Parametric speech synthesis based on Gaussian process regression using global variance and hyperparameter optimization

Tomoki Koriyama, Takashi Nose, Takao Kobayashi

研究成果: Conference contribution

9 被引用数 (Scopus)

抄録

This paper examines two issues of a statistical speech synthesis approach based Gaussian process (GP) regression. Although GP-based speech synthesis can give higher performance in generating spectral parameters than the HMM-based one, a number of issues still remain. In this paper, we incorporate global variance (GV) feature to overcome over-smoothing problem into the parameter generation. Furthermore, in order to utilize an appropriate kernel function in accordance with actual data, we propose an EM-based kernel hyperparameter optimization technique. Objective and subjective evaluation results show that using GV and hyperparameter estimation enhanced the performance in spectral feature generation.

本文言語English
ホスト出版物のタイトル2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
出版社Institute of Electrical and Electronics Engineers Inc.
ページ3834-3838
ページ数5
ISBN(印刷版)9781479928927
DOI
出版ステータスPublished - 2014
イベント2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy
継続期間: 2014 5 42014 5 9

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN(印刷版)1520-6149

Conference

Conference2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
国/地域Italy
CityFlorence
Period14/5/414/5/9

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Parametric speech synthesis based on Gaussian process regression using global variance and hyperparameter optimization」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