# Foley sound synthesis on film clips

Source: [Foley sound synthesis on film clips](<https://www.sota2.com/research/sota/foley-sound-synthesis-on-film-clips>)

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

Data updated: 2026-04-08T08:57:29.540Z

Evaluation of models performing Foley sound synthesis specifically on the film clips dataset, assessed using metrics including IB, SRS, CCS, and AV-Sync.

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 | Foley sound synthesis |
| Dataset (including any stated split) | film clips |
| Metric | IB |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [IB](<https://www.sota2.com/research/sota/foley-sound-synthesis-on-film-clips.md?metric=IB>): Higher is better; unit: SCALAR.

- [SRS](<https://www.sota2.com/research/sota/foley-sound-synthesis-on-film-clips.md?metric=SRS>): Higher is better; unit: SCALAR.

- [CCS](<https://www.sota2.com/research/sota/foley-sound-synthesis-on-film-clips.md?metric=CCS>): Higher is better; unit: SCALAR.

- [AV-Sync](<https://www.sota2.com/research/sota/foley-sound-synthesis-on-film-clips.md?metric=AV-Sync>): Higher is better; unit: SCALAR.

## Recorded results

| Method | IB | Result date | Report paper |
| --- | --- | --- | --- |
| FoleyDesigner | 0.402 | Not recorded | 69d5e1077d0172140ec75a5e |
| SpatialSonic | 0.251 | Not recorded | 69d5e1077d0172140ec75a5e |
| Stable Audio | 0.216 | Not recorded | 69d5e1077d0172140ec75a5e |
| See2Sound | 0.105 | Not recorded | 69d5e1077d0172140ec75a5e |

### FoleyDesigner

IB: 0.402. Result ID: 69d617bc47f34ce924bec7c8.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e1077d0172140ec75a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d5e1077d0172140ec75a5e.md>)

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

### SpatialSonic

IB: 0.251. Result ID: 69d617bc47f34ce924bec7c7.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e1077d0172140ec75a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa771b1e209131cea710b6.md>)

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

### Stable Audio

IB: 0.216. Result ID: 69d617bc47f34ce924bec7c5.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e1077d0172140ec75a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74551e209131cea6122f.md>)

[Implementation](<https://huggingface.co/stabilityai/stable-audio-open-1.0/>)

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

### See2Sound

IB: 0.105. Result ID: 69d617bc47f34ce924bec7c6.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e1077d0172140ec75a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ec1e209131cea80012.md>)

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

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