Main Page
From ManyEars_Wiki
Contents |
The ManyEars Project: Microphone Array-Based Audition for Mobile Robots
It took many years and many man-years to use many ears on a mobile robot
About
Intelligent systems would benefit from being able to localize and track sound sources in real life settings. Such a capability can help localizing a person or an interesting event in the environment, and also provides enhanced processing for other capabilities such as speech recognition. To give this capability to a computing system, the challenge is not only to localize simultaneous sound sources, but to track them over time. The ManyEars project propose a robust sound source localization and tracking method using an array of eight microphones. The method is based on a frequency-domain implementation of a steered beamformer along with a particle filter-based tracking algorithm. Tests on a mobile robot show that the algorithm can localize and track in real-time multiple moving sources of different types over a range of 7 meters. These new capabilities allowed the robot to interact using more natural means with people in real life settings.
The ManyEars project was setup to provide source code for AUDIBLE project. It provides FlowDesigner building-blocks for microphone array processing. This includes sound source localisation, tracking and separation.
Authors
Click here for the list of authors.
News
- 2008/06/02: ManyEars3D prototype added to SVN.
- 2008/05/14: Installation Instructions were added.
- 2007/10/24: ManyEars 0.2 is now available and includes a QT monitoring GUI and Linux/WIN32/OSX sources and binary releases.
- 2007/05/31: ManyEars 0.1 is now available!
- 2007/05/01: Source code uploaded to the Subversion repository. Need cleaning up a bit (especially the build)
- 2007/04/11: Website is up. The source code should be available in May.
Project Information
Getting Started
Please refer to the Installation Instructions.
Hardware Requirements
Hardware requirements are available here.
License
ManyEars is distributed under the GNU General Public License (GPL) and a patent license is provided for use in GPL software. See the full license for details.
Download
Click here to access the download section and release informations.
Publications
Most of the publications about the method are available on Jean-Marc Valin's website. The most relevant ones are given below:
- J.-M. Valin, S. Yamamoto, J. Rouat, F. Michaud, K. Nakadai, H. G. Okuno, Robust Recognition of Simultaneous Speech By a Mobile Robot, IEEE Transactions on Robotics, Vol. 23, No. 4, pp. 742-752, 2007.</li>
- J.-M. Valin, F. Michaud, J. Rouat, Robust Localization and Tracking of Simultaneous Moving Sound Sources Using Beamforming and Particle Filtering. Robotics and Autonomous Systems Journal (Elsevier), Vol. 55, No. 3, pp. 216-228, 2007.
- F. Michaud, C. Cote, D. Letourneau, Y. Brosseau, J.-M. Valin, E. Beaudry, C. Raievsky, A. Ponchon, P. Moisan, P. Lepage, Y. Morin, F. Gagnon, P. Giguere, M.-A. Roux, S. Caron, P. Frenette, F. Kabanza, Spartacus attending the 2005 AAAI conference. Autonomous Robots (Springer), Vol. 22, No. 4, pp. 369-383, 2007.
- S. Yamamoto, K. Nakadai, M. Nakano, H. Tsujino, J.-M. Valin, K. Komatani, T. Ogata, H. G. Okuno, Simultaneous Speech Recognition based on Automatic Missing-Feature Mask Generation integrated with Sound Source Separation (in Japanese). Journal of Robotic Society of Japan, Vol. 25, No. 1, 2007.
- S. Yamamoto, K. Nakadai, M. Nakano, H. Tsujino, J.-M. Valin, R. Takeda, K. Komatani, T. Ogata, H. G. Okuno, Improving Location-Based Speech Recognition of Simultaneous Speech Signals by Parameter Optimization with Genetic Algorithm (in Japanese). Human Interface, Vol.8, No.2, pp. 203-212, 2006.
