Login / Signup
Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds.
Efthymios Tzinis
Scott Wisdom
Aren Jansen
Shawn Hershey
Tal Remez
Daniel P. W. Ellis
John R. Hershey
Published in:
CoRR (2020)
Keyphrases
</>
audio visual
sound source
multi modal
visual information
temporal context
emotion recognition
person authentication
multimedia
visual data
multi stream
speaker verification
multimodal fusion
databases
context aware
audio visual speech recognition