Parametric speech synthesis using local and global sparse Gaussian processes

Tomoki Koriyama, Takashi Nose, Takao Kobayashi

研究成果: Conference contribution

抄録

This paper describes an application of Gaussian process regression (GPR) to parametric speech synthesis. GPR enables us to predict synthetic speech parameters by utilizing exemplars of training speech data directly without converting the acoustic features of training data into too small number of model parameters thanks to nonparametric Bayesian regression. However, GPR inherently requires high computational cost and resources. In this paper, to alleviate this problem, we incorporate local and global sparse Gaussian process approximation into the statistical speech synthesis framework, and investigate trade-off between computational cost and speech synthesis performance through experiments. Moreover, we examine the way of choosing pseudo data set used for the sparse GP approximation.

本文言語English
ホスト出版物のタイトルIEEE International Workshop on Machine Learning for Signal Processing, MLSP
編集者Tulay Adali, Jan Larsen, Mamadou Mboup, Eric Moreau
出版社IEEE Computer Society
ISBN(電子版)9781479936946
DOI
出版ステータスPublished - 2014 11 14
イベント2014 24th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2014 - Reims, France
継続期間: 2014 9 212014 9 24

出版物シリーズ

名前IEEE International Workshop on Machine Learning for Signal Processing, MLSP
ISSN(印刷版)2161-0363
ISSN(電子版)2161-0371

Conference

Conference2014 24th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2014
国/地域France
CityReims
Period14/9/2114/9/24

ASJC Scopus subject areas

  • 人間とコンピュータの相互作用
  • 信号処理

フィンガープリント

「Parametric speech synthesis using local and global sparse Gaussian processes」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル