Payal Mohapatra

Payal Mohapatra

AI Researcher (Audio + Time Series)

About me

I am a fourth-year PhD candidate in Computer Engineering at Northwestern University, part of the IDEAS Lab and advised by Dr. Qi Zhu.

My research is focused on human-centric applications that bridge computer science and health. Specifically, I develop machine learning techniques for real-world challenges involving audio, healthcare, and time-series sensor data. These applications are pervasive but often come with challenges in data analysis and model development. I aim to design robust algorithms that handle issues like data quality, sparsity, and resource constraints. A significant part of my work explores the trade-offs between personalization and generalization in algorithm design, with an emphasis on making technology more inclusive for underrepresented users (e.g., atypical speakers in voice technology, and skin-tone diversity in optical heart rate monitoring). In addition to model performance, I prioritize explainability and resource efficiency.

Before my PhD, I worked as an IC design engineer at Analog Devices Inc., developing formal verification methods for application-specific ICs. I hold a Masters by Research in Electrical Engineering from Indian Institute of Technology, Madras, where I designed a sensing and algorithms framework for cardiac wearables.

You can reach me at payalmohapatra2026 at u dot northwestern dot edu.
Link to my CV (last updated December 2024)

Ongoing Projects

Learning from Irregular Time-Series

Designing a low-overhead technique to model the underlying process dynamics for irregular time-series, ranging from uniformly sampled to sparse or missing variates, to learn task-agnostic representations.

Aligning Heterogeneous Temporal Modalities

Developing strategies for general-purpose foundation models to leverage low-resource, information-dense modalities, such as silent-speech with LLMs or surrogate IMU models for visual pose estimation.

Practitioner's Guide to Manufacturing Workplace Safety

Collaborating with Boeing and MxD to create a browsable repository of COTS sensors and wearable-data analytics to enhance workplace safety by quantifying risk factors.

News

  • [December 2024] - Successfully passed my PhD Prospectus examination – 2/3 of the journey complete!
  • [October 2024] - Our paper Wearable Network for Multi-Level Physical Fatigue Prediction in Manufacturing Workers is accepted in PNAS Nexus journal. Featured by tech news outlets like TechXplore and Popular Science.
  • [August, 2024] - Excited to be selected as the EECS Rising Star 2024! Invited to the 2-day workshop hosted at MIT in October. Read more in this article by Northwestern.
  • [June, 2024] - Started my summer internship with Meta Reality Labs as Research Scientist.
  • [June, 2024] - Our paper on Missingness-resilient Video-enhanced Multimodal Disfluency Detection is accepted and chosen for oral presentation at InterSpeech’24.
  • [February, 2024] - My internship work with Meta Reality Labs on efficient event detection on smart glasses – Non-verbal Hands-free Control for Smart Glasses using Teeth Clicks, is now live!
  • [January, 2024] - Submited a paper on phase driven domain generalization for time series to ICML.
  • [October, 2023] - Corresponding with Meta Reality Labs, Audio Research group as a part-time student researcher.
  • [July, 2023] - Our paper on the Effect of Attention and Self-Supervised Speech Embeddings on Non-Semantic Speech Tasks has been accepted for ACM Multimedia 2023 Multimedia Grand Challenges Track.
  • [June, 2023] - I will be interning with Meta Reality Labs, Redmond, WA this summer as a Research Scientist. Reach out if you are here and want to collaborate (or just catch up over coffee).
  • [May, 2023] - We are participating in the ACM Multimedia 2023 Computational Paralinguistics Challenge (ComParE).
  • [February, 2023] - Our paper on EFFICIENT STUTTERING EVENT DETECTION USING SIAMESE NETWORKS is accepted in ICASSP’23.
  • [February, 2023] - Secured third place in e-Prevention: Person Identification and Relapse Detection from Continuous Recordings of Biosignals Challenge in ICASSP’23. Invited to present a paper on methodology - PERSON IDENTIFICATION WITH WEARABLE SENSING USING MISSING FEATURE ENCODING AND MULTI-STAGE MODALITY FUSION.
  • [December, 2022] - Demonstrated final working prototype of fatigue prediction in workers with near-real-time visualisation at the Boeing, Everett, Washington, factory floor.
  • [August, 2022] - Demonstrated initial working prototype of fatigue prediction in workers with near-real-time visualisation at the John Deere, Knoxville, Tennesse, factory floor.
  • [July, 2022] - Presented Speech Disfluency Detection with Contextual Representation and Data Distillation at Intelligent Acoustic Systems and Applications co-located with MobiSys’22.
  • [April, 2022] - Presented poster on Speech Disfluency Detection under data-constraints at CRA-WP grad cohort at New Orleans, Louisiana.

Services

  • Reviewer: ICASSP’25, ICLR’25, NeurIPS’24 (TSALM workshop), IMWUT’24, IROS’24, ICASSP’24
    • External Reviewer: ASP-DAC’24, EMSOFT’23, ICCPS’23, NSys’22
    • Book Reviews: Cambridge University Press early reader’s reviewing
  • Organize biweekly inter-laboratory Cyber-Physical Systems study group at Northwestern.
  • Active participant in the ML reading group at Northwestern, covering topics like XGBoost, MultiModal Learning, and Non-Stationary Transformers.
  • Mentoring:
    • 2024: Xiaoyuan Zhang, Talia-Ben Naim (MS students, Computer Engineering, Northwestern), Brooks Hu (Undergraduate, Computer Engineering, Northwestern), Mark Zhang (MS students, Mechanical Engineering, Northwestern)
    • 2023:
      • Yueyuan Sui, Shamika Likhite (MS students, Computer Engineering, Northwestern)
      • Brooks Hu, Kiva Joseph (Undergraduates, Computer Engineering, Northwestern)
      • Jonathan Li Chen, Ben Forbes, Justin Lau (Undergraduates, Mechanical Engineering, Northwestern)
    • 2022: Devashri Naik, Jinjin Cai (MS students, Computer Engineering, Northwestern)