• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Estimation of environmental conditions based on acoustic signals for speech dialog systems

Research Project

Project/Area Number 23500230
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Perception information processing/Intelligent robotics
Research InstitutionAichi University of Technology

Principal Investigator

JITSUHIRO Takatoshi  愛知工科大学, 工学部, 准教授 (60394996)

Co-Investigator(Renkei-kenkyūsha) TAKEDA Kazuya  名古屋大学, 大学院・情報科学研究科, 教授 (20273295)
Project Period (FY) 2011 – 2013
Project Status Completed (Fiscal Year 2013)
Budget Amount *help
¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2013: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2012: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2011: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Keywords音声認識 / 音声対話システム / 音源距離推定 / 単一マイクロホン / 音響モデル / VQコードブック / 音声情報処理
Research Abstract

The conditions of users and environments are not considered much in speech dialog systems. We propose the estimation method of environmental conditions based on acoustic signals. The distance from a user to a system is estimated using estimated an acoustic transfer function. At first, templates of frequency characteristics depending on the distance are created from impulse responses for each distance. To estimate the transfer functions, we calculate the difference between input speech and clean speech using clean speech models. This difference means the transfer function depending on the distance. The distance can be estimated from the nearest template. The almost 80 % accuracy was obtained in the discriminative experiments that was to decide if the distance is closer or far than 1 m.

Report

(4 results)
  • 2013 Annual Research Report   Final Research Report ( PDF )
  • 2012 Research-status Report
  • 2011 Research-status Report
  • Research Products

    (6 results)

All 2013 2012 Other

All Presentation (4 results) Remarks (2 results)

  • [Presentation] 単一マイクロホンによる音響モデルを用いた発話者までの距離推定2013

    • Author(s)
      李津, 實廣貴敏, 武田一哉
    • Organizer
      日本音響学会講演論文集
    • Place of Presentation
      東京工科大
    • Year and Date
      2013-03-13
    • Related Report
      2013 Final Research Report
  • [Presentation] 単一マイクロホンによる音響モデルを用いた発話者までの距離推定2013

    • Author(s)
      李津, 實廣貴敏, 武田一哉
    • Organizer
      日本音響学会2013年春季研究発表会講演論文集
    • Place of Presentation
      東京工科大学
    • Related Report
      2012 Research-status Report
  • [Presentation] 音響モデルを用いた発話者までの距離推定2012

    • Author(s)
      李津, 實廣貴敏
    • Organizer
      平成24年度 電気系学会東海支部連合大会
    • Place of Presentation
      豊橋技科大
    • Year and Date
      2012-09-25
    • Related Report
      2013 Final Research Report
  • [Presentation] 音響モデルを用いた発話者までの距離推定2012

    • Author(s)
      李津, 實廣貴敏
    • Organizer
      平成24年度 電気関係学会東海支部連合大会
    • Place of Presentation
      豊橋技術科学大学
    • Related Report
      2012 Research-status Report
  • [Remarks] ホームページ等愛知工科大学:實廣研究室:研究外部資金による研究

    • URL

      http://www1.aut.ac.jp/~jtlab/AUT_JTLAB/yan_jiu_zi_jin.html

    • Related Report
      2013 Final Research Report
  • [Remarks] 愛知工科大学:實廣研究室:研究外部資金による研究

    • URL

      http://www1.aut.ac.jp/~jtlab/AUT_JTLAB/yan_jiu_zi_jin.html

    • Related Report
      2013 Annual Research Report

URL: 

Published: 2011-08-05   Modified: 2019-07-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi