Selective Data Augmentation for Robust Speech Translation

no code implementations • 22 Mar 2023 • Rajul Acharya, Ashish Panda, Sunil Kumar Kopparapu

Though resource intensive, e2e-ST systems have the inherent ability to retain para and non-linguistic characteristics of the speech unlike cascade systems.

Data Augmentation Machine Translation +1

Synthetic speech detection using meta-learning with prototypical loss

no code implementations • 24 Jan 2022 • Monisankha Pal, Aditya Raikar, Ashish Panda, Sunil Kumar Kopparapu

Furthermore, the proposed system with data augmentation outperforms the ASVspoof 2021 challenge best baseline both in the progress and evaluation phase of the LA task.

Data Augmentation Meta-Learning +2