Speech restoration based on deep learning autoencoder with layer-wised pretraining

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 2, Issue , 2012, Pages 1502-1505

  Lu, Xugang ^a   Matsuda, Shigeki ^a   Hori, Chiori ^a   Kashioka, Hideki ^a  

^a NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY   (Japan)

Author keywords

Autoencoder; Deep learning; Noise reduction; Speech recognition

Indexed keywords

AUTO ENCODERS; DEEP LEARNING; INITIAL PARAMETER; NETWORK CAPACITY; QUASI-NEWTON OPTIMIZATION; ROBUST SPEECH RECOGNITION; STATISTICAL REGULARITY; TRAINING STRATEGY;

ALGORITHMS; LEARNING SYSTEMS; NOISE ABATEMENT; RESTORATION; SPEECH; SPEECH RECOGNITION;

NETWORK LAYERS;

EID: 84878421481     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. Bengio, Y., "Learning deep architectures for AI," Foundations and Trends in Machine Learning, 2(1): 1-127, 2009.
2. Hinton, G. E., and Salakhutdinov, R., "Reducing the Dimensionality of Data with Neural Networks," Science, 313: 504-507, 2006.
3. Bengio, Y., Lamblin, P., Popovici, D., and Larochelle, H., "Greedy layer-wise training of deep networks," In Advances in Neural Information Processing Systems, 19: 153-160, MIT Press, Cambridge, 2007.
4. Ranzato, M. A., Huang, F. J., Boureau, Y. L., LeCun, Y., "Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition," IEEE conference on Computer Vision and Pattern Recognition, 1-8, 2007.
5. Dahl, G., Yu, D., Deng, L., Acero, A., "Context-dependent pretrained deep neural networks for large vocabulary speech recognition," IEEE Transactions on Audio, Speech, and Language Processing, 20 (1): 30-42, 2011.
6. Deng, L., Seltzer, M., Yu, D., Acero, A., Mohamed, A., Hinton, A., "Binary Coding of Speech Spectrograms Using a Deep Autoencoder," in Proc. of Interspeech, 1692-1695, 2010.
7. Schmidt, M., Van Den Berg, E., Friedl, M. P., Murphy, K., "Optimizing costly functions with simple constraints: A limitedmemory projected quasi-newton algorithm," in Proc. of Conf. on Artificial Intelligence and Statistics, 456-463, 2009.
8. Loizou, P. C., Speech Enhancement: Theory and Practice, CRC Press, 2007.
9. Lee, H., Ekanadham, C., and Ng, A. Y., "Sparse deep belief net model for visual area V2," in Advances in Neural Information Processing Systems (NIPS), 20: 873-880, 2008.