Hi, I'm Sameep

Sameep Chattopadhyay

Ph.D. Student, Computer Science
Paul G. Allen School of Computer Science & Engineering, University of Washington

I am a Ph.D. student at the Paul G. Allen School of Computer Science & Engineering at the University of Washington, advised by Prof. Mari Ostendorf, and closely collaborating with Prof. Noah A. Smith. I build speech-based multimodal AI systems for conversation: voice agents that listen in real time, audio language models that treat every speaker fairly, and speech recognition that works beyond high-resource languages.

My recent work studies stateful inference for low-latency streaming ASR in voice agents and accent bias in audio language models; the latter received an Outstanding Paper Award at EMNLP 2026. Before UW, I earned a B.Tech. + M.Tech. dual degree in Electrical Engineering (Minor in AI & Data Science) from IIT Bombay, graduating as the department valedictorian. There I worked on multilingual ASR with Prof. Preethi Jyothi and on on-device inference with Prof. Sharayu Moharir. I have also spent time at UT Austin, Texas Instruments, Kyushu Institute of Technology, and Siemens.

I am looking for research internships for Summer 2027! Feel free to reach out.

Voice Agents Audio Language Models Streaming ASR Multilingual AI Test-time Adaptation

sameepch@uw.edu · sameepch@cs.washington.edu

Photo of Sameep Chattopadhyay

News

Selected Publications

EMNLP 2026

Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents

Sameep Chattopadhyay, Alexander Erdmann, Mari Ostendorf

Conference on Empirical Methods in Natural Language Processing (EMNLP), Main

EMNLP 2026

The Cost of Sounding Different: Accent Bias in Audio Language Models

Aruna Srivastava*, Orevaoghene Ahia*, Li Lucy, Ashley Christendat, Sameep Chattopadhyay, Farhan Samir, Tejumade Afonja, Valentin Hofmann, Sachin Kumar, Noah A. Smith, Yulia Tsvetkov

Conference on Empirical Methods in Natural Language Processing (EMNLP), Main Outstanding Paper Award

NeurIPS-W 2025

Observation-free Attacks on Online Learning to Rank

Sameep Chattopadhyay, Nikhil Karamchandani, Sharayu Moharir

NeurIPS 2025 ACA Workshop Oral

NAACL 2025

AMPS: ASR with Multimodal Paraphrase Supervision

Abhishek Gupta*, Amruta Parulekar*, Sameep Chattopadhyay, Preethi Jyothi

Annual Conference of the Nations of the Americas Chapter of the ACL (NAACL)