Anuj Diwan
Anuj Diwan
Home
CV
Publications
Experience
Contact
Light
Dark
Automatic
3
Unit-based Speech-to-Speech Translation Without Parallel Data
We propose an unsupervised speech-to-speech translation (S2ST) system that does not rely on parallel data between the source and target …
Anuj Diwan
,
Anirudh Srinivasan
,
David Harwath
,
Eunsol Choi
PDF
Improved Masking Strategies for Self-Supervised Speech Representation Learning
Models trained using self-supervised speech representation learning algorithms have achieved state-of-the-art performance on …
Anuj Diwan
,
David Harwath
,
Eunsol Choi
Dec 1, 2021
PDF
Slides
Cite
×