This is it! My models are learning to think, they can recognize emotions, enhance my voice, find structure in data….. they can even predict the future. Aweome! I can go an a holiday.

April 11, 2021

Emotions are enmeshed in the neural networks of uncertainty

view teaser image A smart Speech emotion recognition system that can tell how confident it is about its predictions Selective prediction models can be most useful in real-world applications. A model with smartness to abstain from prediction when in doubt can facilitate human-in-the-loop solutions Utilized Monte Carlo approximation to variational inference to implement create a smart emotion recognition system and demonstrated its benefits using reject options.

September 12, 2020

Knowledge Distillation with Latent Representations of Emotions

view teaser image Ensemble of students taught by probabilistic teachers reduces confusion among students and at the same time improves their performance as well. Speech emotion recognition system that gives scalable, reliable and consistent predictions, tailoring it to real-world applications Knowledge transfer between teacher and student using the learned latent emotional representations by the teachers Incorporating model diversity and preserving prediction uncertainty using Monte Carlo dropout and emsembling

September 10, 2020

Coming soon...

Uncertainty is Contagious: A novel generative modeling approach using soft-labels to model prediction uncertainties for speech emotion recognition This study presents a generative modeling approach using VAEs to train emotion recognition models on soft-labels (true annotator distributions) to learn from the intricate confusion between labelers. Presents an interest finding about using uncertainties to do transfer learning (more about this soon…) Representation learning for affective speech signal analysis and processing

Projects

Research projects in Deep learning for Affective Computing