Audio Visual

At my current work (IBM research labs) I research deep learning methods to fuze the audio and visual streams of a camera. Our main use cases are security¹² and media enhancement.

1 Amit Aides, Hagai Aronowitz, “Text-Dependent Audiovisual Synchrony Detection for Spoofing Detection in Mobile Person Recognition,” Proc. INTERSPEECH (2016). ↩

2 Amit Aides, David Dov, Hagai Aronowitz, “Robust Audiovisual Liveness Detection for Biometric Authentication Using Deep Joint Embedding and Dynamic Time Warping,” Proc. ICASSP (2018). ↩