Speaker localization for far-field and near-field wideband sources using neural networks.
Güner Arslan, F. Ayhan Sakarya, Brian L. Evans · 1999
Many applications such as hands-free videoconferencing, speech processing in large rooms, and acoustic echo cancellation, use microphone arrays to track speaker locations in real-time. A speaker is a wideband source whichmaybein the near #eld or far #eld of the array. Current source localization approaches based on neural networks can meet realtime constraints but assume far-#eld narrowband sources. In this paper, we #1# apply neural networks for determining direction-of-arrival for near-#eld and far-#eld wideband speaker localization, and #2# compute the instantaneous cross-power spectra between adjacent pairs of sensors to form the feature vector. We optimized the overall speaker localization system o#-line to yield an absolute error of less than 6 degrees at an SNR of 10 dB and a sampling rate of 8000 Hz at each sensor. When performing speaker localization in real-time, the system would require 1 MFLOP#s.