Sign in

Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization.

Federico LandiniMireia DíezAlicia Lozano-DiezLukás Burget
Published in: CoRR (2022)
Keyphrases
  • end to end
  • wide band
  • training data
  • speaker diarization
  • network architecture
  • admission control
  • speaker identification
  • low light
  • slowly varying
  • speech recognition
  • received signal
  • multimedia
  • denoising
  • subband