Login / Signup
LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes.
Trung Dang
David Aponte
Dung N. Tran
Kazuhito Koishida
Published in:
CoRR (2024)
Keyphrases
</>
text to speech
autoregressive
low latency
speech synthesis
prosodic features
non stationary
high throughput
random fields
high speed
gaussian markov random field
real time
stream processing
highly efficient
word processing
multimedia