This line of research focuses on efficient and accurate models for learning with sequences.
- Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions, Awni Hannun, Ann Lee, Qiantong Xu, Ronan Collobert. Interspeech 2019. (paper, code)
- A Fully Differentiable Beam Search Decoder, Ronan Collobert, Awni Hannun, Gabriel Synnaeve. ICML 2019. (paper, blog)
- Transcribing Real-valued Sequences with Deep Neural Networks, Awni Y. Hannun. PhD Thesis, Stanford University, 2018. (pdf, LaTex)
- Sequence Modeling With CTC, Awni Y. Hannun. Distill, 2017. (html, code)