Universal Paralinguistic Speech Representations Using Self-Supervised Conformers.

Joel Shor Aren Jansen Wei Han Daniel S. Park Yu Zhang

Published in: CoRR (2021)

Keyphrases

speech recognition
speech signal
speech synthesis
speaker recognition
audio visual
automatic speech recognition
language acquisition
vocal tract
artificial intelligence
gaussian mixture model
symbolic representation
representation scheme
multi valued
text to speech
text to speech synthesis