The Sound of Pixels
Name
1804.03160.pdf
Description
Accepted version
Size
5.57 MB
Format
Adobe PDF
Checksum (MD5)
c322d33390f388932574d42815774f10
Author(s)
Zhao, Hang
Gan, Chuang
Rouditchenko, Andrew
Vondrick, Carl Martin
McDermott, Joshua Hartman
Torralba, Antonio
Date Issued
October 6, 2018
Publisher
Springer Nature
Citation
Zhao, Hang et al. "The Sound of Pixels." Computer Vision – European Conference on Computer Vision (ECCV 2018), September 4-18, 2018, Munich, Germany, edited by V. Ferrari, M. Hebert, C. Sminchisescu C., and Y. Weiss. Lecture Notes in Computer Science, vol 11205, pages 587-604. Springer, Cham, 2018. © 2018 Springer Nature
Version
Author's final manuscript
Abstract
We introduce PixelPlayer, a system that, by leveraging large amounts of unlabeled videos, learns to locate image regions which produce sounds and separate the input sounds into a set of components that represents the sound from each pixel. Our approach capitalizes on the natural synchronization of the visual and audio modalities to learn models that jointly parse sounds and images, without requiring additional manual supervision. Experimental results on a newly collected MUSIC dataset show that our proposed Mix-and-Separate framework outperforms several baselines on source separation. Qualitative results suggest our model learns to ground sounds in vision, enabling applications such as independently adjusting the volume of sound sources. Keywords: Cross-modal learning; Sound separation and localization
MIT Department
MIT-IBM Watson AI Lab
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-01246-5_35
