Mobile Application for Stress Detection via MFCC Speech-Features
Bibliographic record
Abstract
Everyone goes through periods of mental stress in their daily lives. While small amounts of stress can enhance focus, alertness, and performance, excessive stress negatively affects productivity, emotional stability, quality of life, and overall health. Early stress detection is crucial for preventing its harmful effects and managing it effectively. Despite significant research in stress detection, there remains a lack of real-time, mobile-based, and intuitive solutions that are easily accessible to the public. This research focuses on developing StressVox, a mobile application that uses speech analysis to identify stress or not stress. The system, developed using Flutter, utilizes a pretrained Convolutional Neural Network (CNN) trained on the Toronto Emotional Speech Set (TESS) dataset. The methodology includes data preparation, Mel Frequency Cepstral Coefficients (MFCC) feature extraction, noise handling, and speaker verification to ensure accurate and personalized results. The application uses a white and blue theme for a calming user experience and integrates with a Python backend via APIs, enabling real-time stress classification. The system achieved a 96% accuracy rate in detecting stress and includes a feedback-driven feature to rework the model when false results occur, further enhancing its performance over time. StressVox is designed to empower users with an accessible and non-invasive tool for early stress detection and management, providing a practical and user centric approach to addressing the growing need for mental health monitoring in daily life.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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 teacher head, 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".