About Me

I am currently a researcher at Siri Speech, Apple with a focus on advancing large-scale, production-oriented automatic speech recognition (ASR) models. My research centers on two key areas to ensure robust and scalable solutions for real-world applications:

• active learning to tackle challenges such as uncertainty modeling (e.g., estimating label (or transcription) noise) and optimizing data selection within a semi-supervised framework that incorporates feedback and
• distributed (federated) learning to address critical real-world concerns including user privacy, data and device heterogeneity, personalization, and interpretability.

I joined Apple’s Class of 2022 AIML Residents in July 2022 after earning a Master of Science (MS) degree from the School of Electrical and Computer Engineering at Purdue Univesity. My thesis titled “Towards Privacy and Communication Efficiency in Distributed Representation Learning.” was completed under the supervision of Dr. Christopher Brinton. During graduate studies, I also actively collaborated with Dr. David Inouye, Dr. Qiang Qiu, Dr. Saurabh Bagchi, and Dr. Seyyedali Hosseinalipour, broadening my expertise across multiple domains.

Academic Service