Conference item
The sound of water: inferring physical properties from pouring liquids
- Abstract:
- We study the connection between audio-visual observations and the underlying physics of a mundane yet intriguing everyday activity: pouring liquids. Given only the sound of liquid pouring into a container, our objective is to automatically infer physical properties such as the liquid level, the shape and size of the container, the pouring rate, and the time to fill. To this end, we: (i) show in theory that these properties can be determined from the fundamental frequency (pitch); (ii) train a pitch detection model with supervision from simulated data and visual data with a physics-inspired objective; (iii) introduce a new large dataset of real pouring videos for a systematic study; (iv) show that the trained model can indeed infer these physical properties for real data; and finally, (v) we demonstrate strong generalization to various container shapes, other datasets, and in-the-wild YouTube videos. Our work presents a keen understanding of a narrow yet rich problem at the intersection of acoustics, physics, and learning. It opens up applications to enhance multisensory perception in robotic pouring.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 13.2MB, Terms of use)
-
- Publisher copy:
- 10.1109/icassp49660.2025.10889950
Authors
+ Engineering and Physical Sciences Research Council
More from this funder
- Funder identifier:
- https://ror.org/0439y7842
- Grant:
- EP/T028572/1
- Publisher:
- IEEE
- Host title:
- ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publication date:
- 2025-03-07
- Event title:
- IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025)
- Event location:
- Hyderabad, India
- Event website:
- https://2025.ieeeicassp.org/
- Event start date:
- 2025-04-06
- Event end date:
- 2025-04-11
- DOI:
- EISSN:
-
1520-6149
- ISSN:
-
2379-190X
- EISBN:
- 9798350368741
- ISBN:
- 9798350368758
- Language:
-
English
- Keywords:
- Pubs id:
-
2097053
- Local pid:
-
pubs:2097053
- Deposit date:
-
2025-04-07
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2025
- Rights statement:
- Copyright © 2025, IEEE
- Notes:
-
The author accepted manuscript (AAM) of this paper has been made available under the University of Oxford's Open Access Publications Policy, and a CC BY public copyright licence has been applied.
This is the accepted manuscript version of the article. The final version is available online from IEEE at https://dx.doi.org/10.1109/icassp49660.2025.10889950
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record