This thesis focuses on representation learning for sequence data over ti...
Large self-supervised models are effective feature extractors, but their...
Acoustic Event Classification (AEC) has been widely used in devices such...
Standard acoustic event classification (AEC) solutions require large-sca...
Deep learning is very data hungry, and supervised learning especially
re...
We propose an approach for pre-training speech representations via a mas...
We study the problem of learning disentangled representations for data a...
This paper targets the problem of image set-based face verification and
...
We introduce a family of multitask variational methods for semi-supervis...
Prior work on controllable text generation usually assumes that the
cont...
We propose a generative model for a sentence that uses two latent variab...
Recent advances in deep generative models have shown promising potential...
Recent advances in deep generative models have shown promising potential...
Previous work has shown that it is possible to improve speech recognitio...
Previous work has shown that it is possible to improve speech recognitio...
We study the problem of acoustic feature learning in the setting where w...
We propose a novel method for network inference from partially observed ...
Learning the network structure underlying data is an important problem i...
This paper considers the problem of estimating multiple related Gaussian...