Language Recognition via Sparse Coding

Youngjune L. Gwon, William M. Campbell, Douglas E. Sturim, H.T. Kung


Spoken language recognition requires a series of signal processing steps and learning algorithms to model distinguishing characteristics of different languages. In this paper, we present a sparse discriminative feature learning framework for language recognition. We use sparse coding, an unsupervised method, to compute efficient representations for spectral features from a speech utterance while learning basis vectors for language models. Differentiated from existing approaches in sparse representation classification, we introduce a maximum a posteriori (MAP) adaptation scheme based on online learning that further optimizes the discriminative quality of sparse-coded speech features. We empirically validate the effectiveness of our approach using the NIST LRE 2015 dataset.


DOI: 10.21437/Interspeech.2016-881

Cite as

Gwon, Y.L., Campbell, W.M., Sturim, D.E., Kung, H. (2016) Language Recognition via Sparse Coding. Proc. Interspeech 2016, 2920-2924.

Bibtex
@inproceedings{Gwon+2016,
author={Youngjune L. Gwon and William M. Campbell and Douglas E. Sturim and H.T. Kung},
title={Language Recognition via Sparse Coding},
year=2016,
booktitle={Interspeech 2016},
doi={10.21437/Interspeech.2016-881},
url={http://dx.doi.org/10.21437/Interspeech.2016-881},
pages={2920--2924}
}