I-vector features and deep neural network modeling for language recognition | Zendy

Wei Wang | Zendy; Wenjie Song | Zendy; Chen Chen | Zendy; Zhaoxin Zhang | Zendy; Yi Xin | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

I-vector features and deep neural network modeling for language recognition

Author(s) -

Wei Wang,

Wenjie Song,

Chen Chen,

Zhaoxin Zhang,

Yi Xin

Publication year - 2019

Publication title -

procedia computer science

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.334

H-Index - 76

ISSN - 1877-0509

DOI - 10.1016/j.procs.2019.01.181

Subject(s) - overfitting , computer science , nist , dropout (neural networks) , artificial intelligence , task (project management) , baseline (sea) , artificial neural network , feature (linguistics) , feature vector , language model , support vector machine , machine learning , pattern recognition (psychology) , deep learning , deep neural networks , speech recognition , linguistics , oceanography , philosophy , management , economics , geology

We combine Total Variability algorithm with Deep Learning theory to complete the language recognition task. The Total Variability algorithm can compensate for the influence of differences in channels and speakers among various languages, while deep learning methods have a stronger ability of nonlinear modeling compared with traditional statistical models. In this paper, I-vector feature is extracted using Total Variability algorithm, and model training is established using fully connected neural network. Meanwhile, the dropout strategy is also used to suppress overfitting. The experimental results show that the new system outperforms the baseline system on the NIST LRE 2007 corpus.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research