NTT コミュニケーション科学基礎研究所　主幹研究員
   

• Speech enhancement
  1. Sound source separation based on harmonic structure and location of sound source [Sound Demonstrations]
  2. Single channel speech dereverberation based on harmonic structure [Sound Demonstrations]
  3. Microphone array based method
• Robust speech recognition in a real world
  1. Mixed speech recognition [PDF]
• Unified approach to speech recognition, speech synthesis and sound source separation
  1. HMM-STRAIGHT based speech recognition/synthesis system [PDF]
• Robust feature extraction of speech
  1. Fundamental frequency and voiced/unvoiced segments estimation based on dominant harmonic components [PDF]
  2. Fundamental frequency analysis for infant voice [PDF]
• Computational auditory scene analysis. [PhD Thesis]

   E-mail: nakatani.tomohiro@lab.ntt.co.jp
   Voice: +81 774 93 5134
   Fax: +81 774 93 5105
   中谷智広（なかたにともひろ）
   NTT コミュニケーション科学基礎研究所
   日本電信電話株式会社
   〒619-0237 京都府相楽郡精華町光台2-4