Learning with Less Labelled Data
This line of research aims to train accurate machine learning models with less labelled data, particularly data which requires resource intensive annotation.
Selected Publications
- Semi-supervised speech recognition via local prior matching, Wei-Ning Hsu, Ann Lee, Gabriel Synnaeve, Awni Hannun. SLT 2021. (paper)
- Iterative Pseudo-Labeling for Speech Recognition, Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn, Awni Hannun, Gabriel Synnaeve, Ronan Collobert. Interspeech 2020. (paper)
- Self-Training for End-to-End Speech Recognition, Jacob Kahn, Ann Lee, Awni Hannun. ICASSP 2020. (paper)