Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
Yangyang Shi, Chunyang Wu, Dilin Wang, Alex Xiao, Jay Mahadeokar, Xiaohui Zhang, Chunxi Liu, Ke Li, Yuan Shangguan, Varun Nagaraja, Ozlem Kalinli, Mike Seltzer
People
Varun Nagaraja
Research Scientist
My research interests are in developing computationally efficient machine learning models for deploying on edge devices. I currently have active collaborations with the Speech and the Audio Research teams. I have previously worked on building wakeword detection models for low power devices. Even before that, I worked on many computer vision problems for my graduate studies at the University of Maryland in College Park.
Latest Publications
ICASSP - 2022
Collaborative Training of Acoustic Encoders for Speech Recognition
Varun Nagaraja, Yangyang Shi, Ganesh Venkatesh, Ozlem Kalinli, Michael L. Seltzer, Vikas Chandra
Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
Yangyang Shi, Varun Nagaraja, Chunyang Wu, Jay Mahadeokar, Duc Le, Rohit Prabhavalkar, Alex Xiao, Ching-Feng Yeh, Julian Chan, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer