Detection of Off-screen Sound Based on Loss Function of Self-supervised Audio-visual Spatialization.

Masaki Yoshida Ren Togo Takahiro Ogawa Miki Haseyama

Published in: GCCE (2021)

Keyphrases

loss function
audio visual
multi modal
sound source
pairwise
visual information
support vector
multi stream
visual data
audio visual speech recognition
multimedia
risk minimization
image database
image data
reproducing kernel hilbert space
information retrieval
data sets