Development of real-time noise reduction method for robot auditory utilizing speech recognition system

• Project/Area Number: 22700186
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Single-year Grants
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Waseda University
• Principal Investigator: MATSUMOTO Tomomi 早稲田大学, 理工学術院, 助教 (10570905)
• Project Period (FY): 2010-04-01 – 2013-03-31
• Project Status: Completed (Fiscal Year 2013)
• Budget Amount: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000); Fiscal Year 2012: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2011: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2010: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
• Keywords: 雑音抑制 / 音声認識 / 最適化 / 音声信号処理 / 音声情報処理 / 信号処理 / パターン認識 / 知能ロボット / センシング情報処理

Research Abstract

In this study, we focus on noise reduction from external environment in robot auditory system, and developed noise reduction and parameter tuning method utilizing speech recognition system. The feature of this study is not to tune speech recognition system and noise reduction system independently, but to tune them in a comprehensive way. By integrating noise reduction system and noise reduction system totally, the applicable range of parameter tuning became wide. It is considered that the developed system will be applicable not only to robot auditory but also to car navigation system and biometric identification.

Research Products

• [Presentation] Monaural Blind Source Separation based on Frequency Spectrum Peak Shift and Power Fluctuation (2013)
  • Author(s): Terumi Umematsu, Guillermo Enriquez, Tomomi Matsumoto, Mitsuharu Matsumoto and Shuji Hashimoto
  • Organizer: International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'13)
  • Place of Presentation: Hawaii, USA (528-531)
  • Year and Date: 2013-03-08
• [Presentation] 分周波数スペクトルのピーク変動および強度変化比の類似性を用いたモノラル音源分離と分離性能向上の検討 (2013)
  • Author(s): 梅松旭美, エンリケズギエルモ, 松本友実, 松本光春, 橋本周司
  • Organizer: 日本音響学会2013年春季研究発表会
  • Place of Presentation: 東京 (721-724)
• [Presentation] Simulated annealing based parameter optimization of time-frequency ε-filter utilizing correlation coefficient (2012)
  • Author(s): Tomomi Matsumoto, Mitsuharu Matsumoto, Shuji Hashimoto
  • Organizer: International conference on signal processing and multimedia applications (SIGMAP2012)
  • Place of Presentation: Rome, Italy (237-241)
• [Presentation] 分離音間の相関係数を用いたモノラル音源分離の性能評価 (2012)
  • Author(s): 梅松旭美,阿部友実, 松本光春, 橋本周司
  • Organizer: 日本音響学会平成24(2012)年春季研究発表会講演論文集
  • Place of Presentation: 神奈川 (717-720)
• [Presentation] Simulated annealing based parameter optimization of time-frequency ε-filter utilizing correlation coefficient (2012)
  • Author(s): Tomomi Matsumoto, Mitsuharu Matsumoto, Shuji Hashimoto
  • Organizer: International conference on signal processing and multimedia applications (SIGMAP2012)
  • Place of Presentation: Rome, Italy
• [Presentation] 周波数スペクトルのピーク追随によるモノラル音源分離の性能評価 (2011)
  • Author(s): 梅松旭美,阿部友実, 松本光春, 橋本周司
  • Organizer: 日本音響学会平成23(2011)年秋季研究発表会講演論文集
  • Place of Presentation: 島根 (665-668)
• [Presentation] Application of cross TF ε-filter to impulse noise reduction (2011)
  • Author(s): Tomomi Abe, Mitsuharu Matsumoto, Shuji Hashimoto
  • Organizer: IASTED International Conference on Signal and Image Processing and Applications (SIPA2011)
  • Place of Presentation: Crete, Greece (173-178)
• [Presentation] Parameter setting of noise reduction filter using speech recognition system (2010)
  • Author(s): Tomomi Abe, Mitsuharu Matsumoto, Shuji Hashimoto
  • Organizer: International Conference on Neural Computation (ICNC2010)
  • Place of Presentation: Valencia, Spain
  • Year and Date: 2010-10-24
• [Presentation] Parameter setting of noise reduction filter using speech recognition system (2010)
  • Author(s): Tomomi Abe, Mitsuharu Matsumoto, Shuji Hashimoto
  • Organizer: International Conference on Neural Computation (ICNC2010)
  • Place of Presentation: Valencia, Spain (387-391)