Transformers in Speech Processing: A Survey

no code implementations • 21 Mar 2023 • Siddique Latif, Aun Zaidi, Heriberto Cuayahuitl, Fahad Shamshad, Moazzam Shoukat, Junaid Qadir

The remarkable success of transformers in the field of natural language processing has sparked the interest of the speech-processing community, leading to an exploration of their potential for modeling long-range dependencies within speech sequences.

Automatic Speech Recognition Speech Enhancement +4

Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination

no code implementations • 31 Jul 2022 • Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayahuitl

Learning robotic tasks in the real world is still highly challenging and effective practical solutions remain to be found.

Imitation Learning reinforcement-learning +1

A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning

no code implementations • 6 Aug 2021 • Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayahuitl

We argue that it is crucial to automate the reward learning process so that new skills can be taught to robots by their users.

reinforcement-learning Reinforcement Learning (RL)