# Video-conditioned sound-speech joint generation on V2C (test)

Source: [Video-conditioned sound-speech joint generation on V2C (test)](<https://www.sota2.com/research/sota/video-conditioned-sound-speech-joint-generation-on-v2c-test>)

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

Data updated: 2026-03-11T06:42:25.278Z

Evaluation of models performing video-conditioned sound and speech joint generation on the test split of the V2C dataset, using metrics like WER, Speaker Similarity, UTMOS, and FAD scores.

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-conditioned sound-speech joint generation |
| Dataset (including any stated split) | V2C (test) |
| Metric | WER |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [WER](<https://www.sota2.com/research/sota/video-conditioned-sound-speech-joint-generation-on-v2c-test.md?metric=WER>): Lower is better; unit: PERCENT.

- [Speaker Similarity](<https://www.sota2.com/research/sota/video-conditioned-sound-speech-joint-generation-on-v2c-test.md?metric=Speaker%20Similarity>): Higher is better; unit: SCALAR.

- [UTMOS](<https://www.sota2.com/research/sota/video-conditioned-sound-speech-joint-generation-on-v2c-test.md?metric=UTMOS>): Higher is better; unit: SCALAR.

- [LSE-C](<https://www.sota2.com/research/sota/video-conditioned-sound-speech-joint-generation-on-v2c-test.md?metric=LSE-C>): Higher is better; unit: SCALAR.

- [FAD (pann.)](<https://www.sota2.com/research/sota/video-conditioned-sound-speech-joint-generation-on-v2c-test.md?metric=FAD%20(pann.)>): Lower is better; unit: SCALAR.

- [FAD (pas.)](<https://www.sota2.com/research/sota/video-conditioned-sound-speech-joint-generation-on-v2c-test.md?metric=FAD%20(pas.)>): Lower is better; unit: SCALAR.

- [KL (pann.)](<https://www.sota2.com/research/sota/video-conditioned-sound-speech-joint-generation-on-v2c-test.md?metric=KL%20(pann.)>): Lower is better; unit: SCALAR.

- [KL (pas.)](<https://www.sota2.com/research/sota/video-conditioned-sound-speech-joint-generation-on-v2c-test.md?metric=KL%20(pas.)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | WER | Result date | Report paper |
| --- | --- | --- | --- |
| VSSFlow-M | 19.4 | Not recorded | 68fa7bc71e209131cea8a6b9 |
| LoVA \| Speaker | 25.98 | Not recorded | 68fa7bc71e209131cea8a6b9 |
| LoVA+Style | 37.56 | Not recorded | 68fa7bc71e209131cea8a6b9 |
| MMAudio+Speaker | 41.47 | Not recorded | 68fa7bc71e209131cea8a6b9 |
| MMAudio+Style | 56.86 | Not recorded | 68fa7bc71e209131cea8a6b9 |

### VSSFlow-M

WER: 19.4. Result ID: 69b10df26dbb7075b95ac213.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6b9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6b9.md>)

Recorded evaluation configuration: {"Model size":"Medium"}. This record does not assert independent reproduction.

### LoVA \| Speaker

WER: 25.98. Result ID: 69b10df26dbb7075b95ac20f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6b9.md>)

Recorded evaluation configuration: {"Conditioning":"Speaker"}. This record does not assert independent reproduction.

### LoVA+Style

WER: 37.56. Result ID: 69b10df26dbb7075b95ac210.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6b9.md>)

Recorded evaluation configuration: {"Conditioning":"Style"}. This record does not assert independent reproduction.

### MMAudio+Speaker

WER: 41.47. Result ID: 69b10df26dbb7075b95ac211.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6b9.md>)

Recorded evaluation configuration: {"Conditioning":"Speaker"}. This record does not assert independent reproduction.

### MMAudio+Style

WER: 56.86. Result ID: 69b10df26dbb7075b95ac212.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6b9.md>)

Recorded evaluation configuration: {"Conditioning":"Style"}. This record does not assert independent reproduction.

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