# Open-set Speaker Identification on VoxCeleb2 (test)

Source: [Open-set Speaker Identification on VoxCeleb2 (test)](<https://www.sota2.com/research/sota/open-set-speaker-identification-on-voxceleb2-test>)

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

Data updated: 2026-04-16T07:45:57.417Z

Evaluation of Open-set Speaker Identification performance on the test split of the VoxCeleb2 dataset, typically measured using EER, minDCF, OSCR, and ACC.

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 | Open-set speaker identification |
| Dataset (including any stated split) | VoxCeleb2 (test) |
| Metric | EER |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 12 of 12 |
| 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

- [EER](<https://www.sota2.com/research/sota/open-set-speaker-identification-on-voxceleb2-test.md?metric=EER>): Lower is better; unit: PERCENT.

- [minDCF](<https://www.sota2.com/research/sota/open-set-speaker-identification-on-voxceleb2-test.md?metric=minDCF>): Lower is better; unit: SCALAR.

- [OSCR](<https://www.sota2.com/research/sota/open-set-speaker-identification-on-voxceleb2-test.md?metric=OSCR>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/open-set-speaker-identification-on-voxceleb2-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | EER | Result date | Report paper |
| --- | --- | --- | --- |
| SpeakerRPL V2 (proposed) | 0.44 | Not recorded | 69e06cf57d0172140ec7c922 |
| SpeakerRPL V2 w/ naive fusion | 0.49 | Not recorded | 69e06cf57d0172140ec7c922 |
| SpeakerRPL V2 w/o fusion | 0.54 | Not recorded | 69e06cf57d0172140ec7c922 |
| AM-Softmax | 0.58 | Not recorded | 69e06cf57d0172140ec7c922 |
| AAM-Softmax | 0.58 | Not recorded | 69e06cf57d0172140ec7c922 |
| Softmax | 0.69 | Not recorded | 69e06cf57d0172140ec7c922 |
| Prototype | 0.72 | Not recorded | 69e06cf57d0172140ec7c922 |
| SpeakerRPL V1 | 0.76 | Not recorded | 69e06cf57d0172140ec7c922 |
| Direct Enrollment | 3.74 | Not recorded | 69e06cf57d0172140ec7c922 |
| SpeakerRPL V1 w/o Target aug | 3.76 | Not recorded | 69e06cf57d0172140ec7c922 |
| Direct Enrollment +Target aug | 3.84 | Not recorded | 69e06cf57d0172140ec7c922 |
| SpeakerRPL V1 w/o Unknown speakers | 3.86 | Not recorded | 69e06cf57d0172140ec7c922 |

### SpeakerRPL V2 (proposed)

EER: 0.44. Result ID: 69e0939847f34ce924c99242.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":true,"Adaptive anchor":true,"Model Fusion":true}. This record does not assert independent reproduction.

### SpeakerRPL V2 w/ naive fusion

EER: 0.49. Result ID: 69e0939847f34ce924c99241.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":true,"Adaptive anchor":true,"Model Fusion":true}. This record does not assert independent reproduction.

### SpeakerRPL V2 w/o fusion

EER: 0.54. Result ID: 69e0939847f34ce924c9923c.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":true,"Adaptive anchor":true,"Model Fusion":false}. This record does not assert independent reproduction.

### AM-Softmax

EER: 0.58. Result ID: 69e0939847f34ce924c9923e.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":true,"Adaptive anchor":true,"Model Fusion":false}. This record does not assert independent reproduction.

### AAM-Softmax

EER: 0.58. Result ID: 69e0939847f34ce924c9923f.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":true,"Adaptive anchor":true,"Model Fusion":false}. This record does not assert independent reproduction.

### Softmax

EER: 0.69. Result ID: 69e0939847f34ce924c9923d.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":true,"Adaptive anchor":true,"Model Fusion":false}. This record does not assert independent reproduction.

### Prototype

EER: 0.72. Result ID: 69e0939847f34ce924c99240.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7fe31e209131cea9b638.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":true,"Adaptive anchor":true,"Model Fusion":false}. This record does not assert independent reproduction.

### SpeakerRPL V1

EER: 0.76. Result ID: 69e0939847f34ce924c9923b.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":true,"Adaptive anchor":false,"Model Fusion":false}. This record does not assert independent reproduction.

### Direct Enrollment

EER: 3.74. Result ID: 69e0939847f34ce924c99237.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa80141e209131cea9be93.md>)

Recorded evaluation configuration: {"Target speaker augmentation":false,"Unknown speaker augmentation":false,"Adaptive anchor":false,"Model Fusion":false}. This record does not assert independent reproduction.

### SpeakerRPL V1 w/o Target aug

EER: 3.76. Result ID: 69e0939847f34ce924c99239.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

Recorded evaluation configuration: {"Target speaker augmentation":false,"Unknown speaker augmentation":false,"Adaptive anchor":false,"Model Fusion":false}. This record does not assert independent reproduction.

### Direct Enrollment +Target aug

EER: 3.84. Result ID: 69e0939847f34ce924c99238.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa80141e209131cea9be93.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":false,"Adaptive anchor":false,"Model Fusion":false}. This record does not assert independent reproduction.

### SpeakerRPL V1 w/o Unknown speakers

EER: 3.86. Result ID: 69e0939847f34ce924c9923a.

[Reporting paper](<https://www.sota2.com/research/paper/69e06cf57d0172140ec7c922.md>)

Recorded evaluation configuration: {"Target speaker augmentation":true,"Unknown speaker augmentation":false,"Adaptive anchor":false,"Model Fusion":false}. This record does not assert independent reproduction.

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