KU-ISPL Speaker Recognition Systems under Language mismatch condition for NIST 2016 Speaker Recognition Evaluation

Korea University Intelligent Signal Processing Lab. (KU-ISPL) developed speaker recognition system for SRE16 fixed training condition. Data for evaluation trials are collected from outside North America, spoken in Tagalog and Cantonese while training data only is spoken English. Thus, main issue for...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-02
Main Authors: Shon, Suwon, Ko, Hanseok
Format: Article
Language:English
Subjects:
Clustering
Language
Signal processing
Speech recognition
State vectors
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Korea University Intelligent Signal Processing Lab. (KU-ISPL) developed speaker recognition system for SRE16 fixed training condition. Data for evaluation trials are collected from outside North America, spoken in Tagalog and Cantonese while training data only is spoken English. Thus, main issue for SRE16 is compensating the discrepancy between different languages. As development dataset which is spoken in Cebuano and Mandarin, we could prepare the evaluation trials through preliminary experiments to compensate the language mismatched condition. Our team developed 4 different approaches to extract i-vectors and applied state-of-the-art techniques as backend. To compensate language mismatch, we investigated and endeavored unique method such as unsupervised language clustering, inter language variability compensation and gender/language dependent score normalization.
ISSN:2331-8422