In this paper we present a novel system that is able to simultaneously localize and detect a predefined number of speech sources in complex acoustic scenes based on binaural signals. The system operates in two steps: First, the acoustic scene is analyzed by a binaural front-end that detects relevant sound source activity. Second, a speech detection module selects source positions from a set of candidate positions that are most likely speech. The proposed method is evaluated in simulated multi-source scenarios consisting of two speech sources, three interfering noise sources and reverberation. © 2011 IEEE.
|Title of host publication||2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics|
|Publication status||Published - 2011|
|Event||2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics - New Paltz, United States|
Duration: 16 Oct 2011 → 19 Oct 2011
|Conference||2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics|
|Period||16/10/2011 → 19/10/2011|