Sparse Autoencoder Based Multiple Audio Objects Coding Method

Zhang S, Wu X, Qu T. Sparse Autoencoder Based Multiple Audio Objects Coding Method. In: AES Convention 146. Audio Engineering Society; 2019. Paper 10172. Available from: https://aes.org/publications/elibrary-page/?id=20305

@inproceedings{Zhang2019_20305,
  author = {Zhang, Shuang and Wu, Xihong and Qu, Tianshu},
  title = {{Sparse Autoencoder Based Multiple Audio Objects Coding Method}},
  booktitle = {AES Convention 146},
  note = {Paper 10172},
  year = {2019},
  month = mar,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20305}
}

TY  - CPAPER
TI  - Sparse Autoencoder Based Multiple Audio Objects Coding Method
AU  - Zhang, Shuang
AU  - Wu, Xihong
AU  - Qu, Tianshu
T2  - AES Convention 146
M1  - Paper 10172
PY  - 2019
DA  - 2019/03/06
UR  - https://aes.org/publications/elibrary-page/?id=20305
PB  - Audio Engineering Society
LA  - en
AB  - The traditional multiple audio objects codec extracts the parameters of each object in the frequency domain and produces serious confusion because of high coincidence degree in subband among objects. This paper uses sparse domain instead of frequency domain and reconstruct audio object using the binary mask from the down-mixed signal based on the sparsity of each audio object. In order to overcome high coincidence degree of subband among different audio objects, the sparse autoencoder neural network is established. On this basis, a multiple audio objects codec system is built up. To evaluate this proposed system, the objective and subjective evaluation are carried on and the results show that the proposed system has the better performance than SAOC.
ER  -