Beyond Hearing: Learning Task-Agnostic ExG Representations from Earphones via Physiology-Informed Tokenization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913171281805312 |
|---|---|
| author | Yoon, Hyungjun Lee, Seungjoo Wu, Yu Yvonne Chen, Xiaomeng Lu, Taiting Liu, Freddy Yifei Lee, Taeckyung Cha, Hyeongheon Zhao, Haochen Zhao, Gaoteng Chen, Dongyao Mascolo, Cecilia Lee, Sung-Ju Qiu, Lili |
| author_facet | Yoon, Hyungjun Lee, Seungjoo Wu, Yu Yvonne Chen, Xiaomeng Lu, Taiting Liu, Freddy Yifei Lee, Taeckyung Cha, Hyeongheon Zhao, Haochen Zhao, Gaoteng Chen, Dongyao Mascolo, Cecilia Lee, Sung-Ju Qiu, Lili |
| contents | Electrophysiological (ExG) signals offer valuable insights into human physiology, yet building foundation models that generalize across everyday tasks remains challenging due to two key limitations: (i)~insufficient data diversity, as most ExG recordings are collected in controlled labs with bulky, expensive devices; and (ii)~task-specific model designs that require tailored processing (i.e., targeted frequency filters) and architectures, which limit generalization across tasks. To address these challenges, we introduce an approach for scalable, task-agnostic ExG monitoring in the wild. We collected 50 hours of unobtrusive free-living ExG data with an earphone-based hardware prototype to narrow the data diversity gap. At the core of our approach is Physiology-informed Multi-band Tokenization (PiMT), which decomposes ExG signals into 12 physiology-informed tokens, followed by a reconstruction task to learn robust representations. This enables adaptive feature recognition across the full frequency spectrum while capturing task-relevant information. Experiments on our new DailySense dataset, the first to enable ExG-based analysis across five human senses, together with four public ExG benchmarks, demonstrate that PiMT consistently outperforms state-of-the-art methods across diverse tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20853 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Hearing: Learning Task-Agnostic ExG Representations from Earphones via Physiology-Informed Tokenization Yoon, Hyungjun Lee, Seungjoo Wu, Yu Yvonne Chen, Xiaomeng Lu, Taiting Liu, Freddy Yifei Lee, Taeckyung Cha, Hyeongheon Zhao, Haochen Zhao, Gaoteng Chen, Dongyao Mascolo, Cecilia Lee, Sung-Ju Qiu, Lili Audio and Speech Processing Computation and Language Sound 68T01 I.2 Electrophysiological (ExG) signals offer valuable insights into human physiology, yet building foundation models that generalize across everyday tasks remains challenging due to two key limitations: (i)~insufficient data diversity, as most ExG recordings are collected in controlled labs with bulky, expensive devices; and (ii)~task-specific model designs that require tailored processing (i.e., targeted frequency filters) and architectures, which limit generalization across tasks. To address these challenges, we introduce an approach for scalable, task-agnostic ExG monitoring in the wild. We collected 50 hours of unobtrusive free-living ExG data with an earphone-based hardware prototype to narrow the data diversity gap. At the core of our approach is Physiology-informed Multi-band Tokenization (PiMT), which decomposes ExG signals into 12 physiology-informed tokens, followed by a reconstruction task to learn robust representations. This enables adaptive feature recognition across the full frequency spectrum while capturing task-relevant information. Experiments on our new DailySense dataset, the first to enable ExG-based analysis across five human senses, together with four public ExG benchmarks, demonstrate that PiMT consistently outperforms state-of-the-art methods across diverse tasks. |
| title | Beyond Hearing: Learning Task-Agnostic ExG Representations from Earphones via Physiology-Informed Tokenization |
| topic | Audio and Speech Processing Computation and Language Sound 68T01 I.2 |
| url | https://arxiv.org/abs/2510.20853 |