Improving speech recognition in reverberation using a room-aware deep neural network and multi-task learning

@article{Giri2015ImprovingSR,
  title={Improving speech recognition in reverberation using a room-aware deep neural network and multi-task learning},
  author={Ritwik Giri and Michael L. Seltzer and Jasha Droppo and Dong Yu},
  journal={2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2015},
  pages={5014-5018}
}
In this paper, we propose two approaches to improve deep neural network (DNN) acoustic models for speech recognition in reverberant environments. Both methods utilize auxiliary information in training the DNN but differ in the type of information and the manner in which it is used. The first method uses parallel training data for multi-task learning, in which the network is trained to perform both a primary senone classification task and a secondary feature enhancement task using a shared… CONTINUE READING
Highly Cited
This paper has 54 citations. REVIEW CITATIONS

From This Paper

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

Key Quantitative Results

  • The proposed approach obtained a word error rate of 7.8% on the SimData test set, which is lower than all reported systems using the same training data and evaluation conditions, and 27.5% on the mismatched RealData test set, which is lower than all but two systems.

Citations

Publications citing this paper.
Showing 1-10 of 34 extracted citations

Statistical Language and Speech Processing

Lecture Notes in Computer Science • 2018
View 5 Excerpts
Highly Influenced

Integrated DNN-based model adaptation technique for noise-robust speech recognition

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2017
View 4 Excerpts
Highly Influenced

Adaptive Permutation Invariant Training with Auxiliary Information for Monaural Multi-Talker Speech Recognition

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 1 Excerpt

Blind Reverberation Time Estimation Using a Convolutional Neural Network

2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC) • 2018
View 1 Excerpt

55 Citations

0102020152016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 55 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 16 references

Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2014
View 2 Excerpts

Neural networks for distant speech recognition

2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA) • 2014
View 1 Excerpt

An investigation of deep neural networks for noise robust speech recognition

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 1 Excerpt

Similar Papers

Loading similar papers…