Login / Signup

Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio.

Antoni DimitriadisSiqi PanVidhyasaharan SethuBeena Ahmed
Published in: CoRR (2023)
Keyphrases
  • multi channel
  • learning algorithm
  • spatial information
  • spatial relations
  • multimedia
  • prior knowledge
  • speech recognition
  • spatial domain
  • audio stream
  • frequency domain
  • spatial data
  • audio visual
  • emotion recognition