Fine-grained Textual Knowledge Transfer to Improve RNN Transducers for Speech Recognition and Understanding
- Vishal Sunder
- Samuel Thomas
- et al.
- 2023
- ICASSP 2023
My Background
I've been a researcher at IBM since 1999. Before that, I was working on my PhD in computer science at the International Computer Science Institute and the University of California, Berkeley. I earned my undergraduate degree in electrical engineering at Michigan State University.
Things I Do
I do research on machine learning and large vocabulary speech recognition, with a focus on acoustic modeling and robustness. I currently serve as a senior area editor for IEEE/ACM Transactions on Audio, Speech, and Language Processing, an action editor for Transactions of Machine Learning Research, and an associate editor for IEEE Transactions on Pattern Analysis and Machine Intelligence.