Sentence intelligibility prediction model using time series analysis for hand-held intelligibility meter

2018 Fiscal Year Final Research Report

• Project/Area Number: 16K21584
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Architectural environment/Equipment; Perceptual information processing
• Research Institution: Muroran Institute of Technology
• Principal Investigator: Kobayashi Yosuke 室蘭工業大学, 大学院工学研究科, 助教 (10735103)
• Research Collaborator: KONDO Kazuhiro ; SAKAMOTO Shuichi ; Ohta Kengo
• Project Period (FY): 2016-04-01 – 2019-03-31
• Keywords: 音声了解度 / 音声明瞭度 / 機械学習 / 屋外拡声システム / PAシステム / 予測モデル

Outline of Final Research Achievements

Subjective speech quality assessment has been used widely for the development of public-address (PA) systems, speech masking systems, hearing aid, mobile-phone, etc.
However, as this assessment is difficult in many cases, we propose an objective speech intelligibility evaluation system that includes a machine learning technique. Through outdoor-field recorded signal experiments, the effectiveness of these approaches could be verified.

Free Research Field

音声情報処理

Academic Significance and Societal Importance of the Research Achievements

駅や空港，学校など音声を放送する拡声システムは様々なところに実装されているが，必ずしも聴き取りやすいとは言い難い。本研究ではより聴き取りやすい拡声システムの設計に利用可能な音声の了解度（聴き取りやすさ or 聴き取りにくさ）の計測器を機械学習技術を利用して開発する。これにより身近な音声システムが聴き取りやすく最適化されることで国民生活の向上を目指す。