# Talking Face Emotion Editing on User Study Extended Emotion

Source: [Talking Face Emotion Editing on User Study Extended Emotion](<https://www.sota2.com/research/sota/talking-face-emotion-editing-on-user-study-extended-emotion>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-10T08:06:43.440Z

Evaluation of models performing Talking Face Emotion Editing using the User Study Extended Emotion dataset, assessed via metrics covering emotional accuracy, visual fidelity, and lip synchronization.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Talking Face Emotion Editing |
| Dataset (including any stated split) | User Study Extended Emotion |
| Metric | Emotional Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Emotional Accuracy](<https://www.sota2.com/research/sota/talking-face-emotion-editing-on-user-study-extended-emotion.md?metric=Emotional%20Accuracy>): Higher is better; unit: PERCENT.

- [Visual Quality](<https://www.sota2.com/research/sota/talking-face-emotion-editing-on-user-study-extended-emotion.md?metric=Visual%20Quality>): Higher is better; unit: PERCENT.

- [Lip Synchronization](<https://www.sota2.com/research/sota/talking-face-emotion-editing-on-user-study-extended-emotion.md?metric=Lip%20Synchronization>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Emotional Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| C-MET | 91 | Not recorded | 69d883f47d0172140ec7791c |
| C-MET | 86.9 | Not recorded | 69d883f47d0172140ec7791c |
| C-MET | 80.4 | Not recorded | 69d883f47d0172140ec7791c |
| C-MET | 51.2 | Not recorded | 69d883f47d0172140ec7791c |
| EDTalk | 36.5 | Not recorded | 69d883f47d0172140ec7791c |
| EAT | 17.1 | Not recorded | 69d883f47d0172140ec7791c |
| Tie | 12.2 | Not recorded | 69d883f47d0172140ec7791c |
| FLOAT | 11.8 | Not recorded | 69d883f47d0172140ec7791c |
| EAMM | 6.7 | Not recorded | 69d883f47d0172140ec7791c |
| Tie | 2.4 | Not recorded | 69d883f47d0172140ec7791c |
| Tie | 2.2 | Not recorded | 69d883f47d0172140ec7791c |
| Tie | 1.2 | Not recorded | 69d883f47d0172140ec7791c |

### C-MET

Emotional Accuracy: 91. Result ID: 69d8af7647f34ce924c15fe7.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Implementation](<https://github.com/ChanHyeok-Choi/C-MET>)

Recorded evaluation configuration: {"Comparison Baseline":"EAMM"}. This record does not assert independent reproduction.

### C-MET

Emotional Accuracy: 86.9. Result ID: 69d8af7647f34ce924c15ff0.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Implementation](<https://github.com/ChanHyeok-Choi/C-MET>)

Recorded evaluation configuration: {"Comparison Baseline":"FLOAT"}. This record does not assert independent reproduction.

### C-MET

Emotional Accuracy: 80.4. Result ID: 69d8af7647f34ce924c15fea.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Implementation](<https://github.com/ChanHyeok-Choi/C-MET>)

Recorded evaluation configuration: {"Comparison Baseline":"EAT"}. This record does not assert independent reproduction.

### C-MET

Emotional Accuracy: 51.2. Result ID: 69d8af7647f34ce924c15fed.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Implementation](<https://github.com/ChanHyeok-Choi/C-MET>)

Recorded evaluation configuration: {"Comparison Baseline":"EDTalk"}. This record does not assert independent reproduction.

### EDTalk

Emotional Accuracy: 36.5. Result ID: 69d8af7647f34ce924c15fee.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72c21e209131cea58724.md>)

Recorded evaluation configuration: {"Comparison Baseline":"C-MET"}. This record does not assert independent reproduction.

### EAT

Emotional Accuracy: 17.1. Result ID: 69d8af7647f34ce924c15feb.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

Recorded evaluation configuration: {"Comparison Baseline":"C-MET"}. This record does not assert independent reproduction.

### Tie

Emotional Accuracy: 12.2. Result ID: 69d8af7647f34ce924c15fef.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

Recorded evaluation configuration: {"Comparison Baseline":"EDTalk vs C-MET"}. This record does not assert independent reproduction.

### FLOAT

Emotional Accuracy: 11.8. Result ID: 69d8af7647f34ce924c15ff1.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b641e209131cea88220.md>)

Recorded evaluation configuration: {"Comparison Baseline":"C-MET"}. This record does not assert independent reproduction.

### EAMM

Emotional Accuracy: 6.7. Result ID: 69d8af7647f34ce924c15fe8.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d831e209131cea3a40d.md>)

Recorded evaluation configuration: {"Comparison Baseline":"C-MET"}. This record does not assert independent reproduction.

### Tie

Emotional Accuracy: 2.4. Result ID: 69d8af7647f34ce924c15fec.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

Recorded evaluation configuration: {"Comparison Baseline":"EAT vs C-MET"}. This record does not assert independent reproduction.

### Tie

Emotional Accuracy: 2.2. Result ID: 69d8af7647f34ce924c15fe9.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

Recorded evaluation configuration: {"Comparison Baseline":"EAMM vs C-MET"}. This record does not assert independent reproduction.

### Tie

Emotional Accuracy: 1.2. Result ID: 69d8af7647f34ce924c15ff2.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f47d0172140ec7791c.md>)

Recorded evaluation configuration: {"Comparison Baseline":"FLOAT vs C-MET"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
