This paper proposes two novel frontends for robust language identification (LID) using a convolutional neural network (CNN) trained for automatic speech recognition (ASR). In the CNN/i-vector frontend, the CNN is used to obtain the posterior probabilities for i-vector training and extraction instead of a universal background model (UBM). The CNN/posterior frontend is somewhat similar to a phonetic system in that the occupation counts of (tied) triphone states (senones) given by the CNN are used for classification. They are compressed to a low dimensional vector using probabilistic principal component analysis (PPCA). Evaluated on heavily degraded speech data, the proposed front ends provide significant improvements of up to 50% on average equal error rate compared to a UBM/i-vector baseline. Moreover, the proposed frontends are complementary and give significant gains of up to 20% relative to the best single system when combined.
Cite as: Lei, Y., Ferrer, L., Lawson, A., McLaren, M., Scheffer, N. (2014) Application of Convolutional Neural Networks to Language Identification in Noisy Conditions. Proc. The Speaker and Language Recognition Workshop (Odyssey 2014), 287-292, doi: 10.21437/Odyssey.2014-43
@inproceedings{lei14b_odyssey,
author={Yun Lei and Luciana Ferrer and Aaron Lawson and Mitchell McLaren and Nicolas Scheffer},
title={{Application of Convolutional Neural Networks to Language Identification in Noisy Conditions}},
year=2014,
booktitle={Proc. The Speaker and Language Recognition Workshop (Odyssey 2014)},
pages={287--292},
doi={10.21437/Odyssey.2014-43}
}