Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

END-TO-END HIERARCHICAL LANGUAGE IDENTIFICATION SYSTEM

Abstract: 

Recently, hierarchical language identification systems have shown significant improvement over single level systems in both closed and open set language identification tasks. However, developing such a system requires the features and classifier selection at each node in the hierarchical structure to be hand crafted. Motivated by the superior ability of end-to-end deep neural network architecture to jointly optimize the feature extraction and classification process, we propose a novel approach developing an end-to-end hierarchical language identification system. The proposed approach also demonstrates the in-built ability of the end-to-end hierarchical structure training that enables an out-of-set language model, without using any additional out-of-set language training data. Experiments are conducted on the NIST LRE 2015 data set. The overall results show relative improvements of 18.6% and 27.3% in terms of Cavg in closed and open set tasks over the corresponding baseline systems.

up
0 users have voted:

Paper Details

Authors:
Saad Irtza, Vidhasaharan Sethu, Eliathamby Ambikairajah, Haizhou Li
Submitted On:
12 April 2018 - 9:20pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Ting Dang
Paper Code:
SP-P4
Document Year:
2018
Cite

Document Files

Poster

(156)

Subscribe

[1] Saad Irtza, Vidhasaharan Sethu, Eliathamby Ambikairajah, Haizhou Li, "END-TO-END HIERARCHICAL LANGUAGE IDENTIFICATION SYSTEM", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2538. Accessed: Oct. 18, 2019.
@article{2538-18,
url = {http://sigport.org/2538},
author = {Saad Irtza; Vidhasaharan Sethu; Eliathamby Ambikairajah; Haizhou Li },
publisher = {IEEE SigPort},
title = {END-TO-END HIERARCHICAL LANGUAGE IDENTIFICATION SYSTEM},
year = {2018} }
TY - EJOUR
T1 - END-TO-END HIERARCHICAL LANGUAGE IDENTIFICATION SYSTEM
AU - Saad Irtza; Vidhasaharan Sethu; Eliathamby Ambikairajah; Haizhou Li
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2538
ER -
Saad Irtza, Vidhasaharan Sethu, Eliathamby Ambikairajah, Haizhou Li. (2018). END-TO-END HIERARCHICAL LANGUAGE IDENTIFICATION SYSTEM. IEEE SigPort. http://sigport.org/2538
Saad Irtza, Vidhasaharan Sethu, Eliathamby Ambikairajah, Haizhou Li, 2018. END-TO-END HIERARCHICAL LANGUAGE IDENTIFICATION SYSTEM. Available at: http://sigport.org/2538.
Saad Irtza, Vidhasaharan Sethu, Eliathamby Ambikairajah, Haizhou Li. (2018). "END-TO-END HIERARCHICAL LANGUAGE IDENTIFICATION SYSTEM." Web.
1. Saad Irtza, Vidhasaharan Sethu, Eliathamby Ambikairajah, Haizhou Li. END-TO-END HIERARCHICAL LANGUAGE IDENTIFICATION SYSTEM [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2538