Convolutional Neural Networks-based continuous speech recognition using raw speech signal
Authors:
- 1 April 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 4295-4299
Abstract
State-of-the-art automatic speech recognition systems model the relationship between acoustic speech signal and phone classes in two stages, namely, extraction of spectral-based features based on prior knowledge followed by training of acoustic model, typically an artificial neural network (ANN). In our recent work, it was shown that Convolutional Neural Networks (CNNs) can model phone classes from raw acoustic speech signal, reaching performance on par with other existing feature-based approaches. This paper extends the CNN-based approach to large vocabulary speech recognition task. More precisely, we compare the CNN-based approach against the conventional ANN-based approach on Wall Street Journal corpus. Our studies show that the CNN-based approach achieves better performance than the conventional ANN-based approach with as many parameters. We also show that the features learned from raw speech by the CNN-based approach could generalize across different databases.Keywords
This publication has 16 references indexed in Scilit:
- Convolutional Neural Networks for Distant Speech RecognitionIEEE Signal Processing Letters, 2014
- Deep convolutional neural networks for LVCSR2013
- Investigating deep neural network based transforms of robust audio features for LVCSR2013
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Acoustic Modeling Using Deep Belief NetworksIEEE Transactions on Audio, Speech, and Language Processing, 2011
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Large vocabulary continuous speech recognition using HTK2002
- Robust decision tree state tying for continuous speech recognitionIEEE Transactions on Speech and Audio Processing, 2000
- 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