Daniel’s thesis focuses on the use of binaural audio for acoustic scene analysis, with multiple joint tasks that jointly perform sound event detection, acoustic scene classification, direction-of-arrival estimation, and sound distance estimation. One key innovation is the use of listener motion cues such as the head rotations and the listener’s movement through space, to mimic human strategies for resolving auditory ambiguities.
The opponents were Professor Nilesh Madhu from Ghent University, Belgium and Professor Jung-Woo Choi from Korea Advanced Institute of Science & Technology (KAIST), South Korea. The discussion was fierce, and the opponents even needed a break (!!) before concluding that indeed, Daniel did good work.
The thesis is available online: Binaural audio for multi-task acoustic scene analysis
