The Secret Source : Incorporating Source Features to Improve Acoustic-to-Articulatory Speech Inversion.

Yashish M. Siriwardena Carol Y. Espy-Wilson

Published in: CoRR (2022)

Keyphrases

data sets
speech recognition
acoustic features
low level
multiple sources
speech signal
emotional speech
spectral features
feature space
feature set
language model
emotion recognition
audio signal
lexical features
speech recognition systems