# Gesture Synthesis on BEAT (Body-Expression-Audio-Text) 1.0 (test)

Source: [Gesture Synthesis on BEAT (Body-Expression-Audio-Text) 1.0 (test)](<https://www.sota2.com/research/sota/gesture-synthesis-on-beat-body-expression-audio-text-1-0-test>)

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

Data updated: 2026-02-26T05:44:08.134Z

Evaluation of Gesture Synthesis performance on the test split of the BEAT (Body-Expression-Audio-Text) 1.0 dataset, measured using metrics like FGD, SRGR, and BeatAlign.

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 | Gesture Synthesis |
| Dataset (including any stated split) | BEAT (Body-Expression-Audio-Text) 1.0 (test) |
| Metric | FGD |
| 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

- [FGD](<https://www.sota2.com/research/sota/gesture-synthesis-on-beat-body-expression-audio-text-1-0-test.md?metric=FGD>): Lower is better; unit: SCALAR.

- [SRGR](<https://www.sota2.com/research/sota/gesture-synthesis-on-beat-body-expression-audio-text-1-0-test.md?metric=SRGR>): Higher is better; unit: SCALAR.

- [BeatAlign](<https://www.sota2.com/research/sota/gesture-synthesis-on-beat-body-expression-audio-text-1-0-test.md?metric=BeatAlign>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FGD | Result date | Report paper |
| --- | --- | --- | --- |
| MambaTalk | 51.3 | Not recorded | 68fa79811e209131cea7dddf |
| TalkShow | 91 | Not recorded | 68fa79811e209131cea7dddf |
| CaMN | 123.7 | Not recorded | 68fa79811e209131cea7dddf |
| MultiContext | 176.2 | Not recorded | 68fa79811e209131cea7dddf |
| Audio2Gesture | 223.8 | Not recorded | 68fa79811e209131cea7dddf |
| Speech2Gesture | 256.7 | Not recorded | 68fa79811e209131cea7dddf |
| Seq2Seq | 261.3 | Not recorded | 68fa79811e209131cea7dddf |

### MambaTalk

FGD: 51.3. Result ID: 698b50098d67a41d0a6cfd98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79811e209131cea7dddf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79811e209131cea7dddf.md>)

Recorded evaluation configuration: {"training\_dataset":"BEAT"}. This record does not assert independent reproduction.

### TalkShow

FGD: 91. Result ID: 698b50098d67a41d0a6cfd97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79811e209131cea7dddf.md>)

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

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

Recorded evaluation configuration: {"training\_dataset":"BEAT"}. This record does not assert independent reproduction.

### CaMN

FGD: 123.7. Result ID: 698b50098d67a41d0a6cfd96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79811e209131cea7dddf.md>)

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

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

Recorded evaluation configuration: {"training\_dataset":"BEAT"}. This record does not assert independent reproduction.

### MultiContext

FGD: 176.2. Result ID: 698b50098d67a41d0a6cfd94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79811e209131cea7dddf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68451e209131cea1af0f.md>)

[Implementation](<https://github.com/ai4r/Gesture-Generation-from-Trimodal-Context>)

Recorded evaluation configuration: {"training\_dataset":"BEAT"}. This record does not assert independent reproduction.

### Audio2Gesture

FGD: 223.8. Result ID: 698b50098d67a41d0a6cfd95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79811e209131cea7dddf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a8b1e209131cea28a9c.md>)

[Implementation](<https://jingli513.github.io/audio2gestures>)

Recorded evaluation configuration: {"training\_dataset":"BEAT"}. This record does not assert independent reproduction.

### Speech2Gesture

FGD: 256.7. Result ID: 698b50098d67a41d0a6cfd93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79811e209131cea7dddf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e11e209131cea0d19e.md>)

[Implementation](<http://people.eecs.berkeley.edu/~shiry/speech2gesture>)

Recorded evaluation configuration: {"training\_dataset":"BEAT"}. This record does not assert independent reproduction.

### Seq2Seq

FGD: 261.3. Result ID: 698b50098d67a41d0a6cfd92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79811e209131cea7dddf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65011e209131cea07c73.md>)

Recorded evaluation configuration: {"training\_dataset":"BEAT"}. This record does not assert independent reproduction.

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