# Video-to-audio dubbing on GRID Setting 3.0

Source: [Video-to-audio dubbing on GRID Setting 3.0](<https://www.sota2.com/research/sota/video-to-audio-dubbing-on-grid-setting-3-0>)

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

Data updated: 2026-03-25T13:36:33.610Z

Evaluation of Video-to-audio dubbing performance on the GRID Setting 3.0 dataset, measured using LSE-C, LSE-D, and Word Error Rate (WER).

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 | Video-to-audio dubbing |
| Dataset (including any stated split) | GRID Setting 3.0 |
| Metric | LSE-C |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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/video-to-audio-dubbing-on-grid-setting-3-0.md?metric=LSE-C>): Higher is better; unit: SCALAR.

- [LSE-D](<https://www.sota2.com/research/sota/video-to-audio-dubbing-on-grid-setting-3-0.md?metric=LSE-D>): Lower is better; unit: SCALAR.

- [WER](<https://www.sota2.com/research/sota/video-to-audio-dubbing-on-grid-setting-3-0.md?metric=WER>): Lower is better; unit: PERCENT.

## Recorded results

| Method | LSE-C | Result date | Report paper |
| --- | --- | --- | --- |
| UniAVGen | 7.59 | Not recorded | 690c2b732828b7cc6937c495 |
| EmoDubber | 7.25 | Not recorded | 690c2b732828b7cc6937c495 |
| StyleDubber | 5.94 | Not recorded | 690c2b732828b7cc6937c495 |

### UniAVGen

LSE-C: 7.59. Result ID: 69c3e40347f34ce924ad6fab.

[Reporting paper](<https://www.sota2.com/research/paper/690c2b732828b7cc6937c495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690c2b732828b7cc6937c495.md>)

Recorded evaluation configuration: {"Dubbing Setting":"3.0"}. This record does not assert independent reproduction.

### EmoDubber

LSE-C: 7.25. Result ID: 69c3e40347f34ce924ad6faa.

[Reporting paper](<https://www.sota2.com/research/paper/690c2b732828b7cc6937c495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78331e209131cea772b4.md>)

[Implementation](<https://galaxycong.github.io/EmoDub>)

Recorded evaluation configuration: {"Dubbing Setting":"3.0"}. This record does not assert independent reproduction.

### StyleDubber

LSE-C: 5.94. Result ID: 69c3e40347f34ce924ad6fa9.

[Reporting paper](<https://www.sota2.com/research/paper/690c2b732828b7cc6937c495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73f11e209131cea5f044.md>)

[Implementation](<https://github.com/GalaxyCong/StyleDubber>)

Recorded evaluation configuration: {"Dubbing Setting":"3.0"}. This record does not assert independent reproduction.

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