Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

AAC encoding detection and bitrate estimation using a convolutional neural network

 
: Seichter, Daniel; Cuccovillo, Luca; Aichroth, Patrick

:

Institute of Electrical and Electronics Engineers -IEEE-; IEEE Signal Processing Society:
IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016. Proceedings : March 20-25, 2016, Shanghai International Convention Center, Shanghai, China
Piscataway, NJ: IEEE, 2016
ISBN: 978-1-4799-9988-0 (electronic)
ISBN: 978-1-4799-9987-3 (USB)
ISBN: 978-1-4799-9989-7 (print)
S.2069-2073
International Conference on Acoustics, Speech and Signal Processing (ICASSP) <2016, Shanghai>
Englisch
Konferenzbeitrag
Fraunhofer IDMT ()
audio forensics; neural networks; quality assessment; MPEG-2 AAC; deep learning

Abstract
In this paper, we propose a new method for AAC encoding detection and bitrate estimation from PCM material. The algorithm is based on a Convolutional Neural Network that can distinguish between eight different bitrates. It achieves an average accuracy of 94.65% by analysis of only 116.10 ms of content.

: http://publica.fraunhofer.de/dokumente/N-391933.html