Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network.

Takaaki Saeki Shinnosuke Takamichi Hiroshi Saruwatari

Published in: ASRU (2021)

Keyphrases

low latency
high bandwidth
massive scale
text to speech synthesis
high speed
highly efficient
end to end
mobile nodes
high throughput
network structure
real time
peer to peer
stream processing
response time
wireless sensor networks
databases
data sets