ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Localization of multiple sound sources based on inter-channel correlation using a distributed microphone system

Kook Cho, Hajime Okumura, Takanobu Nishiura, Yoichi Yamashita

Recently the importance of hands-free speech interfaces is increasingly recognized. However, in real environments, the presence of ambient noises and room reverberations seriously degrades the performance of the hands-free speech recognition. Reliable sound source localization is necessary to maximize the effect of noise reduction. This paper proposes a new method of multiple sound source localization using a distributed microphone system that is a recording system with multiple microphones dispersed to a wide space. The proposed method localizes a sound source by finding the position that maximizes the accumulated correlation coefficient between multiple channel pairs. After the estimation of the first sound source, a model of the accumulated correlation for a single sound source is subtracted from the observed distribution of the accumulated correlation. Subsequently, the second sound source is searched again. To evaluate the effectiveness of the proposed method, experiments of multiple sound source localization were carried out in an actual office room. The result shows that multiple sound source localization accuracy is about 96.0%. The proposed method could realize the multiple sound source localization robustly and stably.


doi: 10.21437/Interspeech.2008-57

Cite as: Cho, K., Okumura, H., Nishiura, T., Yamashita, Y. (2008) Localization of multiple sound sources based on inter-channel correlation using a distributed microphone system. Proc. Interspeech 2008, 443-446, doi: 10.21437/Interspeech.2008-57

@inproceedings{cho08_interspeech,
  author={Kook Cho and Hajime Okumura and Takanobu Nishiura and Yoichi Yamashita},
  title={{Localization of multiple sound sources based on inter-channel correlation using a distributed microphone system}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={443--446},
  doi={10.21437/Interspeech.2008-57}
}