Voice as a sensitive biomarker for predicting exercise intensity: a modelling study
Bibliographic record
Abstract
Objective: This study investigates the potential of using voice as a sensitive omics marker to predict exercise intensity. Methods: Ninety-two healthy university students aged 18-25 participated in this cross-sectional study, engaging in physical activities of varying intensities, including the Canadian Agility and Movement Skill Assessment (CAMSA), the Plank test, and the Progressive Aerobic Cardiovascular Endurance Run (PACER). Speech data were collected before, during, and after these activities using professional recording equipment. Acoustic features were extracted using the openSMILE toolkit, focusing on the Geneva Minimalistic Acoustic Parameter Set (GeMAPS) and the Computational Paralinguistics Challenge (ComParE) feature sets. These features were analyzed using statistical models, including support vector machine (SVM), to classify exercise intensity. Results: Significant variations in speech characteristics, such as speech duration, fundamental frequency (F0), and pause times, were observed across different exercise intensities, with the models achieving high accuracy in distinguishing between exercise states. Conclusion: These findings suggest that speech analysis can provide a non-invasive, real-time method for monitoring exercise intensity. The study's implications extend to personalized exercise prescriptions, chronic disease management, and the integration of speech analysis into routine health assessments. This approach promotes better exercise adherence and overall health outcomes, highlighting the potential for innovative health monitoring techniques.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".