Login / Signup
ACE-VC: Adaptive and Controllable Voice Conversion Using Explicitly Disentangled Self-Supervised Speech Representations.
Shehzeen Hussain
Paarth Neekhara
Jocelyn Huang
Jason Li
Boris Ginsburg
Published in:
ICASSP (2023)
Keyphrases
</>
text to speech
emotion recognition
speech synthesis
voice activity detection
synthesized speech
speech sounds
fundamental frequency
speech recognition
audio visual
speech signal
relation extraction
database
non stationary
hidden markov models
pattern recognition
e learning
search engine