Anonymous

In this video, we showcase the output of our system, featuring HRTF and 3D audio technologies, alongside two CVPR papers: Mono2Binaural and PseudoBinaural. Additionally, we compare these with ground truth audio, which is generated through manual mixing and recording, as well as a mono example.

The presentation is divided into two sections:

Speech: The stimuli are sourced from YouTube.
Music: The stimuli are collected from the Fair-play dataset.