Online End-to-End Neural Diarization with Speaker-Tracing Buffer.
Yawen XueShota HoriguchiYusuke FujitaShinji WatanabeKenji NagamatsuPublished in: CoRR (2020)
Keyphrases
- end to end
- speaker diarization
- admission control
- wireless ad hoc networks
- neural network
- high bandwidth
- congestion control
- multipath
- network architecture
- content delivery
- speaker identification
- ad hoc networks
- transport layer
- application layer
- text localization and recognition
- internet protocol
- automatic speech recognition
- image sequences