DocumentCode
2772316
Title
Enhancing MP3 encoding by utilizing a predictive Complex-Valued Neural Network
Author
Al-Nuaimi, A.Y.H. ; Amin, Md Faijul ; Murase, Kazuyuki
Author_Institution
Dept. of Syst. Design Eng., Univ. of Fukui, Fukui, Japan
fYear
2012
fDate
10-15 June 2012
Firstpage
1
Lastpage
6
Abstract
We design a Complex-Valued Neural Network (CVNN) used for audio prediction. This CVNN is inserted into an MP3 encoder to increase the compression ratio of audio data. Experiments show that CVNNs can increase the compression capabilities of the encoder, and that CVNN is more suitable than Real Valued Neural Networks for audio prediction.
Keywords
audio coding; data compression; neural nets; CVNN; MP3 encoding; audio data compression ratio; audio prediction; predictive complex-valued neural network; real valued neural networks; Bit rate; Digital audio players; Discrete cosine transforms; Encoding; Neural networks; Quantization; Transform coding; CVNN; MP3 encoding; audio; predictive encoding;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks (IJCNN), The 2012 International Joint Conference on
Conference_Location
Brisbane, QLD
ISSN
2161-4393
Print_ISBN
978-1-4673-1488-6
Electronic_ISBN
2161-4393
Type
conf
DOI
10.1109/IJCNN.2012.6252535
Filename
6252535
Link To Document