Login / Signup

Real-time Architecture for Audio-Visual Active Speaker Detection.

Min HuangWen WangZheyuan LinFiseha B. TesemaShanshan JiJason GuMinhong WangWei SongTe LiShiqiang Zhu
Published in: ROBIO (2022)
Keyphrases
  • audio visual
  • real time
  • multi modal
  • visual information
  • speaker verification
  • visual data
  • multimedia
  • multi stream
  • temporal context
  • person authentication
  • emotion recognition
  • audio visual speech recognition