projects

Selected research and engineering projects across AI evaluation, safety, and speech.

Evaluation & Safety
project thumbnail

MedExpert

A clinician-annotated benchmark for evaluating the factuality and completeness of medical chatbots.
project thumbnail

Data Annotation: Rubrics, Interface & Processing

End-to-end human-data infrastructure for expert-grade evaluation.
project thumbnail

Analyzing Clinician–System Disagreements

Where automated medical evaluation diverges from expert judgment, and why scaling doesn't fix it.
project thumbnail

Agentic Evaluation Pipeline for Medical AI

An agentic triage layer that cuts expert annotation cost while preserving clinical grounding (ARPA-H CARE).

Speech & Robustness
project thumbnail

ASR for Noisy Radio Speech, TTS for Fine-Tuning

Turning noisy EMS radio into structured clinical data before the patient arrives.
project thumbnail

Personalized Keyword Spotting at Microsoft Azure

Wake-word detection that knows who's speaking, and resists noise and adversarial audio.
project thumbnail

Low-Resource Hindi ASR for Indian Farmers (mKRISHI)

Speech recognition deployed at scale for Indian agriculture.
project thumbnail

US Patents: Robust Speech Recognition

Foundational robustness work, patented.

Some project illustrations were generated with Google Gemini.