A Spectral Masking Approach to Noise-Robust Speech Recognition Using Deep Neural Networks

@article{Li2014ASM,
  title={A Spectral Masking Approach to Noise-Robust Speech Recognition Using Deep Neural Networks},
  author={Bo Li and Khe Chai Sim},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year={2014},
  volume={22},
  pages={1296-1305}
}
Improving the noise robustness of automatic speech recognition systems has been a challenging task for many years. Recently, it was found that Deep Neural Networks (DNNs) yield large performance gains over conventional GMM-HMM systems, when used in both hybrid and tandem systems. However, they are still far from the level of human expectations especially under adverse environments. Motivated by the separation-prior-to-recognition process of the human auditory system, we propose a robust… CONTINUE READING
Highly Cited
This paper has 37 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • Experimental results on benchmark Aurora2 and Aurora4 tasks demonstrated the effectiveness of our system, which yielded Word Error Rates (WERs) of 4.6% and 11.8% respectively.

Citations

Publications citing this paper.
Showing 1-10 of 29 extracted citations

Improvement of mask-based speech source separation using DNN

2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP) • 2016
View 4 Excerpts
Highly Influenced

Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018

Isolated Word Recognition with Audio Derivation and CNN

2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI) • 2017
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-6 of 6 references

An investigation of deep neural networks for noise robust speech recognition

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 5 Excerpts
Highly Influenced

A Fast Learning Algorithm for Deep Belief Nets

Neural Computation • 2006
View 5 Excerpts
Highly Influenced

Aurora working group: DSR front end LVCSR evaluation AU/384/02

N. Parihar, J. Picone
Inst. for Signal and Inf. Process, Mississippi State Univ., Tech. Rep, 2002. • 2002
View 11 Excerpts
Highly Influenced

Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2014
View 4 Excerpts
Highly Influenced

Ideal ratio mask estimation using deep neural networks for robust speech recognition

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…