Sciweavers

Share
ICASSP
2010
IEEE

Language recognition using deep-structured conditional random fields

8 years 11 months ago
Language recognition using deep-structured conditional random fields
We present a novel language identification technique using our recently developed deep-structured conditional random fields (CRFs). The deep-structured CRF is a multi-layer CRF model in which each higher layer’s input observation sequence consists of the lower layer’s observation sequence and the resulting lower layer’s frame-level marginal probabilities. In this paper we extend the original deep-structured CRF by allowing for distinct state representations at different layers and demonstrate its benefits. We propose an unsupervised algorithm to pre-train the intermediate layers by casting it as a multi-objective programming problem that is aimed at minimizing the average frame-level conditional entropy while maximizing the state occupation entropy. Empirical evaluation on a seven-language/dialect voice mail routing task showed that our approach can achieve a routing accuracy (RA) of 86.4% and average equal error rate (EER) of 6.6%. These results are significantly better than th...
Dong Yu, Shizhen Wang, Zahi Karam, Li Deng
Added 06 Dec 2010
Updated 06 Dec 2010
Type Conference
Year 2010
Where ICASSP
Authors Dong Yu, Shizhen Wang, Zahi Karam, Li Deng
Comments (0)
books