3 accepted papers
This paper presents an improved approach to multimodal active speaker detection in egocentric videos, specifically designed to be robust against the rapid movements and motion blur commonly found in such videos. We propose two key techniques to improve the model’s resilience: (i) spatially fixing th…
MetricGAN, a notable generative approach, provides an effective framework to train speech enhancement models to produce high metric scores. However, we identify two key limitations of current MetricGAN-family models, i.e. neglecting certain mainstream metrics during evaluation and conducting evaluat…
Unknown global permutation of the separated sources, time-varying source activity and under determination are common problems affecting on-line Independent Vector Analysis when applied to real-world speech enhancement. In this work we propose to extend the signal model of IVA by introducing addition…