ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

A feature compensation approach using high-order vector taylor series approximation of an explicit distortion model for noisy speech recognition

Jun Du, Qiang Huo

This paper presents a new feature compensation approach to noisy speech recognition by using high-order vector Taylor series (HOVTS) approximation of an explicit model of environmental distortions. Formulations for maximum likelihood (ML) estimation of noise model parameters and minimum mean-squared error (MMSE) estimation of clean speech are derived. Experimental results on Aurora2 database demonstrate that the proposed approach achieves consistently significant improvement in recognition accuracy compared to traditional first-order VTS based feature compensation approach.


doi: 10.21437/Interspeech.2008-302

Cite as: Du, J., Huo, Q. (2008) A feature compensation approach using high-order vector taylor series approximation of an explicit distortion model for noisy speech recognition. Proc. Interspeech 2008, 1257-1260, doi: 10.21437/Interspeech.2008-302

@inproceedings{du08b_interspeech,
  author={Jun Du and Qiang Huo},
  title={{A feature compensation approach using high-order vector taylor series approximation of an explicit distortion model for noisy speech recognition}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={1257--1260},
  doi={10.21437/Interspeech.2008-302}
}