@INPROCEEDINGS{LehJoh06Experimental,
  author =    {Eric A. Lehmann and Anders M. Johansson},
  title =     {Experimental performance assessment of a particle filter with voice activity data fusion for acoustic speaker tracking},
  booktitle = {Proceedings of the IEEE Nordic Signal Processing Symposium (NORSIG'06)},
  pages =     {126--129},
  month =     {June},
  year =      {2006},
  address =   {Reykjavik, Iceland}
  abstract =  {The problem of acoustic source localization and tracking (ASLT) in reverberant environments by means of a microphone array constitutes a challenging task from many viewpoints. One of the main issues when considering real-world situations involving human speakers is the presence of silence gaps in the speech, which can easily send the tracking algorithm off-track, even in practical environments with low to moderate noise and reverberation levels. This work is concerned with an implementation of the ASLT algorithm proposed in [1], which circumvents this problem by integrating measurements from a voice activity detector (VAD) within the tracking algorithm framework. The tracking performance of this method is tested experimentally using audio data recorded in a real reverberant room. To this purpose, we describe a quick and efficient way of determining the ground-truth speaker location versus time, an operation that is not always easy to perform. The experimental results confirm the improved robustness of the method presented in [1] (compared to a previously proposed non-VAD ASLT algorithm) when tracking sources emitting real-world speech signals, which typically involve significant silence gaps between utterances.}
}