Loading [a11y]/accessibility-menu.js
Extracting deep neural network bottleneck features using low-rank matrix factorization | IEEE Conference Publication | IEEE Xplore

Extracting deep neural network bottleneck features using low-rank matrix factorization


Abstract:

In this paper, we investigate the use of deep neural networks (DNNs) to generate a stacked bottleneck (SBN) feature representation for low-resource speech recognition. We...Show More

Abstract:

In this paper, we investigate the use of deep neural networks (DNNs) to generate a stacked bottleneck (SBN) feature representation for low-resource speech recognition. We examine different SBN extraction architectures, and incorporate low-rank matrix factorization in the final weight layer. Experiments on several low-resource languages demonstrate the effectiveness of the SBN configurations when compared to state-of-the-art hybrid DNN approaches.
Date of Conference: 04-09 May 2014
Date Added to IEEE Xplore: 14 July 2014
Electronic ISBN:978-1-4799-2893-4

ISSN Information:

Conference Location: Florence, Italy

References

References is not available for this document.