6 citations · 8 across the 5 of their papers we have counts for
5 papers
StepShield: When, Not Whether to Intervene on Rogue Agents
Gloria Felicia, Zitha Sasindran, Jinfeng He +3
Agent safety benchmarks measure whether a monitor detects harm, not when. Yet timing is the difference between intervention and autopsy. We introduce StepShield, the first benchmar…
SeMaScore : a new evaluation metric for automatic speech recognition tasks
Zitha Sasindran, Harsha Yelchuri, T. V. Prabhakar
In this study, we present SeMaScore, generated using a segment-wise mapping and scoring algorithm that serves as an evaluation metric for automatic speech recognition tasks. SeMaSc…
Ed-Fed: A generic federated learning framework with resource-aware client selection for edge devices
Zitha Sasindran, Harsha Yelchuri, T. V. Prabhakar
Federated learning (FL) has evolved as a prominent method for edge devices to cooperatively create a unified prediction model while securing their sensitive training data local to…
MobileASR: A resource-aware on-device learning framework for user voice personalization applications on mobile phones
Zitha Sasindran, Harsha Yelchuri, Pooja Rao +1
We describe a comprehensive methodology for developing user-voice personalized automatic speech recognition (ASR) models by effectively training models on mobile phones, allowing u…
H_eval: A new hybrid evaluation metric for automatic speech recognition tasks
Zitha Sasindran, Harsha Yelchuri, T. V. Prabhakar +1
Many studies have examined the shortcomings of word error rate (WER) as an evaluation metric for automatic speech recognition (ASR) systems. Since WER considers only literal word-l…