Gaze Patterns and Audiovisual Speech Enhancement
Bibliographic record
Abstract
PURPOSE: In this study, the authors sought to quantify the relationships between speech intelligibility (perception) and gaze patterns under different auditory-visual conditions. METHOD: Eleven subjects listened to low-context sentences spoken by a single talker while viewing the face of one or more talkers on a computer display. Subjects either maintained their gaze at a specific distance (0°, 2.5°, 5°, 10°, and 15°) from the center of the talker's mouth (CTM) or moved their eyes freely on the computer display. Eye movements were monitored with an eye-tracking system, and speech intelligibility was evaluated by the mean percentage of correctly perceived words. RESULTS: With a single talker and a fixed point of gaze, speech intelligibility was similar for all fixations within 10° of the CTM. With visual cues from two talker faces and a speech signal from one of the talkers, speech intelligibility was similar to that of a single talker for fixations within 2.5° of the CTM. With natural viewing of a single talker, gaze strategy changed with speech-signal-to-noise ratio (SNR). For low speech-SNR, a strategy that brought the point of gaze directly to within 2.5° of the CTM was used in approximately 80% of trials, whereas in high speech-SNR it was used in only approximately 50% of trials. CONCLUSIONS: With natural viewing of a single talker and high speech-SNR, subjects can shift their gaze between points on the talker's face without compromising speech intelligibility. With low-speech SNR, subjects change their gaze patterns to fixate primarily on points that are in close proximity to the talker's mouth. The latter strategy is essential to optimize speech intelligibility in situations where there are simultaneous visual cues from multiple talkers (i.e., when some of the visual cues are distracters).
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 | 0.000 | 0.002 |
| 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) | 0.003 | 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".