Index Catalog // 蹄兔

清除过滤

过滤: 学科 Speech synthesis

Síntesis de voz basada en modelos ocultos de Markov y algoritmos de aprendizaje profundo

描述:	This thesis addresses the problem of improving the results of statistical parametric speech synthesis using deep learning algorithms. The subject has become more important in recent times due to the increasing presence of artificial voices in several devices and applications. In these, there is a need to refine the results...
学科:	Aprendizaje automático (Inteligencia artificial), Machine learning, Síntesis de Voz, Speech synthesis, Modelos ocultos de Markov, and Hidden Markov models
创造者:	Coto Jiménez, Marvin
贡献者:	Lara Velázquez, Pedro, Goddard Close, John Charles Henry, Mackinney Romero, René, and Rojas Cárdenas, Luis Martín
出版者:	Universidad Autónoma Metropolitana
Posgrado:	Doctorado en Ciencias y Tecnologias de la Informacion
语言:	spa
Año de publicación:	2017
权:	Acceso Abierto
执照:	Atribucion-NoComercial 4.0 Internacional (CC BY-NC 4.0)
Tipo de Recurso:	info:eu-repo/semantics/masterThesis
识别码:	https://doi.org/10.24275/uami.dj52w4688