Towards Improving the Correct Lyric Detection by Deaf and Hard of Hearing People
Bibliographic record
Abstract
Abstract Access to music for people who are Deaf/Hard of Hearing (D/HoH) includes the instrumental portion and the lyrics. While closed captioning can provide the lyrics in text format, it does not necessarily provide accurate timing of the lyrics with the instrumental portion. This study aims to clarify how vibrotactile stimuli affect understanding the onset timing of song lyrics for D/HoH people. To achieve this goal, we developed a system called VIBES: VIBrotactile Engagement for Songs that simultaneously provides music and vibration playback as an iPhone app. Unlike other vibrotactile systems for music, which focus primarily on the percussion/beat or frequencies of the instrumental portions, VIBES presents vibrations for the timing of vocal utterances, syllable by syllable. We conducted a study with 10 participants to determine the system’s effectiveness by comparing the understanding of lyric timing with vibration and sound only. Statistically, one of the four songs in the experiment showed significant differences, where understanding lyric timing with vibration is better than in sound-only conditions. Two songs revealed the opposite results, and the other showed no differences between the two conditions. Although these results were unexpected, we obtained several findings to make the next version of VIBES, such as the frequency of vibrations.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.004 |
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".