An End-to-End Binaural Sound Localization Model Based on the Equalization and Cancellation Theory

Song T, Zhang W, Chen J. An End-to-End Binaural Sound Localization Model Based on the Equalization and Cancellation Theory. In: AES Convention 152. Audio Engineering Society; 2022. Paper 10576. Available from: https://aes.org/publications/elibrary-page/?id=21689

@inproceedings{Song2022_21689,
  author = {Song, Tao and Zhang, Wenwen and Chen, Jing},
  title = {{An End-to-End Binaural Sound Localization Model Based on the Equalization and Cancellation Theory}},
  booktitle = {AES Convention 152},
  note = {Paper 10576},
  year = {2022},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=21689}
}

TY  - CPAPER
TI  - An End-to-End Binaural Sound Localization Model Based on the Equalization and Cancellation Theory
AU  - Song, Tao
AU  - Zhang, Wenwen
AU  - Chen, Jing
T2  - AES Convention 152
M1  - Paper 10576
PY  - 2022
DA  - 2022/05/06
UR  - https://aes.org/publications/elibrary-page/?id=21689
PB  - Audio Engineering Society
LA  - en
AB  - The end-to-end framework has been introduced into the binaural localization modeling and achieved higher localization accuracy than the other models, however, the reasonability and interpretability for applying the related neural networks remain unclear. It has been well documented that the auditory system relies on binaural cues for sound localization, and the equalization and cancellation (EC) theory describes how the binaural cues are extracted. In this paper, an end-to-end binaural localization model is proposed based on the EC theory. In the proposed model, a convolution neural network(CNN) with a specifically designed activation function is used to implement the EC theory. The proposed model was trained in synthesized rooms and evaluated in real rooms. Experiment results show that CNN kernels learned by the proposed model are corresponding to binaural cues, and the proposed model outperforms the current end-to-end model by a 10.73% improvement in localization accuracy and a 12.91%improvement in root mean square error(RMSE).
ER  -