On learning associations of faces and voices
Name
1805.05553.pdf
Description
Submitted version
Size
9.98 MB
Format
Adobe PDF
Checksum (MD5)
37f7315f8b8d1848e1ab3a007b7ca175
Author(s)
Kim, Changil
Shin, Hijung Valentina
Oh, Tae-Hyun
Kaspar, Alexandre
Elgharib, Mohamed
Matusik, Wojciech
Date Issued
December 2018
Journal
Lecture notes in computer science
Publisher
Springer Nature
Citation
Kim, Changil, et al., "On learning associations of faces and voices." In Jawahar, C., H. Li, G.Mori, and K. Schindler, eds., Computer vision: 14th Asian Conference on Computer Vision (ACCV 2018), December 2–6, 2018, Perth, Western Australia. Lecture notes in computer science 11365 (Cham: Springer Nature, 2018): p. 276-92 doi 10.1007/978-3-030-20873-8_18 ©2018 Author(s)
Version
Original manuscript
Abstract
In this paper, we study the associations between human faces and voices. Audiovisual integration, specifically the integration of facial and vocal information is a well-researched area in neuroscience. It is shown that the overlapping information between the two modalities plays a significant role in perceptual tasks such as speaker identification. Through an online study on a new dataset we created, we confirm previous findings that people can associate unseen faces with corresponding voices and vice versa with greater than chance accuracy. We computationally model the overlapping information between faces and voices and show that the learned cross-modal representation contains enough information to identify matching faces and voices with performance similar to that of humans. Our representation exhibits correlations to certain demographic attributes and features obtained from either visual or aural modality alone. We release our dataset of audiovisual recordings and demographic annotations of people reading out short text used in our studies. ©2019 keywords: face-voice association; multi-modal representation learning
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-20873-8_18
