Supervised learning in voice type discrimination using neck-skin vibration signals: Preliminary results on single vowels
Bibliographic record
Abstract
Discrimination between normal and pathological voice is a critical component in laryngeal pathology diagnosis and vocal rehabilitative treatment. In the present study, a portable miniature glottal notch accelerometer (GNA) device with supervised machine learning techniques was proposed to discriminate between three human voice types: normal, breathy, and pressed voice. Fourteen native American English speakers who were wearing a GNA device produced five different English single vowels in each of the three voice types. Acoustic features of the GNA signals were extracted using spectral analysis. Preliminary assessments of feature discrepancy among different voice types were made to present physical clues of discrimination. The linear discriminant analysis technique was applied to reduce the dimensionality of the raw-feature vector of the GNA signals. Maximization of between-class distance and minimization of within-class distance were synchronously achieved. The voice types were then classified using several supervised learning techniques, such as Linear Discriminant, Decision Tree, Support Vector Machine, and K-Nearest Neighbors. A classification accuracy of up to 91.0% was achieved. One mapping model from voice input to type output was eventually obtained based on the training set, so as to make predictions with new data in the future work.
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 | 0.001 | 0.003 |
| 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 | 0.000 | 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 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".