# Foreground Speaker Diarization on MMCSG

Source: [Foreground Speaker Diarization on MMCSG](<https://www.sota2.com/research/sota/foreground-speaker-diarization-on-mmcsg>)

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

Data updated: 2026-03-12T09:24:15.266Z

Evaluation of Foreground Speaker Diarization performance on the MMCSG dataset, including metrics like Miss Detection, False Alarm, Speaker Confusion, and DER.

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 | Foreground Speaker Diarization |
| Dataset (including any stated split) | MMCSG |
| Metric | Miss Detection |
| Unit | SCALAR |
| Direction | Lower 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

- [Miss Detection](<https://www.sota2.com/research/sota/foreground-speaker-diarization-on-mmcsg.md?metric=Miss%20Detection>): Lower is better; unit: SCALAR.

- [False Alarm](<https://www.sota2.com/research/sota/foreground-speaker-diarization-on-mmcsg.md?metric=False%20Alarm>): Lower is better; unit: SCALAR.

- [Speaker Confusion](<https://www.sota2.com/research/sota/foreground-speaker-diarization-on-mmcsg.md?metric=Speaker%20Confusion>): Lower is better; unit: SCALAR.

- [DER](<https://www.sota2.com/research/sota/foreground-speaker-diarization-on-mmcsg.md?metric=DER>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Miss Detection | Result date | Report paper |
| --- | --- | --- | --- |
| Whisper-Large | 3.5 | Not recorded | 69b2488ed030084c22e2f8df |
| Whisper-Small | 3.6 | Not recorded | 69b2488ed030084c22e2f8df |
| VoxCare-ResNet | 5.6 | Not recorded | 69b2488ed030084c22e2f8df |
| ResNet | 6.3 | Not recorded | 69b2488ed030084c22e2f8df |
| Whisper-Tiny | 9.8 | Not recorded | 69b2488ed030084c22e2f8df |

### Whisper-Large

Miss Detection: 3.5. Result ID: 69b285e36dbb7075b95d7114.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ed030084c22e2f8df.md>)

Recorded evaluation configuration: {"Model Category":"Teacher Model"}. This record does not assert independent reproduction.

### Whisper-Small

Miss Detection: 3.6. Result ID: 69b285e36dbb7075b95d7113.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ed030084c22e2f8df.md>)

Recorded evaluation configuration: {"Model Category":"Teacher Model"}. This record does not assert independent reproduction.

### VoxCare-ResNet

Miss Detection: 5.6. Result ID: 69b285e36dbb7075b95d7116.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ed030084c22e2f8df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b2488ed030084c22e2f8df.md>)

Recorded evaluation configuration: {"Model Category":"Student Model"}. This record does not assert independent reproduction.

### ResNet

Miss Detection: 6.3. Result ID: 69b285e36dbb7075b95d7115.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ed030084c22e2f8df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62321e209131ce9f8328.md>)

Recorded evaluation configuration: {"Model Category":"Student Model"}. This record does not assert independent reproduction.

### Whisper-Tiny

Miss Detection: 9.8. Result ID: 69b285e36dbb7075b95d7112.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ed030084c22e2f8df.md>)

Recorded evaluation configuration: {"Model Category":"Teacher Model"}. This record does not assert independent reproduction.

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