A Computational Model for Combinatorial Generalization in Physical Perception from Sound
Name
0000751.pdf
Description
Published version
Size
1.45 MB
Format
Unknown
Checksum (MD5)
671e8bccee8c21a876ff1b94753463b8
Author(s)
Wang, Yunyun
Gan, Chuang
Siegel, Max Harmon
Zhang, Zhoutong
Wi, Jiajun
Tenenbaum, Joshua B
Date Issued
2019
Journal
2019 Conference on Cognitive Computational Neuroscience
Publisher
Cognitive Computational Neuroscience
Citation
Wang, Yunyun, Gan, Chuang, Siegel, Max, Zhang, Zhoutong, Wu, Jiajun et al. 2019. "A Computational Model for Combinatorial Generalization in Physical Perception from Sound." 2019 Conference on Cognitive Computational Neuroscience.
Version
Final published version
Abstract
Humans possess the unique ability of combinatorial generalization in auditory perception: given novel auditory stimuli, humans perform auditory scene analysis and infer causal physical interactions based on prior knowledge. Could we build a computational model that achieves human-like combinatorial generalization? In this paper, we present a case study on box-shaking: having heard only the sound of a single ball moving in a box, we seek to interpret the sound of two or three balls of different materials. To solve this task, we propose a hybrid model with two components: a neural network for perception, and a physical audio engine for simulation. We use the outcome of the network as an initial guess and perform MCMC sampling with the audio engine to improve the result. Combining neural networks with a physical audio engine, our hybrid model achieves combinatorial generalization efficiently and accurately in auditory scene perception.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
MIT-IBM Watson AI Lab
Center for Brains, Minds, and Machines
Terms of Use
Creative Commons Attribution 3.0 unported license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.32470/CCN.2019.1276-0
