Frame-Wise Streaming end-to-end Speaker Diarization with Non-Autoregressive Self-Attention-Based Attractors.

Di Liang Nian Shao Xiaofei Li

Published in: ICASSP (2024)

Keyphrases

end to end
autoregressive
speaker diarization
scalable video
non stationary
rate adaptation
random fields
sar images
congestion control
pairwise
speech recognition
video streaming
frame rate
bayesian information criterion
neural network
pattern recognition
image segmentation
computer vision
information retrieval