OxTalks will soon move to the new Halo platform and will become 'Oxford Events.' There will be a need for an OxTalks freeze. This was previously planned for Friday 14th November – a new date will be shared as soon as it is available (full details will be available on the Staff Gateway).
In the meantime, the OxTalks site will remain active and events will continue to be published.
If staff have any questions about the Oxford Events launch, please contact halo@digital.ox.ac.uk
In complex room settings, machine listening systems may experience a degradation in performance due to factors like room reverberations, background noise, and unwanted sounds. Concurrently, machine vision systems can suffer from issues like visual occlusions, insufficient lighting, and background clutter. Combining audio and visual data has the potential to overcome these limitations and enhance machine perception in complex audio-visual environments. In this talk, we will first discuss the machine cocktail party problem, and the development of speech source separation algorithms for extracting individual speech sources from sound mixtures. We will then discuss selected works related to audio-visual speech separation. This encompasses the fusion of audio-visual data for speech source separation, employing techniques such as Gaussian mixture models, dictionary learning, and deep learning.
