SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces

no code implementations • 23 Jul 2023 • Ivan Vallés-Pérez, Grzegorz Beringer, Piotr Bilinski, Gary Cook, Roberto Barra-Chicote

We train a CLIP-based model with the aim to learn shared representations of phonetic and acoustic spaces.

Cross Attention Transformers for Multi-modal Unsupervised Whole-Body PET Anomaly Detection

no code implementations • 14 Apr 2023 • Ashay Patel, Petru-Danial Tudiosu, Walter H. L. Pinaya, Gary Cook, Vicky Goh, Sebastien Ourselin, M. Jorge Cardoso

In addition, we show the efficacy of this approach on out-of-sample data showcasing the generalizability of this approach with limited training data.

Density Estimation Unsupervised Anomaly Detection