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...
Guardado en:
Autores principales: | Michele Ferro, Fabio Tamburini |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Accademia University Press
2019
|
Materias: | |
Acceso en línea: | https://doaj.org/article/7241abc1b2644793b4cac8ebe884d74f |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
State-of-the-art Italian dependency parsers based on neural and ensemble systems
por: Oronzo Antonelli, et al.
Publicado: (2019) -
Multitask Learning with Deep Neural Networks for Community Question Answering
por: Daniele Bonadiman, et al.
Publicado: (2017) -
Distributed Smoothed Tree Kernel
por: Lorenzo Ferrone, et al.
Publicado: (2015) -
Deep Learning of Inflection and the Cell-Filling Problem
por: Franco Alberto Cardillo, et al.
Publicado: (2018) -
Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
por: Yuri Bizzoni, et al.
Publicado: (2018)