Conference paper
Binaural detection of speech sources in complex acoustic scenes
University of Oldenburg, 26111, Germany1
Eindhoven University of Technology and Philips Research, The Netherlands2
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.
| Language: | English |
|---|---|
| Year: | 2011 |
| Pages: | 241-244 |
| Proceedings: | 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) |
| ISBN: | 1457706911 , 145770692X , 145770692x , 1457706938 , 9781457706912 , 9781457706929 and 9781457706936 |
| ISSN: | 19471610 and 19311168 |
| Types: | Conference paper |
| DOI: | 10.1109/ASPAA.2011.6082276 |
Acoustics Azimuth Feature extraction Histograms Noise Speech Speech recognition acoustic signal detection binaural front-end binaural localization binaural signals complex acoustic scenes computational auditory scene analysis interfering noise sources missing data recognition sound source activity detection speech detection speech processing speech source binaural detection
