# Audio-driven talking head synthesis on VoxCeleb2 13 (test)

Source: [Audio-driven talking head synthesis on VoxCeleb2 13 (test)](<https://www.sota2.com/research/sota/audio-driven-talking-head-synthesis-on-voxceleb2-13-test>)

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

Data updated: 2026-02-26T05:48:20.863Z

Evaluation of models performing Audio-driven talking head synthesis on the specific test split (version 13) of the VoxCeleb2 dataset, assessed using metrics including FID, LSE-C, NLSE-C, LMDm, and LMD.

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 | Audio-driven talking head synthesis |
| Dataset (including any stated split) | VoxCeleb2 13 (test) |
| Metric | LSE-C |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| 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

- [LSE-C](<https://www.sota2.com/research/sota/audio-driven-talking-head-synthesis-on-voxceleb2-13-test.md?metric=LSE-C>): Lower is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/audio-driven-talking-head-synthesis-on-voxceleb2-13-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [NLSE-C](<https://www.sota2.com/research/sota/audio-driven-talking-head-synthesis-on-voxceleb2-13-test.md?metric=NLSE-C>): Lower is better; unit: SCALAR.

- [LMDm](<https://www.sota2.com/research/sota/audio-driven-talking-head-synthesis-on-voxceleb2-13-test.md?metric=LMDm>): Lower is better; unit: SCALAR.

- [LMD](<https://www.sota2.com/research/sota/audio-driven-talking-head-synthesis-on-voxceleb2-13-test.md?metric=LMD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | LSE-C | Result date | Report paper |
| --- | --- | --- | --- |
| MakeItTalk | 2.03 | Not recorded | 68fa6e0e1e209131cea3db85 |
| EAMM | 4.55 | Not recorded | 68fa6e0e1e209131cea3db85 |
| EAMM | 4.75 | Not recorded | 68fa6e0e1e209131cea3db85 |
| PD-FGC | 7.26 | Not recorded | 68fa6e0e1e209131cea3db85 |
| GT | 7.35 | Not recorded | 68fa6e0e1e209131cea3db85 |
| PC-AVS | 8.21 | Not recorded | 68fa6e0e1e209131cea3db85 |
| Wav2Lip | 9.23 | Not recorded | 68fa6e0e1e209131cea3db85 |

### MakeItTalk

LSE-C: 2.03. Result ID: 698ff74d3a6c314849fd228b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e0e1e209131cea3db85.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### EAMM

LSE-C: 4.55. Result ID: 698ff74d3a6c314849fd228e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e0e1e209131cea3db85.md>)

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

Recorded evaluation configuration: {"mode":"Emo"}. This record does not assert independent reproduction.

### EAMM

LSE-C: 4.75. Result ID: 698ff74d3a6c314849fd228d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e0e1e209131cea3db85.md>)

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

Recorded evaluation configuration: {"mode":"Neutral"}. This record does not assert independent reproduction.

### PD-FGC

LSE-C: 7.26. Result ID: 698ff74d3a6c314849fd228f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e0e1e209131cea3db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e0e1e209131cea3db85.md>)

[Implementation](<https://dorniwang.github.io/PD-FGC/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GT

LSE-C: 7.35. Result ID: 698ff74d3a6c314849fd2289.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e0e1e209131cea3db85.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PC-AVS

LSE-C: 8.21. Result ID: 698ff74d3a6c314849fd228c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e0e1e209131cea3db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cb1e209131cea24114.md>)

[Implementation](<https://hangz-nju-cuhk.github.io/projects/PC-AVS>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Wav2Lip

LSE-C: 9.23. Result ID: 698ff74d3a6c314849fd228a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e0e1e209131cea3db85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68361e209131cea1ad36.md>)

[Implementation](<https://www.sota2.com/github.com/Rudrabha/Wav2Lip>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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