Linear neural networks for spectral envelope estimation

スポンサーリンク

概要

• 論文の詳細を見る

• 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.

著者

• Abeyratne Udantha

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

• Emoto Takahiro

  Institute of Technology and Science, The University of Tokushima

• 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

• Abeyratne Udantha

  School Of Info. And Electrical Engineering The University Of Queensland

• Abeyratne Udantha

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

関連論文

• いびき音解析による無呼吸の兆候抽出に関する基礎的検討
• 鼾音解析による閉塞型無呼吸症候群に関する新しい診断方法の開発
• Linear neural networks for spectral envelope estimation
• 腸蠕動音解析による薬剤投与前後の腸活動評価
• 時間周波数解析によるいびき・母音識別に関する基礎検討
• 時間周波数解析によるいびき・母音識別に関する基礎検討
• Inactivation of MS2 Phage and Cryptosporidium parvum Oocysts Using UV-A from High-Intensity Light-Emitting Diode for Water Disinfection
• MI sensor-aided screening system for assessing swallowing dysfunction: Application to the repetitive saliva-swallowing test

スポンサーリンク