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

facebooktwittermailshare

AUDIO CODING BASED ON SPECTRAL RECOVERY BY CONVOLUTIONAL NEURAL NETWORK

Abstract: 

This study proposes a new method of audio coding based on spectral recovery, which can enhance the performance of transform audio coding. An encoder represents spectral information of an input in a time-frequency domain and transmits only a portion of it so that the remaining spectral information can be recovered based on the transmitted information. A decoder recovers the magnitudes of missing spectral information using a convolutional neural network. The signs of missing spectral information are either transmitted or randomly assigned, according to their importance. By combining transmission and recovery of spectral information, the proposed method can enhance the coding performance, compared with conventional transform coding. The subjective performance evaluation shows that, for mono coding at 39.4 kbps, the proposed method provides higher sound quality than the USAC, by an average MUSHRA score of 8.5.

up
0 users have voted:

Paper Details

Authors:
Seong-Hyeon Shin, Seung Kwon Beack, Taejin Lee, Hochong Park
Submitted On:
10 May 2019 - 6:05am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Seong-Hyeon Shin
Paper Code:
ICASSP 2019 Paper #3334
Document Year:
2019
Cite

Document Files

AUDIO_CODING_BASED_ON_SPECTRAL_RECOVERY_BY_CONVOLUTIONAL_NEURAL_NETWORK.pdf

(41)

Keywords

Subscribe

[1] Seong-Hyeon Shin, Seung Kwon Beack, Taejin Lee, Hochong Park, "AUDIO CODING BASED ON SPECTRAL RECOVERY BY CONVOLUTIONAL NEURAL NETWORK", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4295. Accessed: Nov. 15, 2019.
@article{4295-19,
url = {http://sigport.org/4295},
author = {Seong-Hyeon Shin; Seung Kwon Beack; Taejin Lee; Hochong Park },
publisher = {IEEE SigPort},
title = {AUDIO CODING BASED ON SPECTRAL RECOVERY BY CONVOLUTIONAL NEURAL NETWORK},
year = {2019} }
TY - EJOUR
T1 - AUDIO CODING BASED ON SPECTRAL RECOVERY BY CONVOLUTIONAL NEURAL NETWORK
AU - Seong-Hyeon Shin; Seung Kwon Beack; Taejin Lee; Hochong Park
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4295
ER -
Seong-Hyeon Shin, Seung Kwon Beack, Taejin Lee, Hochong Park. (2019). AUDIO CODING BASED ON SPECTRAL RECOVERY BY CONVOLUTIONAL NEURAL NETWORK. IEEE SigPort. http://sigport.org/4295
Seong-Hyeon Shin, Seung Kwon Beack, Taejin Lee, Hochong Park, 2019. AUDIO CODING BASED ON SPECTRAL RECOVERY BY CONVOLUTIONAL NEURAL NETWORK. Available at: http://sigport.org/4295.
Seong-Hyeon Shin, Seung Kwon Beack, Taejin Lee, Hochong Park. (2019). "AUDIO CODING BASED ON SPECTRAL RECOVERY BY CONVOLUTIONAL NEURAL NETWORK." Web.
1. Seong-Hyeon Shin, Seung Kwon Beack, Taejin Lee, Hochong Park. AUDIO CODING BASED ON SPECTRAL RECOVERY BY CONVOLUTIONAL NEURAL NETWORK [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4295