The language recognition evaluation (LRE) 2017 challenge comprises an open evaluation of the language identification (LID) task on a set of 14 languages/dialects. In this paper, we describe our submission to the LRE 2017 challenge fixed condition which consisted of developing various LID systems using i-vector based modeling. The front end processing is performed using deep neural network (DNN) based bottleneck features for i-vector modeling with a Gaussian mixture model (GMM) universal background model (UBM) approach. Several back-end systems consisting of support vector machines (SVMs) and deep neural network (DNN) models were used for the language/dialect classification. The submission system achieved significant improvements over the evaluation baseline system provided by NIST (relative improvements of more than 50% over the baseline). In the later part of the paper, we detail our post evaluation efforts to improve the language recognition system for short duration speech data using novel approaches of sequence modeling of segment i-vectors. The post evaluation efforts resulted in further improvements over the submitted system (relative improvements of about 22%). An error analysis is also presented which highlights the confusions and errors in the final system.
Cite as: Padi, B., Ramoji, S., Yeruva, V., Kumar, S., Ganapathy, S. (2018) The LEAP Language Recognition System for LRE 2017 Challenge - Improvements and Error Analysis . Proc. The Speaker and Language Recognition Workshop (Odyssey 2018), 31-38, doi: 10.21437/Odyssey.2018-5
@inproceedings{padi18_odyssey,
author={Bharat Padi and Shreyas Ramoji and Vaishnavi Yeruva and Satish Kumar and Sriram Ganapathy},
title={{The LEAP Language Recognition System for LRE 2017 Challenge - Improvements and Error Analysis }},
year=2018,
booktitle={Proc. The Speaker and Language Recognition Workshop (Odyssey 2018)},
pages={31--38},
doi={10.21437/Odyssey.2018-5}
}