Active speech source localization by a dual coarse-to-fine search

Ramani Duraiswami, Dmitry N. Zotkin, Larry S. Davis

Abstract

Accurate and fast localization of multiple speech sound sources is a significant problem in videoconferencing systems. Based on the observation that the wavelengths of the sound from a speech source are comparable to the dimensions of the space being searched, and that the source is broadband, we develop an efficient search strategy that finds the source(s) in a given space. The search is made efficient by using coarse-to-fine strategies in both space and frequency. The algorithm is shown to be robust compared to typical delay-based estimators and fast enough for real-time implementation. Its performance can be further improved by using constraints from computer vision.
BibTeX
@inproceedings{duraiswami2001active,
  author = {Ramani Duraiswami and Dmitry N. Zotkin and Larry S. Davis},
  title = {{Active speech source localization by a dual coarse-to-fine search}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2001},
  doi = {10.1109/icassp.2001.940366},
}

Loading related content...

Figure