Content matching for sound generating objects within a visual scene using a computer vision approach

Turner D, Pike C, Murphy D. Content matching for sound generating objects within a visual scene using a computer vision approach. In: AES Convention 148. Audio Engineering Society; 2020. Paper 10375. Available from: https://aes.org/publications/elibrary-page/?id=20792

@inproceedings{Turner2020_20792,
  author = {Turner, Daniel and Pike, Chris and Murphy, Damian},
  title = {{Content matching for sound generating objects within a visual scene using a computer vision approach}},
  booktitle = {AES Convention 148},
  note = {Paper 10375},
  year = {2020},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20792}
}

TY  - CPAPER
TI  - Content matching for sound generating objects within a visual scene using a computer vision approach
AU  - Turner, Daniel
AU  - Pike, Chris
AU  - Murphy, Damian
T2  - AES Convention 148
M1  - Paper 10375
PY  - 2020
DA  - 2020/05/06
UR  - https://aes.org/publications/elibrary-page/?id=20792
PB  - Audio Engineering Society
LA  - en
AB  - The increase in and demand for immersive audio content production and consumption, particularly in VR, is driving the need for tools to facilitate creation. Immersive productions place additional demands on sound design teams, specifically around the increased complexity of scenes, increased number of sound producing objects, and the need to spatialise sound in 360?. This paper presents an initial feasibility study for a methodology utilising visual object detection in order to detect, track, and match content for sound generating objects, in this case based on a simple 2D visual scene. Results show that while successful for a single moving object there are limitations within the current computer vision system used which causes complications for scenes with multiple objects. Results also show that the recommendation of candidate sound effect files is heavily dependent on the accuracy of the visual object detection system and the labelling of the audio repository used.
ER  -