Login / Signup
Alaryngeal Speech Generation Using MaskCycleGAN-VC and Timbre-Enhanced Loss.
Hnin Yadana Lwin
Wuttipong Kumwilaisak
Chatchawarn Hansakunbuntheung
Nattanun Thatphithakkul
Published in:
IAIT (2023)
Keyphrases
</>
speech recognition
acoustic features
automatic speech recognition
endpoint detection
neural network
spoken language
generation process
audio visual
vc dimension
low level
dialogue system
lower bound
linear prediction
video sequences
speaker verification
website
recognition engine
audio stream
machine learning