Audio-Visual Overlapped Speech Detection for Spontaneous Distant Speech.

Minyoung Kyoung Hyung Jae Jeon Kiyoung Park

Published in: IEEE Access (2023)

Keyphrases

audio visual
multi modal
multi stream
emotion recognition
visual information
multimedia
visual data
audio features
speaker verification
speech recognition
noisy environments
person authentication
audio visual speech recognition
metadata
image database
spatio temporal
three dimensional