Advertisement videos (ads) play an integral part in the domain of Intern...
Recent studies have explored the use of pre-trained embeddings for speec...
The process of human affect understanding involves the ability to infer
...
Audio event detection is a widely studied audio processing task, with
ap...
Speech-centric machine learning systems have revolutionized many leading...
Longform media such as movies have complex narrative structures, with ev...
Speech emotion recognition (SER) processes speech signals to detect and
...
Robust face clustering is a key step towards computational understanding...