Jinyu Li
Partner Applied Science Manager
Talks
- IEEE SPS webinar “End-to-End Automatic Speech Recognition”, Slides, Video, 2024.
- Invited talk at APSIPA ASC 2023 for receiving the APSIPA Sadaoki Furui Prize Paper Award for the paper “Recent Advances in End-to-End Automatic Speech Recognition” published in APSIPA Transactions on Signal and Information Processing, 2022.
- Large-Scale Streaming End-to-End Speech Translation, Slides. Invited talk at Shanghai Jiaotong University and National Taiwan University, 2023.
- Decoder-only Modeling for Speech, Slides. Invited talk at Shanghai Jiaotong University and National Taiwan University, 2023.
- Advancing end-to-end automatic speech recognition and beyond, Slides, Video. Keynote talk at International Symposium on Chinese Spoken Language Processing (ISCSLP), 2022.
- Recent Advances in End-to-End Automatic Speech Recognition (video), at Center for Signal and Information Processing, Georgia Institute of Technology, 2021.
- Advancing end-to-end automatic speech recognition, Keynote talk at the conference on Computational Linguistics and Speech Processing, 2021.
- Developing streaming end-to-end models for automatic speech recognition in industry, Keynote talk at Accented English Speech Recognition Challenge Workshop, 2020.
- Deep Learning Acoustic Model in Microsoft Cortana Voice Assistant, at Johns Hopkins University, 2017.
- Deep Neural Network for Automatic Speech Recognition: from the Industry’s View, at Nanyang Technological University, 2014.