Streaming Anchor Loss: Augmenting Supervision with Temporal Significance

no code implementations • 9 Oct 2023 • Utkarsh Oggy Sarawgi, John Berkowitz, Vineet Garg, Arnav Kundu, Minsik Cho, Sai Srujana Buddi, Saurabh Adya, Ahmed Tewfik

Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms.

Efficient Multimodal Neural Networks for Trigger-less Voice Assistants

no code implementations • 20 May 2023 • Sai Srujana Buddi, Utkarsh Oggy Sarawgi, Tashweena Heeramun, Karan Sawnhey, Ed Yanosik, Saravana Rathinam, Saurabh Adya

The adoption of multimodal interactions by Voice Assistants (VAs) is growing rapidly to enhance human-computer interactions.

Decision Making