Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition

@article{AbdelHamid2012ApplyingCN,
  title={Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition},
  author={Ossama Abdel-Hamid and Abdel-rahman Mohamed and Hui Jiang and Gerald Penn},
  journal={2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2012},
  pages={4277-4280}
}
Convolutional Neural Networks (CNN) have showed success in achieving translation invariance for many image processing tasks. The success is largely attributed to the use of local filtering and max-pooling in the CNN architecture. In this paper, we propose to apply CNN to speech recognition within the framework of hybrid NN-HMM model. We propose to use local filtering and max-pooling in frequency domain to normalize speaker variance to achieve higher multi-speaker speech recognition performance… CONTINUE READING
Highly Influential
This paper has highly influenced 35 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 545 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 372 extracted citations

Convolutional neural network bottleneck features for bi-directional generalized variable parameter HMMs

2016 IEEE International Conference on Information and Automation (ICIA) • 2016
View 9 Excerpts
Highly Influenced

Convolutional deep maxout networks for phone recognition

INTERSPEECH • 2014
View 18 Excerpts
Highly Influenced

Convolutional deep rectifier neural nets for phone recognition

INTERSPEECH • 2013
View 7 Excerpts
Highly Influenced

Recent advances in deep learning for speech research at Microsoft

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

Comparison on Neural Network based acoustic model in Mongolian speech recognition

2016 International Conference on Asian Language Processing (IALP) • 2016
View 10 Excerpts
Highly Influenced

End-to-End Speech Recognition Models

View 6 Excerpts
Highly Influenced

Acoustic modeling using auditory model features and Convolutional neural Network

2015 International Conference on Power, Instrumentation, Control and Computing (PICC) • 2015
View 9 Excerpts
Highly Influenced

Combination of two-dimensional cochleogram and spectrogram features for deep learning-based ASR

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 6 Excerpts
Highly Influenced

545 Citations

050100'12'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 545 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Acoustic Modeling Using Deep Belief Networks

IEEE Transactions on Audio, Speech, and Language Processing • 2012
View 4 Excerpts

Making Deep Belief Networks effective for large vocabulary continuous speech recognition

2011 IEEE Workshop on Automatic Speech Recognition & Understanding • 2011
View 1 Excerpt

Learning methods for generic object recognition with invariance to pose and lighting

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. • 2004

Experiments in vocal tract normalization

A. Andreou, T. Kamm, J. Cohen
Proc. the CAIP Workshop: Frontiers in Speech Recognition II, 1994. • 1994
View 1 Excerpt

Similar Papers

Loading similar papers…