Continuous speech recognition based on convolutional neural network

Qing-qing Zhang; Yong Liu; Jie-lin Pan; Yong-hong Yan

doi:10.1117/12.2197152

6 July 2015 Continuous speech recognition based on convolutional neural network

Qing-qing Zhang, Yong Liu, Jie-lin Pan, Yong-hong Yan

Proceedings Volume 9631, Seventh International Conference on Digital Image Processing (ICDIP 2015); 963121 (2015) https://doi.org/10.1117/12.2197152
Event: Seventh International Conference on Digital Image Processing (ICDIP15), 2015, Los Angeles, United States

Abstract

Convolutional Neural Networks (CNNs), which showed success in achieving translation invariance for many image processing tasks, are investigated for continuous speech recognitions in the paper. Compared to Deep Neural Networks (DNNs), which have been proven to be successful in many speech recognition tasks nowadays, CNNs can reduce the NN model sizes significantly, and at the same time achieve even better recognition accuracies. Experiments on standard speech corpus TIMIT showed that CNNs outperformed DNNs in the term of the accuracy when CNNs had even smaller model size.

Citation Download Citation

Qing-qing Zhang, Yong Liu, Jie-lin Pan, and Yong-hong Yan "Continuous speech recognition based on convolutional neural network", Proc. SPIE 9631, Seventh International Conference on Digital Image Processing (ICDIP 2015), 963121 (6 July 2015); https://doi.org/10.1117/12.2197152

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available