no code implementations • 11 Apr 2022 • Shakti Kumar, Hussain Zaidi
Few shot learning is an important problem in machine learning as large labelled datasets take considerable time and effort to assemble.
no code implementations • Findings (ACL) 2021 • Shakti Kumar, Jithin Pradeep, Hussain Zaidi
State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable text-to-speech (TTS) synthesis.
no code implementations • 17 Feb 2020 • Shi Yu, Yuxin Chen, Hussain Zaidi
Our main novel contribution is the discussion about uncertainty measure for BERT, where three different approaches are systematically compared on real problems.