Empirical study of neural network language models for Arabic speech recognition

In this paper we investigate the use of neural network language models for Arabic speech recognition. By using a distributed representation of words, the neural network model allows for more robust generalization and is better able to fight the data sparseness problem. We investigate different confi...

Full description

Saved in:
Bibliographic Details
Published in2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) pp. 147 - 152
Main Authors Emami, A., Mangu, L.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2007
Subjects
Broadcasting
History
Language Modeling
Natural languages
Neural networks
Polynomials
Probability
Robustness
Smoothing methods
Speech recognition
Vocabulary
Online AccessGet full text

Cover

More Information
Summary:In this paper we investigate the use of neural network language models for Arabic speech recognition. By using a distributed representation of words, the neural network model allows for more robust generalization and is better able to fight the data sparseness problem. We investigate different configurations of the neural probabilistic model, experimenting with such parameters as N-gram order, output vocabulary, normalization method, and model size and parameters. Experiments were carried out on Arabic broadcast news and broadcast conversations data and the optimized neural network language models showed significant improvements over the baseline N-gram model.
ISBN:9781424417452
1424417457
DOI:10.1109/ASRU.2007.4430100