An Improved Low Complexity AMR-WB+ Encoder Using Neural Networks for Mode Selection

Lecomte J, Lefebvre R, Richard G. An Improved Low Complexity AMR-WB+ Encoder Using Neural Networks for Mode Selection. In: AES Convention 123. Audio Engineering Society; 2007. Paper 7294. Available from: https://aes.org/publications/elibrary-page/?id=14351

@inproceedings{Lecomte2007_14351,
  author = {Lecomte, Jérémie and Lefebvre, Roch and Richard, Guy},
  title = {{An Improved Low Complexity AMR-WB+ Encoder Using Neural Networks for Mode Selection}},
  booktitle = {AES Convention 123},
  note = {Paper 7294},
  year = {2007},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14351}
}

TY  - CPAPER
TI  - An Improved Low Complexity AMR-WB+ Encoder Using Neural Networks for Mode Selection
AU  - Lecomte, Jérémie
AU  - Lefebvre, Roch
AU  - Richard, Guy
T2  - AES Convention 123
M1  - Paper 7294
PY  - 2007
DA  - 2007/10/06
UR  - https://aes.org/publications/elibrary-page/?id=14351
PB  - Audio Engineering Society
LA  - en
AB  - This paper presents an alternative mode selector based on neural networks to improve the low-complexity AMR WB+ standard audio coder especially at low bit rates. The AMR-WB+ audio coder is a multi-mode coder using both time-domain and frequency-domain modes. In low complexity operation, the standard encoder determines the coding mode on a frame-by-frame basis by essentially applying thresholding to parameters extracted from the input signal and using a logic which favors time-domain modes. The mode selector proposed in this paper reduces this bias, and achieves a mode decision which is closer to the full complexity encoder. This results in measurable quality improvements, in both objective and subjective assessments.
ER  -