Deep Neural Networks for Cross-Modal Estimations of Acoustic Reverberation Characteristics from Two-Dimensional Images

Kon H, Koike H. Deep Neural Networks for Cross-Modal Estimations of Acoustic Reverberation Characteristics from Two-Dimensional Images. In: AES Convention 144. Audio Engineering Society; 2018. Paper 9995. Available from: https://aes.org/publications/elibrary-page/?id=19512

@inproceedings{Kon2018_19512,
  author = {Kon, Homare and Koike, Hideki},
  title = {{Deep Neural Networks for Cross-Modal Estimations of Acoustic Reverberation Characteristics from Two-Dimensional Images}},
  booktitle = {AES Convention 144},
  note = {Paper 9995},
  year = {2018},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19512}
}

TY  - CPAPER
TI  - Deep Neural Networks for Cross-Modal Estimations of Acoustic Reverberation Characteristics from Two-Dimensional Images
AU  - Kon, Homare
AU  - Koike, Hideki
T2  - AES Convention 144
M1  - Paper 9995
PY  - 2018
DA  - 2018/05/06
UR  - https://aes.org/publications/elibrary-page/?id=19512
PB  - Audio Engineering Society
LA  - en
AB  - In augmented reality (AR) applications, reproduction of acoustic reverberation is essential for creating an immersive audio experience. The audio component of an AR experience should simulate the acoustics of the environment that users are experiencing. Earlier, sound engineers could program all the reverberation parameters in advance for a scene or if the audience was in a fixed position. However, adjusting the reverberation parameters using conventional methods is difficult because all such parameters cannot be programmed for AR applications. Considering that skilled acoustic engineers can estimate reverberation parameters from an image of a room, we trained a deep neural network (DNN) to estimate reverberation parameters from two-dimensional images. The results suggest a DNN can estimate the acoustic reverberation parameters from one image.
ER  -