Summary of Emg2qwerty: a Large Dataset with Baselines For Touch Typing Using Surface Electromyography, by Viswanath Sivakumar et al.
emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography
by Viswanath Sivakumar, Jeffrey Seely, Alan Du, Sean R Bittner, Adam Berenzweig, Anuoluwapo Bolarinwa, Alexandre Gramfort, Michael I Mandel
First submitted to arxiv on: 26 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Human-Computer Interaction (cs.HC); Audio and Speech Processing (eess.AS)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed dataset, emg2qwerty, is a large-scale collection of surface electromyography (sEMG) signals recorded from the wrists while typing on a QWERTY keyboard. With 1,135 sessions and 346 hours of recording, it is the largest public dataset to date in this domain. The data demonstrate hierarchical relationships between muscle activity, key-presses, and user-specific patterns. By applying ASR modeling techniques, strong baseline performance is achieved in predicting key-presses using sEMG signals alone. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The emg2qwerty dataset is a collection of sEMG signals recorded from the wrists while typing on a QWERTY keyboard. This data helps researchers understand how our muscles work when we type and can be used to make computers better understand what we’re trying to say. The data is very large, with over 1,000 sessions and hundreds of hours of recording. |
