Sign in

TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings.

Christoph BöddekerAswin Shanmugam SubramanianGordon WichernReinhold Haeb-UmbachJonathan Le Roux
Published in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
  • speaker diarization
  • speaker identification
  • low dimensional
  • vector space
  • accurate estimation
  • real time
  • search engine
  • hidden markov models
  • high dimensional data
  • audio visual
  • broadcast news
  • spatial coordinates