# Speech-driven talking face generation on Wild Dataset

Source: [Speech-driven talking face generation on Wild Dataset](<https://www.sota2.com/research/sota/speech-driven-talking-face-generation-on-wild-dataset>)

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

Data updated: 2026-03-04T12:14:08.272Z

Evaluation of Speech-driven talking face generation models using the Wild Dataset, assessed via metrics including LSE-D, LSE-C, LPIPS, SSIM, PSNR, FID, and MAD.

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 | Speech-driven talking face generation |
| Dataset (including any stated split) | Wild Dataset |
| Metric | LSE-D |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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-D](<https://www.sota2.com/research/sota/speech-driven-talking-face-generation-on-wild-dataset.md?metric=LSE-D>): Lower is better; unit: SCALAR.

- [LSE-C](<https://www.sota2.com/research/sota/speech-driven-talking-face-generation-on-wild-dataset.md?metric=LSE-C>): Lower is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/speech-driven-talking-face-generation-on-wild-dataset.md?metric=LPIPS>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/speech-driven-talking-face-generation-on-wild-dataset.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/speech-driven-talking-face-generation-on-wild-dataset.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/speech-driven-talking-face-generation-on-wild-dataset.md?metric=FID>): Lower is better; unit: SCALAR.

- [MAD](<https://www.sota2.com/research/sota/speech-driven-talking-face-generation-on-wild-dataset.md?metric=MAD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | LSE-D | Result date | Report paper |
| --- | --- | --- | --- |
| HRTF | 8.89 | Not recorded | 690836f03ef7ccd74e5e5345 |
| HRTF-SCFP | 9.94 | Not recorded | 690836f03ef7ccd74e5e5345 |
| VideoRetalking | 12.56 | Not recorded | 690836f03ef7ccd74e5e5345 |
| SyncTalk | 13.55 | Not recorded | 690836f03ef7ccd74e5e5345 |
| Aniportait | 14.64 | Not recorded | 690836f03ef7ccd74e5e5345 |
| Hallo | 18.57 | Not recorded | 690836f03ef7ccd74e5e5345 |
| Real3D-portrait | 19.07 | Not recorded | 690836f03ef7ccd74e5e5345 |
| Anitalker | 19.5 | Not recorded | 690836f03ef7ccd74e5e5345 |

### HRTF

LSE-D: 8.89. Result ID: 69a821fc6dbb7075b94e33e7.

[Reporting paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

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

### HRTF-SCFP

LSE-D: 9.94. Result ID: 69a821fc6dbb7075b94e33e8.

[Reporting paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

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

### VideoRetalking

LSE-D: 12.56. Result ID: 69a821fc6dbb7075b94e33e6.

[Reporting paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e0e1e209131cea3dbd2.md>)

Recorded evaluation configuration: {"Venue":"SIGGRAPH 2022"}. This record does not assert independent reproduction.

### SyncTalk

LSE-D: 13.55. Result ID: 69a821fc6dbb7075b94e33e3.

[Reporting paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa730f1e209131cea5a370.md>)

[Implementation](<https://ziqiaopeng.github.io/synctalk>)

Recorded evaluation configuration: {"Venue":"CVPR 2024"}. This record does not assert independent reproduction.

### Aniportait

LSE-D: 14.64. Result ID: 69a821fc6dbb7075b94e33e1.

[Reporting paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b31e209131cea5805f.md>)

Recorded evaluation configuration: {"Venue":"ECCV 2024"}. This record does not assert independent reproduction.

### Hallo

LSE-D: 18.57. Result ID: 69a821fc6dbb7075b94e33e4.

[Reporting paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73b31e209131cea5dfcf.md>)

Recorded evaluation configuration: {"Venue":"arXiv 2024.7"}. This record does not assert independent reproduction.

### Real3D-portrait

LSE-D: 19.07. Result ID: 69a821fc6dbb7075b94e33e2.

[Reporting paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a31e209131cea57ba3.md>)

Recorded evaluation configuration: {"Venue":"ICLR 2024"}. This record does not assert independent reproduction.

### Anitalker

LSE-D: 19.5. Result ID: 69a821fc6dbb7075b94e33e5.

[Reporting paper](<https://www.sota2.com/research/paper/690836f03ef7ccd74e5e5345.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73141e209131cea5a5b7.md>)

Recorded evaluation configuration: {"Venue":"ACM MM 2024"}. This record does not assert independent reproduction.

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