Sign in
Probabilistic Kernels for Improved Text-to-Speech Alignment in Long Audio Tracks.
Germán Bordel
Mikel Peñagarikano
Luis Javier Rodríguez-Fuentes
Aitor Álvarez
Amparo Varona
Published in:
IEEE Signal Process. Lett. (2016)
Keyphrases
</>
text to speech
prosodic features
speech synthesis
multimodal interaction
text to speech synthesis
programming tool
english text
bayesian networks
generative model
probabilistic model
kernel function
feature space
multimedia
support vector
kernel methods
sequence alignment
word processing
multi modal