Paper Info
Title
Improving Of Open-Set Language Identification By Using Deep Svm And Thresholding Functions
Abstract
State-of-the-art language identification (LID) systems are based on an iVector feature extractor front-end followed by a multi-class recognition back-end. Identification accuracy degrades considerably when LID systems face open-set languages. As compared to in-set identification task, the open-set task is adequate to mimic the real challenge of language identification. In this paper, we propose an approach to the problem of out of-set (OOS) data detection in the context of open-set language identification with zero-knowledge for OOS languages. The main feature of this study is the emphasis on the in-set (target) language identification, on the one hand, and on OOS language detection, on the other hand. Accordingly, we propose a deep SVM based LID back-end system to improve the target languages identification. Along with that, we define three OOS thresholding formulations. These formulations are used to decide whether the speech segment is a target or OOS language. The experimental results demonstrate the effectiveness of the deep SVM back-end system as compared to state-of-the-art techniques. Besides that, the thresholding functions perfectly detect and reject the OOS data. A relative decrease of 6% in Equal Error Rate (EER) is reported over classical OOS detection methods, in discriminating target and OOS languages.
Year
DOI
Venue
2017
10.1109/AICCSA.2017.119
2017 IEEE/ACS 14TH INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS AND APPLICATIONS (AICCSA)
Field
DocType
ISSN
Kernel (linear algebra),Data modeling,Pattern recognition,Task analysis,Computer science,Support vector machine,Word error rate,Real-time computing,NIST,Language identification,Artificial intelligence,Thresholding
Conference
2161-5322
Citations 
PageRank 
References 
0
0.34
0
Authors
3
Name
Order
Citations
PageRank
ilyes rebai1133.65
Benayed, Y.211.38
Walid Mahdi311625.49