Differences

This shows you the differences between two versions of the page.

--- projects:cnn4asr:start [2015/02/11 16:26] – created hj
+++ projects:cnn4asr:start [2015/02/11 16:34] (current) – hj
@@ Line 3: / Line 3: @@
 ===== CNNs for Speech Processing =====
+{{ :projects:cnn4asr:screen_shot_2015-02-11_at_11.27.34_am.png?0x300 |}}
+\\
+\\
+We propose to use convolutional neural networks (CNNs) for speech recognition, where convolution is applied in the frequency domain to normalize speech variations. We further propose a limited-weight-sharing scheme that can better model speech features. The special structure such as local connectivity, weight sharing, and pooling in
+CNNs exhibits some degree of invariance to small shifts of speech
+features along the frequency axis, which is important to deal with
+speaker and environment variations.
+\\
+**Reference:** \\
+[1] O. Abdel-Hamid, A. Mohamed, **H. Jiang**, L. Deng, G. Penn, D. Yu, "[[http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6857341&tag=1|Convolutional Neural Networks for Speech Recognition]]," //IEEE/ACM Trans. on Audio, Speech and Language Processing//, pp.1533-1545, Vol. 22, No. 10,  October 2014. \\ \\
+[2] O. Abdel-Hamid, A. Mohamed, **H. Jiang**, G. Penn, "Applying Convolutional Neural Networks Concepts to Hybrid NN-HMM Model for Speech Recognition," //Proc. of IEEE International Conference on Acoustic, Speech, Signal Processing (ICASSP'2012)//, Japan, March 2012.