Computer Science, p. 528-534, 2012.

Abstract

In this paper we investigate whether a combination of statistical, neural network and cache language models can outperform a basic statistical model. These models have been developed, tested and exploited for a Czech spontaneous speech data, which is very different from common written Czech and is specified by a small set of the data available and high inflection of the words. As a baseline model we used a trigram model and after its training several cache models interpolated with the baseline model have been tested and measured on a perplexity. Finally, an evaluation of the model with the lowest perplexity has been performed on speech recordings of phone calls.

Detail of publication

Title: Neural Network Language Model with Cache
Author: Soutner, D. ; Loose, Z. ; Müller, L. ; Pražák, A.
Language: English
Date of publication: 1 Sep 2012
Year: 2012
Type of publication: Papers in proceedings of reviewed conferences
Series: Lecture Notes in Computer Science
Page: 528 - 534
DOI: 10.1007/978-3-642-32790-2_64
/ 2013-12-16 13:41:35 /

Keywords

neural networks, language modelling, automatic speech recognition

BibTeX

@ARTICLE{SoutnerD_2012_NeuralNetwork,
 author = {Soutner, D. and Loose, Z. and M\"{u}ller, L. and Pra\v{z}\'{a}k, A.},
 title = {Neural Network Language Model with Cache},
 year = {2012},
 pages = {528-534},
 series = {Lecture Notes in Computer Science},
 doi = {10.1007/978-3-642-32790-2_64},
 url = {http://www.kky.zcu.cz/en/publications/SoutnerD_2012_NeuralNetwork},
}