Real-Time Human-Voice Enhancement for a Hose-Shaped Rescue Robot Based on Multi-Channel Low-Rank Sparse Decomposition

• bando Yoshiaki

  Kyoto University

• Ambe Yuichi

  Tohoku University

• Itoyama Katsutoshi

  Kyoto University

• Konyo Masashi

  Tohoku University

• Tadokoro Satoshi

  Tohoku University

• Nakadai Kazuhiro

  Tokyo Institute of Technology Honda Research Institute Japan

• Yoshii Kazuyoshi

  Kyoto University

• G. Okuno Hiroshi

  Waseda University

Bibliographic Information

Other Title

• 多チャネル低ランク・スパース分解に基づく柔軟索状レスキューロボットのためのリアルタイム音声強調

Abstract

This paper presents a real-time human-voice enhancement method for a hose-shaped rescue robot based on multi-channel low-rank sparse decomposition. Although microphone arrays equipped on hose-shaped robots are crucial for finding victims under collapsed buildings, human voices captured by the microphone array are contaminated by environment-dependent and non-stationary ego-noise. Our method decomposes multi-channel amplitude spectrograms into sparse and low-rank components (human voice and noise) without any prior training. This decomposition is conducted with a state-space model representing the dynamics of these components in a mini-batch manner. Experimental results show that the performance difference between our method and its offline version is less than 3dB in signal-to-distortion ratio.

Journal

• The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)

  The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) 2017 (0), 1P2-P05-, 2017

  The Japan Society of Mechanical Engineers

Keywords

• Hose-shaped rescue robot
• Human-voice enhancement
• Bayesian signal processing

Details

• CRID: 1390001205940260352
• NII Article ID: 130006220750
• DOI: 10.1299/jsmermd.2017.1p2-p05
• ISSN: 24243124
• Web Site: https://www.jstage.jst.go.jp/article/jsmermd/2017/0/2017_1P2-P05/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed