Off-Screen Sound Separation Based on Audio-visual Pre-training Using Binaural Audio.

Masaki Yoshida Ren Togo Takahiro Ogawa Miki Haseyama

Published in: Sensors (2023)

Keyphrases

audio visual
sound source
multi modal
audio features
visual information
visual data
multi stream
multimedia
emotion recognition
person authentication
audio visual speech recognition
speaker verification
multimodal fusion
training set
e learning
acoustic features
input data