# Audio Classification on FSDnoisy18k (1773 labels)

Source: [Audio Classification on FSDnoisy18k (1773 labels)](<https://www.sota2.com/research/sota/audio-classification-on-fsdnoisy18k-1773-labels>)

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

Data updated: 2026-02-26T06:07:19.376Z

Evaluation of audio classification performance using the FSDnoisy18k dataset, which contains 1773 labeled audio events.

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 | Audio Classification |
| Dataset (including any stated split) | FSDnoisy18k (1773 labels) |
| Metric | Top-1 Error Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 6 of 6 |
| 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

- [Top-1 Error Rate](<https://www.sota2.com/research/sota/audio-classification-on-fsdnoisy18k-1773-labels.md?metric=Top-1%20Error%20Rate>): Lower is better; unit: PERCENT.

- [Average Gain](<https://www.sota2.com/research/sota/audio-classification-on-fsdnoisy18k-1773-labels.md?metric=Average%20Gain>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Top-1 Error Rate | Result date | Report paper |
| --- | --- | --- | --- |
| FlexMatch + SemiReward | 25.63 | Not recorded | 68fa72451e209131cea556d1 |
| SoftMatch/FreeMatch + SemiReward | 26.1 | Not recorded | 68fa72451e209131cea556d1 |
| FlexMatch | 26.29 | Not recorded | 68fa72451e209131cea556d1 |
| SoftMatch/FreeMatch | 29.39 | Not recorded | 68fa72451e209131cea556d1 |
| Pseudo Label + SemiReward | 33.24 | Not recorded | 68fa72451e209131cea556d1 |
| Pseudo Label | 34.6 | Not recorded | 68fa72451e209131cea556d1 |

### FlexMatch + SemiReward

Top-1 Error Rate: 25.63. Result ID: 699229363a6c3148490cff4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

Recorded evaluation configuration: {"Backbone":"Hubert \[Hsu et al., 2021\]","SemiReward":true}. This record does not assert independent reproduction.

### SoftMatch/FreeMatch + SemiReward

Top-1 Error Rate: 26.1. Result ID: 699229363a6c3148490cff4d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

Recorded evaluation configuration: {"Backbone":"Hubert \[Hsu et al., 2021\]","SemiReward":true}. This record does not assert independent reproduction.

### FlexMatch

Top-1 Error Rate: 26.29. Result ID: 699229363a6c3148490cff4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

Recorded evaluation configuration: {"Backbone":"Hubert \[Hsu et al., 2021\]","SemiReward":false}. This record does not assert independent reproduction.

### SoftMatch/FreeMatch

Top-1 Error Rate: 29.39. Result ID: 699229363a6c3148490cff4c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

Recorded evaluation configuration: {"Backbone":"Hubert \[Hsu et al., 2021\]","SemiReward":false}. This record does not assert independent reproduction.

### Pseudo Label + SemiReward

Top-1 Error Rate: 33.24. Result ID: 699229363a6c3148490cff49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

Recorded evaluation configuration: {"Backbone":"Hubert \[Hsu et al., 2021\]","SemiReward":true}. This record does not assert independent reproduction.

### Pseudo Label

Top-1 Error Rate: 34.6. Result ID: 699229363a6c3148490cff48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556d1.md>)

Recorded evaluation configuration: {"Backbone":"Hubert \[Hsu et al., 2021\]","SemiReward":false}. This record does not assert independent reproduction.

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