Music Enhancement by a Novel CNN Architecture

Porov A, Oh E, Choo K, Sung H, Jeong J, Osipov K, Francois H. Music Enhancement by a Novel CNN Architecture. In: AES Convention 145. Audio Engineering Society; 2018. Paper 10036. Available from: https://aes.org/publications/elibrary-page/?id=19762

@inproceedings{Porov2018_19762,
  author = {Porov, Anton and Oh, Eunmi and Choo, Kihyun and Sung, Hosang and Jeong, Jonghoon and Osipov, Konstantin and Francois, Holly},
  title = {{Music Enhancement by a Novel CNN Architecture}},
  booktitle = {AES Convention 145},
  note = {Paper 10036},
  year = {2018},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19762}
}

TY  - CPAPER
TI  - Music Enhancement by a Novel CNN Architecture
AU  - Porov, Anton
AU  - Oh, Eunmi
AU  - Choo, Kihyun
AU  - Sung, Hosang
AU  - Jeong, Jonghoon
AU  - Osipov, Konstantin
AU  - Francois, Holly
T2  - AES Convention 145
M1  - Paper 10036
PY  - 2018
DA  - 2018/10/06
UR  - https://aes.org/publications/elibrary-page/?id=19762
PB  - Audio Engineering Society
LA  - en
AB  - This paper is concerned with music enhancement by removal of coding artifacts and recovery of acoustic characteristics that preserve the sound quality of the original music content. In order to achieve this, we propose a novel convolution neural network (CNN) architecture called FTD (Frequency-Time Dependent) CNN, which utilizes correlation and context information across spectral and temporal dependency for music signals. Experimental results show that both subjective and objective sound quality metrics are significantly improved. This unique way of applying a CNN to exploit global dependency across frequency bins may effectively restore information that is corrupted by coding artifacts in compressed music content.
ER  -