# Speech Detection on LibriBrain (holdout)

Source: [Speech Detection on LibriBrain (holdout)](<https://www.sota2.com/research/sota/speech-detection-on-libribrain-holdout>)

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

Data updated: 2026-02-27T10:57:06.038Z

Evaluation of Speech Detection performance on the holdout split of the LibriBrain dataset, measured using metrics such as F1-macro.

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 | Speech Detection |
| Dataset (including any stated split) | LibriBrain (holdout) |
| Metric | F1-macro |
| Unit | PERCENT |
| Direction | Higher 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

- [F1-macro](<https://www.sota2.com/research/sota/speech-detection-on-libribrain-holdout.md?metric=F1-macro>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1-macro | Result date | Report paper |
| --- | --- | --- | --- |
| Best (Standard track) | 91.66 | Not recorded | 692e7311d6b0dd3342932718 |
| MEGConformer | 88.9 | Not recorded | 692e7311d6b0dd3342932718 |
| 10th place | 88.89 | Not recorded | 692e7311d6b0dd3342932718 |
| Baseline | 68.04 | Not recorded | 692e7311d6b0dd3342932718 |
| Naive Baseline | 45.3 | Not recorded | 692e7311d6b0dd3342932718 |

### Best (Standard track)

F1-macro: 91.66. Result ID: 69a1787b35dfcabb00e743d3.

[Reporting paper](<https://www.sota2.com/research/paper/692e7311d6b0dd3342932718.md>)

Recorded evaluation configuration: {"Track":"Standard track"}. This record does not assert independent reproduction.

### MEGConformer

F1-macro: 88.9. Result ID: 69a1787b35dfcabb00e743d2.

[Reporting paper](<https://www.sota2.com/research/paper/692e7311d6b0dd3342932718.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692e7311d6b0dd3342932718.md>)

[Implementation](<https://github.com/neural2speech/libribrain-experiments>)

Recorded evaluation configuration: {"Track":"Standard track"}. This record does not assert independent reproduction.

### 10th place

F1-macro: 88.89. Result ID: 69a1787b35dfcabb00e743d1.

[Reporting paper](<https://www.sota2.com/research/paper/692e7311d6b0dd3342932718.md>)

Recorded evaluation configuration: {"Track":"Standard track"}. This record does not assert independent reproduction.

### Baseline

F1-macro: 68.04. Result ID: 69a1787b35dfcabb00e743d0.

[Reporting paper](<https://www.sota2.com/research/paper/692e7311d6b0dd3342932718.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79531e209131cea7d173.md>)

Recorded evaluation configuration: {"Track":"Standard track"}. This record does not assert independent reproduction.

### Naive Baseline

F1-macro: 45.3. Result ID: 69a1787b35dfcabb00e743cf.

[Reporting paper](<https://www.sota2.com/research/paper/692e7311d6b0dd3342932718.md>)

Recorded evaluation configuration: {"Track":"Standard track"}. This record does not assert independent reproduction.

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