Research for improvement of the body-conducted speech microphone using Optical Fiber Grating at low SNR environment

• Project/Area Number: 24700181
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Hiroshima City University (2014-2015); Kagawa National College of Technology (2012-2013)
• Principal Investigator: Nakayama Masashi 広島市立大学, 情報科学研究科, 助教 (20508163)
• Project Period (FY): 2012-04-01 – 2016-03-31
• Project Status: Completed (Fiscal Year 2015)
• Budget Amount: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000); Fiscal Year 2014: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000); Fiscal Year 2013: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2012: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
• Keywords: 音声 / 骨伝導音 / 音声認識 / 明瞭化 / 骨伝導 / 骨伝導光音 / 明瞭性 / 単語了解度 / 音声コミュニケーション / 日本語 / 母音

Outline of Final Research Achievements

This academic year as extended term of the grand was experimented the subjective evaluations for the effectiveness of sound quality improvement using proposal method. The experimental results confirmed to achieve the improved at clarity the sounds between treated and non-treated. The derivatives gives new findings for continuous to next project. So, we contentiously the project which are extended to estimate more clear sound with the new approaching.

Research Products

• [Presentation] Improvement of body-conducted speech recognition using modelestimation (2015)
  • Author(s): Masashi Nakayama, Satoshi Nakatani and Shunsuke Ishimitsu
  • Organizer: Ｔｈｅ 43rd International Congress on Noise Control Engineering (Inter-noise2014)
  • Place of Presentation: Melborune, Australia
  • Year and Date: 2015-11-16
  • Int'l Joint Research
• [Presentation] Improvement of body-conducted speech recognition using modelestimation (2014)
  • Author(s): Masashi Nakayama, Satoshi Nakatani, and Shunsuke Ishimitsu
  • Organizer: 43rd International Congress on Noise Control Engineering
  • Place of Presentation: Melbourne, Australia
  • Year and Date: 2014-11-16 – 2014-11-19
• [Presentation] 骨伝導音認識性能改善のための音響モデルの再推定に関する基礎検討 (2014)
  • Author(s): 中山仁史，石光俊介，中谷聡志
  • Organizer: 平成26年電気学会全国大会
  • Place of Presentation: 愛媛大学
• [Presentation] Formant frequencies of sung vowels intonated by six traditional Japanese Shigin singers. Part I: Dataset construction and analysis method (2013)
  • Author(s): Masashi Nakayama, Kosuke Kato, and Masaru Matsunaga
  • Organizer: Stockholm Music Acoustics Conference 2013 (SMAC2013)
  • Place of Presentation: Stockholm, Sweden
• [Presentation] Formant frequencies of sung vowels intonated by six traditional Japanese Shigin singers. Part II: Results of analysis and statistical investigations (2013)
  • Author(s): Kosuke Kato, Masashi Nakayama, and Masaru Matsunaga
  • Organizer: Stockholm Music Acoustics Conference 2013 (SMAC2013)
  • Place of Presentation: Stockholm, Sweden
• [Presentation] Extracting the fundamental frequency of steady-state portions of traditional Japanese singing Shigin (2013)
  • Author(s): Masashi Nakayama, Kosuke Kato and Masaru Matsunaga
  • Organizer: 2013 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing
  • Place of Presentation: The Island of Hawaii, USA
• [Presentation] Sound quality improvement for the body-conducted speech of a sentence unit using differential acceleration (2012)
  • Author(s): Masashi Nakayama, Shunsuke Ishimitsu and Seiji Nakagawa
  • Organizer: 2012 ICME International Conference on Complex Medical Engineering (ICME CME 2012)
  • Place of Presentation: ANA Crowne Plaza Hotel, Kobe, Japan