In our previous work, a new feature compensation approach to robust speech recognition was proposed by using high-order vector Taylor series (HOVTS) approximation of an explicit model of distortions caused by additive noises, and evaluation results were reported on Aurora2 database. This paper extends the above approach to deal with both additive noises and convolutional distortions, and reports evaluation results on Aurora2, Aurora3, and Aurora4 tasks. Index Terms— robust speech recognition, feature compensation, vector Taylor series, distortion model.
Cite as: Du, J., Huo, Q., Hu, Y. (2008) Evaluation of A Feature Compensation Approach Using High-order Vector Taylor Series Approximation of An Explicit Distortion Model on Aurora2, Aurora3, and Aurora4 Tasks. Proc. International Symposium on Chinese Spoken Language Processing, 81-84
@inproceedings{du08_iscslp,
author={Jun Du and Qiang Huo and Yu Hu},
title={{Evaluation of A Feature Compensation Approach Using High-order Vector Taylor Series Approximation of An Explicit Distortion Model on Aurora2, Aurora3, and Aurora4 Tasks}},
year=2008,
booktitle={Proc. International Symposium on Chinese Spoken Language Processing},
pages={81--84}
}