@inproceedings{11931,
  abstract     = {{The paper is concerned with binaural signal processing for a bimodal human-robot interface with hearing and vision. The two microphone signals are processed to obtain an enhanced single-channel input signal for the subsequent speech recognizer and to localize the acoustic source, an important information for establishing a natural human-robot communication. We utilize a robust adaptive algorithm for filter-and-sum beamforming (FSB) and extract speaker direction information from the resulting FIR filter coefficients. Further, particle filtering is applied which conducts a nonlinear Bayesian tracking of speaker movement. Good location accuracy can be achieved even in highly reverberant environments. The results obtained outperform the conventional generalized cross correlation (GCC) method.}},
  author       = {{Warsitz, Ernst and Haeb-Umbach, Reinhold}},
  booktitle    = {{IEEE Workshop on Multimedia Signal Processing (MMSP 2004)}},
  keywords     = {{bimodal human-robot interface, binaural signal processing, enhanced single-channel input signal, filter-and-sum beamforming, filtering theory, FIR filter coefficient, generalized cross correlation method, microphones, microphone signal, nonlinear Bayesian tracking, particle filtering, robust adaptive algorithm, robust speaker direction estimation, signal processing, speech enhancement, speech recognition, speech recognizer, user interfaces}},
  pages        = {{367--370}},
  title        = {{{Robust speaker direction estimation with particle filtering}}},
  doi          = {{10.1109/MMSP.2004.1436569}},
  year         = {{2004}},
}