End-to-End Neural Speaker Diarization with Self-Attention.

Yusuke Fujita Naoyuki Kanda Shota Horiguchi Yawen Xue Kenji Nagamatsu Shinji Watanabe

Published in: ASRU (2019)

Keyphrases

end to end
speaker diarization
network architecture
neural network
broadcast news
speech recognition
congestion control
bayesian networks
application layer
bayesian information criterion
machine learning
scalable video