Objective Estimation of Word Intelligibility for Noise-Reduced Speech

• YAMADA Takeshi

  Graduate School of Systems and Information Engineering, University of Tsukuba

• KUMAKURA Masakazu

  Fujitsu Limited

• KITAWAKI Nobuhiko

  Graduate School of Systems and Information Engineering, University of Tsukuba

Abstract

It is essential to ensure a satisfactory QoS (Quality of Service) when offering a speech communication system with a noise reduction algorithm. In this paper, we propose a new obejective test methodology for noise-reduced speech that estimates word intelligibility by using a distortion measure. Experimental results confirmed that the proposed methodology gives an accurate estimate with independence of noise reduction algorithms and noise types.

Journal

• IEICE Transactions on Communications

  IEICE Transactions on Communications E91-B (12), 4075-4077, 2008

  The Institute of Electronics, Information and Communication Engineers

Keywords

• objective estimation
• word intelligibility
• noise reduction
• PESQ

Details

• CRID: 1390282679351705216
• NII Article ID: 10026834651
• NII Book ID: AA10826261
• DOI: 10.1093/ietcom/e91-b.12.4075
• ISSN: 17451345
• ISSN: 09168516
• HANDLE: 2241/105184
• Web Site: https://tsukuba.repo.nii.ac.jp/records/19289
• Web Site: https://www.jstage.jst.go.jp/article/transcom/E91.B/12/E91.B_12_4075/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • IRDB
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed