Linear neural networks for spectral envelope estimation

• Emoto Takahiro

  Institute of Technology and Science, The University of Tokushima

• Abeyratne Udantha R.

  School of Info. Tech. and Electrical Engineering, The University of Queensland

• Akutagawa Masatake

  Institute of Technology and Science, The University of Tokushima

• Konaka Shinsuke

  Institute of Technology and Science, The University of Tokushima

• Kinouchi Yohsuke

  Institute of Technology and Science, The University of Tokushima

抄録

The spectral envelope is mainly determined by the shape of vocal tract and it is generally represented by linear estimation methods such as an autoregressive (AR) modeling. Neural network (NN) is general tools for modeling nonlinear function. Nonlinear aspects of NN have been emphasized. However, in this study, a novel approach to spectral estimation, which is based on the use of a linear feed-forward NN is discussed. Example of the linear network for estimating the spectral envelope of vowel sound is presented. The proposed linear NN technique leads to interesting new paradigms which could not have been considered in advance.

収録刊行物

• IEICE Electronics Express

  IEICE Electronics Express 7 (10), 691-696, 2010

  一般社団法人 電子情報通信学会

キーワード

• linear neural network
• spectral envelope
• vowel sound

詳細情報

• CRID: 1390001205214772608
• NII論文ID: 130000254761
• DOI: 10.1587/elex.7.691
• ISSN: 13492543
• Web Site: http://www.jstage.jst.go.jp/article/elex/7/10/7_10_691/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可