A Feature Compensation Approach Using High-Order Vector Taylor Series Approximation of an Explicit Distortion Model for Noisy Speech Recognition

@article{Du2008AFC,
  title={A Feature Compensation Approach Using High-Order Vector Taylor Series Approximation of an Explicit Distortion Model for Noisy Speech Recognition},
  author={Jun Du and Qiang Huo},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2008},
  volume={19},
  pages={2285-2293}
}
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 both additive noises and convolutional distortions, and minimum mean squared error (MMSE) estimation of clean speech are derived. Experimental results on Aurora2 and Aurora4 benchmark databases, where the modeling assumption of the distortion… CONTINUE READING
Highly Cited
This paper has 32 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 26 extracted citations

Bayesian feature enhancement using a mixture of unscented transformation for uncertainty decoding of noisy speech

2009 IEEE International Conference on Acoustics, Speech and Signal Processing • 2009
View 7 Excerpts
Highly Influenced

Assistive system for physically disabled people using gesture recognition

2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP) • 2017

VTS feature compensation based on two-layer GMM structure for robust speech recognition

2016 8th International Conference on Wireless Communications & Signal Processing (WCSP) • 2016
View 1 Excerpt

A novel static parameter calculation method for model compensation

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 1 Excerpt

Nonparametric Uncertainty Estimation and Propagation for Noise Robust ASR

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2015

On using heterogeneous data for vehicle-based speech recognition: A DNN-based approach

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 1 Excerpt

An Improved VTS Feature Compensation using Mixture Models of Distortion and IVN Training for Noisy Speech Recognition

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2014
View 10 Excerpts

An Overview of Noise-Robust Automatic Speech Recognition

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2014
View 2 Excerpts

Model Adaptation Algorithm Based on Central Subband Regression for Robust Speech Recognition

2014 Seventh International Symposium on Computational Intelligence and Design • 2014
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 10 references

Evaluation of a feature compensation approach using high - order vector Taylor series approximation of an explicit distortion model on Aurora 2 , Aurora 3 , and Aurora 4 tasks

Y. Hu
Proc . ISCSLP • 2008

Robust Automatic Speech Recognition in Time- Varying Environemnts, Ph.D

V. Stouten
2006
View 2 Excerpts

The design of Wall Street Journal - based CSR corpus

J. Baker
2002

Statistical linear approximation for environment compensation

IEEE Signal Processing Letters • 1998
View 2 Excerpts

Similar Papers

Loading similar papers…