Myo-Speech: A System for Recognizing Word Utterances of the Speech Impaired
Bibliographic record
Abstract
We report a new method for identification of unintelligible vocal sounds obtained from two speech impaired volunteers.The ultimate goal of this research is to generate some speech production capabilities for persons with speech impairment by reissuing intelligible versions of words corresponding to the vocal sounds they generate in their typically unsuccessful efforts to produce spoken words.The ability to generate understandable spoken words can have a major positive impact on the quality of life of speech impairment communities around the world.To acquire classifiable signals corresponding to the produced vocal sounds we did not use a conventional microphone as it is not immune to background noise.Rather, we used surface electromyography (sEMG) signals obtained from the sternocleidomastoid muscle in proximity of the vocal cords, with the hypothesis that there should be consistent correlation between the intended words and their myo signals.A preliminary dataset consisting of three Arabic words was acquired from two subjects (one female and one male) in a lab-controlled environment.Average classification accuracy was about 82% using standard machine learning techniques (KNN, NN, and SVM).Preliminary results indicate that classification of this limited vocabulary dataset is feasible with reasonable accuracy to motivate future work involving more subjects and larger datasets.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| 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) | 0.006 | 0.006 |
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".