# Co-speech Gesture Generation on BEAT-2 (1 Speaker)

Source: [Co-speech Gesture Generation on BEAT-2 (1 Speaker)](<https://www.sota2.com/research/sota/co-speech-gesture-generation-on-beat-2-1-speaker>)

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

Data updated: 2026-02-26T05:36:37.995Z

Evaluation of Co-speech gesture generation performance on the BEAT-2 dataset, specifically using data derived from a single speaker setup, assessed using metrics such as FGD, BC, and Diversity.

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 | Co-speech gesture generation |
| Dataset (including any stated split) | BEAT-2 (1 Speaker) |
| Metric | BC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [BC](<https://www.sota2.com/research/sota/co-speech-gesture-generation-on-beat-2-1-speaker.md?metric=BC>): Higher is better; unit: SCALAR.

- [FGD](<https://www.sota2.com/research/sota/co-speech-gesture-generation-on-beat-2-1-speaker.md?metric=FGD>): Lower is better; unit: SCALAR.

- [Diversity](<https://www.sota2.com/research/sota/co-speech-gesture-generation-on-beat-2-1-speaker.md?metric=Diversity>): Higher is better; unit: SCALAR.

## Recorded results

| Method | BC | Result date | Report paper |
| --- | --- | --- | --- |
| SynTalker | 7.971 | Not recorded | 68fa76391e209131cea6bf5d |
| Language of Motion | 7.78 | Not recorded | 68fa76391e209131cea6bf5d |
| Language of Motion | 7.742 | Not recorded | 68fa76391e209131cea6bf5d |
| EMAGE | 7.724 | Not recorded | 68fa76391e209131cea6bf5d |
| Habibie et al. | 7.716 | Not recorded | 68fa76391e209131cea6bf5d |
| DiffStyleGesture | 7.241 | Not recorded | 68fa76391e209131cea6bf5d |
| TalkSHOW | 6.947 | Not recorded | 68fa76391e209131cea6bf5d |
| CaMN | 6.769 | Not recorded | 68fa76391e209131cea6bf5d |
| DisCo | 6.439 | Not recorded | 68fa76391e209131cea6bf5d |
| Language of Motion | 6.148 | Not recorded | 68fa76391e209131cea6bf5d |
| EMAGE | 0.793 | Not recorded | 68fa7ba41e209131cea89971 |
| RAG-Gesture | 0.73 | Not recorded | 68fa7ba41e209131cea89971 |
| GestureLSM | 0.714 | Not recorded | 68fa7ba41e209131cea89971 |
| Ground Truth | 0.703 | Not recorded | 68fa7ba41e209131cea89971 |
| Intentional-Gesture | 0.69 | Not recorded | 68fa7ba41e209131cea89971 |
| CaMN | 0.676 | Not recorded | 68fa7ba41e209131cea89971 |
| Audio2Photoreal | 0.55 | Not recorded | 68fa7ba41e209131cea89971 |

### SynTalker

BC: 7.971. Result ID: 699417a93a6c3148491afc84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75081e209131cea6565f.md>)

[Implementation](<https://robinwitch.github.io/SynTalker-Page/>)

Recorded evaluation configuration: {"Condition Signal":"audio, text"}. This record does not assert independent reproduction.

### Language of Motion

BC: 7.78. Result ID: 699417a93a6c3148491afc88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Implementation](<https://www.sota2.com/languageofmotion.github.io>)

Recorded evaluation configuration: {"Condition Signal":"audio"}. This record does not assert independent reproduction.

### Language of Motion

BC: 7.742. Result ID: 699417a93a6c3148491afc87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Implementation](<https://www.sota2.com/languageofmotion.github.io>)

Recorded evaluation configuration: {"Condition Signal":"audio","multimodal pre-training":false}. This record does not assert independent reproduction.

### EMAGE

BC: 7.724. Result ID: 699417a93a6c3148491afc85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72c11e209131cea5867d.md>)

[Implementation](<https://pantomatrix.github.io/EMAGE/>)

Recorded evaluation configuration: {"Condition Signal":"audio, text"}. This record does not assert independent reproduction.

