Different facial cues for different speech styles in Mandarin tone articulation
Bibliographic record
Abstract
Visual facial information, particularly hyperarticulated lip movements in clear speech, has been shown to benefit segmental speech perception. Little research has focused on prosody, such as lexical tone, presumably because production of prosody primarily involves laryngeal activities not necessarily distinguishable through visible articulatory movements. However, there is evidence that head, eyebrow, and lip movements correlate with production of pitch-related variations. One subsequent question is whether such visual cues are linguistically meaningful. In this study, we compare movements of the head, eyebrows and lips associated with plain (conversational) vs. clear speech styles of Mandarin tone articulation to examine the extent to which clear-speech modifications involve signal-based overall exaggerated facial movements or code-based enhancement of linguistically relevant articulatory movements. Applying computer-vision techniques to recorded speech, visible movements of the frontal face were tracked and measured for 20 native Mandarin speakers speaking in two speech styles: plain and clear. Thirty-three head, eyebrow and lip movement features based on distance, time, and kinematics were extracted from each individual tone word. A random forest classifier was used to identify the important features that differentiate the two styles across tones and for each tone. Mixed-effects models were then performed to determine the features that were significantly different between the two styles. Overall, for all the four Mandarin tones, we found longer duration and greater movements of the head, eyebrows, and lips in clear speech than in plain speech. Additionally, across tones, the maximum movement happened relatively earlier in clear than plain speech. Although limited evidence of tone-specific modifications was also observed, the cues involved overlap with signal-based changes. These findings suggest that visual facial tonal modifications for clear speech primarily adopt signal-based general emphatic cues that strengthen signal saliency.
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) | 0.001 | 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".