Unsupervised Instance Discriminative Learning for Depression Detection from Speech Signals

no code implementations • 27 Jun 2022 • Jinhan Wang, Vijay Ravi, Jonathan Flint, Abeer Alwan

To learn instance-spread-out embeddings, we explore methods for sampling instances for a training batch (distinct speaker-based and random sampling).

Data Augmentation Depression Detection +1

A Step Towards Preserving Speakers' Identity While Detecting Depression Via Speaker Disentanglement

no code implementations • 20 Jun 2022 • Vijay Ravi, Jinhan Wang, Jonathan Flint, Abeer Alwan

With adversarial training, depression classification improves for every feature when compared to the baseline.

Depression Detection Disentanglement +1

FrAUG: A Frame Rate Based Data Augmentation Method for Depression Detection from Speech Signals

no code implementations • 11 Feb 2022 • Vijay Ravi, Jinhan Wang, Jonathan Flint, Abeer Alwan

The improvements for the CONVERGE (Mandarin) dataset when using the x-vector embeddings with CNN as the backend and MFCCs as input features were 9. 32% (validation) and 12. 99% (test).

Data Augmentation Depression Detection