Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)

<Previous Article In Volume
Next Article In Volume>

Discriminative Language Model With Part-of-speech for Mandarin Large Vocabulary Continuous Speech Recognition System

Authors
Yujing Si, Zhen Zhang, Qingqing Zhang, Jielin Pan, Yonghong Yan
Corresponding Author
Yujing Si
Available Online March 2013.
DOI
10.2991/iccsee.2013.244How to use a DOI?
Keywords
speech recognition, language model, DLM, POS
Abstract

Statistical language model, trained by a large number of text corpus, is an integral component in many speech and natural language model processing systems, such as speech recognition and machine translation. It is a probabilistic model which describes the distribution pattern of natural language. Over the last few decades, N-gram language model (LM) is the most popular technique since it is simple and effective. However, the training of the N-gram language model is based on the maximum likelihood rule resulting in suboptimal output in speech recognition systems. In this paper, a discriminative training based language model (DLM) which directly focused on minimizing speech recognition word error rate (WER) was employed to improve the performance of speech recognition system. In particular, the part-of-speech (POS) feature was used to train DLM as well as the n-gram features. Experimental results showed that DLM with n-gram features gave 1% absolute reduction in word error rate (WER). Combining n-gram features with POS feature, DLM could obtain another 0.4% absolute reduction in WER.

Copyright
© 2013, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
Series
Advances in Intelligent Systems Research
Publication Date
March 2013
ISBN
10.2991/iccsee.2013.244
ISSN
1951-6851
DOI
10.2991/iccsee.2013.244How to use a DOI?
Copyright
© 2013, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

risenwbib
TY  - CONF
AU  - Yujing Si
AU  - Zhen Zhang
AU  - Qingqing Zhang
AU  - Jielin Pan
AU  - Yonghong Yan
PY  - 2013/03
DA  - 2013/03
TI  - Discriminative Language Model With Part-of-speech for Mandarin Large Vocabulary Continuous Speech Recognition System
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 970
EP  - 973
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.244
DO  - 10.2991/iccsee.2013.244
ID  - Si2013/03
ER  -