Login / Signup

CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments.

Xiulong LiuSudipta PaulMoitreya ChatterjeeAnoop Cherian
Published in: AAAI (2024)
Keyphrases
  • noisy environments
  • visual navigation
  • speaker identification
  • collision avoidance
  • voice activity detection
  • speech recognition
  • noise reduction
  • speech enhancement
  • speech signal