### Habibie et al.

BC: 7.716. Result ID: 699417a93a6c3148491afc82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69511e209131cea21863.md>)

Recorded evaluation configuration: {"Condition Signal":"audio, text"}. This record does not assert independent reproduction.

### DiffStyleGesture

BC: 7.241. Result ID: 699417a93a6c3148491afc81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f4d1e209131cea44eb3.md>)

Recorded evaluation configuration: {"Condition Signal":"audio, style"}. This record does not assert independent reproduction.

### TalkSHOW

BC: 6.947. Result ID: 699417a93a6c3148491afc83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fcb1e209131cea4771a.md>)

[Implementation](<https://talkshow.is.tue.mpg.de/>)

Recorded evaluation configuration: {"Condition Signal":"audio"}. This record does not assert independent reproduction.

### CaMN

BC: 6.769. Result ID: 699417a93a6c3148491afc80.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d751e209131cea3a0d5.md>)

[Implementation](<https://pantomatrix.github.io/BEAT/>)

Recorded evaluation configuration: {"Condition Signal":"audio, text, facial"}. This record does not assert independent reproduction.

### DisCo

BC: 6.439. Result ID: 699417a93a6c3148491afc7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

Recorded evaluation configuration: {"Condition Signal":"audio"}. This record does not assert independent reproduction.

### Language of Motion

BC: 6.148. Result ID: 699417a93a6c3148491afc86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76391e209131cea6bf5d.md>)

[Implementation](<https://www.sota2.com/languageofmotion.github.io>)

Recorded evaluation configuration: {"Condition Signal":"audio","language pre-training":false}. This record does not assert independent reproduction.

### EMAGE

BC: 0.793. Result ID: 698b89157a967eddb76f62b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba41e209131cea89971.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72c11e209131cea5867d.md>)

[Implementation](<https://pantomatrix.github.io/EMAGE/>)

Recorded evaluation configuration: {"speaker\_mode":"1 Speaker"}. This record does not assert independent reproduction.

### RAG-Gesture

BC: 0.73. Result ID: 698b89157a967eddb76f62b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba41e209131cea89971.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77c11e209131cea751db.md>)

Recorded evaluation configuration: {"speaker\_mode":"1 Speaker"}. This record does not assert independent reproduction.

### GestureLSM

BC: 0.714. Result ID: 698b89157a967eddb76f62ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba41e209131cea89971.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a641e209131cea82d92.md>)

[Implementation](<https://andypinxinliu.github.io/GestureLSM>)

Recorded evaluation configuration: {"speaker\_mode":"1 Speaker"}. This record does not assert independent reproduction.

### Ground Truth

BC: 0.703. Result ID: 698b89157a967eddb76f62b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba41e209131cea89971.md>)

Recorded evaluation configuration: {"speaker\_mode":"1 Speaker"}. This record does not assert independent reproduction.

### Intentional-Gesture

BC: 0.69. Result ID: 698b89157a967eddb76f62bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba41e209131cea89971.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba41e209131cea89971.md>)

[Implementation](<https://andypinxinliu.github.io/Intentional-Gesture>)

Recorded evaluation configuration: {"speaker\_mode":"1 Speaker"}. This record does not assert independent reproduction.

### CaMN

BC: 0.676. Result ID: 698b89157a967eddb76f62b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba41e209131cea89971.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d751e209131cea3a0d5.md>)

[Implementation](<https://pantomatrix.github.io/BEAT/>)

Recorded evaluation configuration: {"speaker\_mode":"1 Speaker"}. This record does not assert independent reproduction.

### Audio2Photoreal

BC: 0.55. Result ID: 698b89157a967eddb76f62b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba41e209131cea89971.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ba1e209131cea52ca0.md>)

Recorded evaluation configuration: {"speaker\_mode":"1 Speaker"}. This record does not assert independent reproduction.

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