Login / Signup
Minimizing Residuals for Native-Nonnative Voice Conversion in a Sparse, Anchor-Based Representation of Speech.
Christopher Liberatore
Ricardo Gutierrez-Osuna
Published in:
ICASSP (2022)
Keyphrases
</>
text to speech
neural network
automatic speech recognition
high dimensional
image representation
speech recognition
sparse data
object recognition
dimensionality reduction
language model
speech signal
representation scheme
noisy environments
emotion recognition
sparsity constraints
speech quality