End-to-end DNN-CNN Classification for Language Identification

A defining problem in spoken language identification (LID) is how to design effective representations which allow features to be extracted that are specific to language information.

In this paper, a novel network is proposed and explored that models an effective representation using first and second-order statistics of features extracted from a well-trained phoneme-related DNN bottleneck network followed by a stack of CNN convolutional layers.

Evaluation with NIST LRE 2009 shows improved performance compared to current state-of-the-art systems, achieving over 33% and 20% relative equal error rate (EER) improvement for 3s and 10s utterances.