Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH PROCESSING

Abstract: 

Different neural networks have exhibited excellent performance on various speech processing tasks, and they usually have specific advantages and disadvantages. We propose to use a recently developed deep learning model, recurrent convolutional neural network (RCNN), for speech processing, which inherits some merits of recurrent neural network (RNN) and convolutional neural network (CNN). The core module can be viewed as a convolutional layer embedded with an RNN, which enables the model to capture both temporal and frequency dependence in the spectrogram of the speech in an efficient way. The model is tested on speech corpus TIMIT for phoneme recognition and IEMOCAP for emotion recognition. Experimental results show that the model is competitive with previous methods in terms of accuracy and efficiency.

up
0 users have voted:

Paper Details

Authors:
Yue Zhao, Xingyu Jin, Xiaolin Hu
Submitted On:
5 March 2017 - 10:18am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Xiaolin Hu
Paper Code:
1332
Document Year:
2017
Cite

Document Files

icassp2017_poster.pptx

(115 downloads)

Subscribe

[1] Yue Zhao, Xingyu Jin, Xiaolin Hu, "RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH PROCESSING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1632. Accessed: Sep. 25, 2017.
@article{1632-17,
url = {http://sigport.org/1632},
author = {Yue Zhao; Xingyu Jin; Xiaolin Hu },
publisher = {IEEE SigPort},
title = {RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH PROCESSING},
year = {2017} }
TY - EJOUR
T1 - RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH PROCESSING
AU - Yue Zhao; Xingyu Jin; Xiaolin Hu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1632
ER -
Yue Zhao, Xingyu Jin, Xiaolin Hu. (2017). RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH PROCESSING. IEEE SigPort. http://sigport.org/1632
Yue Zhao, Xingyu Jin, Xiaolin Hu, 2017. RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH PROCESSING. Available at: http://sigport.org/1632.
Yue Zhao, Xingyu Jin, Xiaolin Hu. (2017). "RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH PROCESSING." Web.
1. Yue Zhao, Xingyu Jin, Xiaolin Hu. RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH PROCESSING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1632