Using Deep Neural Networks for Smoothing Pitch Profiles in Connected Speech
This paper presents a new pitch tracking smoother based on deep neural networks (DNN). It leverages Long Short-Term Memories, a particular kind of recurrent neural network, for correcting pitch detection errors produced by state-of-the-art Pitch Detection Algorithms. The proposed system has been ext...
Enregistré dans:
| Udgivet i: | URI:https://journals.openedition.org/ijcol, |
|---|---|
| Auteurs principaux: | , |
| Format: | Article ou chapitre numérique |
| Sprog: | Anglais |
| Udgivet: |
IJCoL
2020
|
| Online adgang: | Accès Université d'Orléans et IFPM Accès Université d'Orléans et IFPM |