Study of noise reduction which can automatically control speech quality based on higher-order statistics pursuit

2015 Fiscal Year Final Research Report

• Project/Area Number: 26880027
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Single-year Grants
• Research Field: Perceptual information processing
• Research Institution: Tokuyama College of Technology
• Principal Investigator: Miyazaki Ryoichi 徳山工業高等専門学校, 情報電子工学科, 助教 (40734728)
• Project Period (FY): 2014-08-29 – 2016-03-31
• Keywords: 雑音抑圧 / 高次統計量 / 補聴システム

Outline of Final Research Achievements

In this study, I evaluated the accuracy of speech higher-ordrer statistics estimation in various environments. Also I inspected the efficacy of speech higher-order statistics estimation with the assumption that the complex spectra obey the generalized gaussian distribution.
From the objective evaluation, I confirm that the proposed method can estimate the higher-order statistics with high accuracy in each noise environment.

Free Research Field

音響信号処理