Collaborated feature supervector and collaborated language model for phonotactic language recognition
by Wei-Wei Liu; Guo-Chun Li; Cun-Xue Zhang; Tai-Qing Dong; Jian-Hua Zhou; Yan-Miao Song; Jian-Zhong Liu; Zhao Peng; Yu-Bin Huang; Jian-Feng Tong; Jing-Fang Lu; Xing-Hua He; Yu-Jian Tang; Fu-Qiang Yuan; Bin Guo; Lei Gao
International Journal of Hybrid Intelligence (IJHI), Vol. 1, No. 4, 2019

Abstract: The now-acknowledged vulnerabilities of phonotactic language recognition (PLR) technology to long-term contexts have spawned interests to develop many methods to overcome it. In this paper an approach to build a collaborated feature supervector (CFS) built with binary decision tree feature and N-gram feature is proposed, and a collaborated language model (CLM) is introduced, which used to applied to deal with the problems of phonotactic language identification tasks, such as weak to handling long-term contexts and an exponential growth of the number of the parameters in the processing of modelling. Experiments are carried out on the database of National Institute of Standards and Technology Language Recognition Evaluation 2009 (NIST LRE 2009). The experimental results have confirmed that phonotactic language recognition system using the collaborated language model yields 1.07%, 2.68%, 13.48% in equal error rate (EER), which means 8.54%, 12.70% and 4.60% relative reduction for 30 s, 10 s, 3 s compared to the baseline system, respectively.

Online publication date: Mon, 20-Apr-2020

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Hybrid Intelligence (IJHI):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com