Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition
Top Cited Papers
- 1 March 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4277-4280
- https://doi.org/10.1109/icassp.2012.6288864
Abstract
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. In our method, a pair of local filtering layer and max-pooling layer is added at the lowest end of neural network (NN) to normalize spectral variations of speech signals. In our experiments, the proposed CNN architecture is evaluated in a speaker independent speech recognition task using the standard TIMIT data sets. Experimental results show that the proposed CNN method can achieve over 10% relative error reduction in the core TIMIT test sets when comparing with a regular NN using the same number of hidden layers and weights. Our results also show that the best result of the proposed CNN model is better than previously published results on the same TIMIT test sets that use a pre-trained deep NN model.Keywords
This publication has 6 references indexed in Scilit:
- Making Deep Belief Networks effective for large vocabulary continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Acoustic Modeling Using Deep Belief NetworksIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Learning methods for generic object recognition with invariance to pose and lightingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Maximum likelihood linear transformations for HMM-based speech recognitionComputer Speech & Language, 1998
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Speaker-independent phone recognition using hidden Markov modelsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989