# Speaker Recognition on VoxCeleb1 original (vox1-o)

Source: [Speaker Recognition on VoxCeleb1 original (vox1-o)](<https://www.sota2.com/research/sota/speaker-recognition-on-voxceleb1-original-vox1-o>)

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

Data updated: 2026-04-16T07:45:57.540Z

Evaluation of Speaker Recognition performance on the original (vox1-o) split of the VoxCeleb1 dataset, typically measured using Equal Error Rate (EER).

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 | Speaker Recognition |
| Dataset (including any stated split) | VoxCeleb1 original (vox1-o) |
| Metric | EER (mean) |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 13 of 13 |
| 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 (mean)](<https://www.sota2.com/research/sota/speaker-recognition-on-voxceleb1-original-vox1-o.md?metric=EER%20(mean)>): Lower is better; unit: PERCENT.

- [EER Std Dev](<https://www.sota2.com/research/sota/speaker-recognition-on-voxceleb1-original-vox1-o.md?metric=EER%20Std%20Dev>): Lower is better; unit: PERCENT.

- [minDCF](<https://www.sota2.com/research/sota/speaker-recognition-on-voxceleb1-original-vox1-o.md?metric=minDCF>): Lower is better; unit: SCALAR.

- [OSCR](<https://www.sota2.com/research/sota/speaker-recognition-on-voxceleb1-original-vox1-o.md?metric=OSCR>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/speaker-recognition-on-voxceleb1-original-vox1-o.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | EER (mean) | Result date | Report paper |
| --- | --- | --- | --- |
| SpeakerRPL V2 | 0.24 | Not recorded | 69e06cf57d0172140ec7c922 |
| NEMO | 0.74 | Not recorded | 68fa71111e209131cea4f0cc |
| NEMO | 0.88 | Not recorded | 68fa71111e209131cea4f0cc |
| Proposed RecXi | 0.984 | Not recorded | 68fa71111e209131cea4f0cc |
| MCL-DPP-C | 1.44 | Not recorded | 68fa71111e209131cea4f0cc |
| ECAPA-TDNN | 1.61 | Not recorded | 68fa6c761e209131cea340cb |
| Direct Enrollment | 1.72 | Not recorded | 69e06cf57d0172140ec7c922 |
| IPA | 1.81 | Not recorded | 68fa71111e209131cea4f0cc |
| w2v2-aam | 1.91 | Not recorded | 68fa6c761e209131cea340cb |
| w2v2-ce | 2.25 | Not recorded | 68fa6c761e209131cea340cb |
| MCL-DPP | 2.89 | Not recorded | 68fa71111e209131cea4f0cc |
| x-vector | 5.22 | Not recorded | 68fa6c761e209131cea340cb |
| w2v2-bce | 7.28 | Not recorded | 68fa6c761e209131cea340cb |

### SpeakerRPL V2

EER (mean): 0.24. Result ID: 69e0939847f34ce924c9925e.

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

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

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

### NEMO

EER (mean): 0.74. Result ID: 699194803a6c31484909211f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0cc.md>)

Recorded evaluation configuration: {"Params (Million)":"15.88","Need Speaker Labels?":"Yes","Need Pre-trained ASR Model?":"No"}. This record does not assert independent reproduction.

### NEMO

EER (mean): 0.88. Result ID: 699194803a6c31484909211e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0cc.md>)

Recorded evaluation configuration: {"Params (Million)":"15.88","Need Speaker Labels?":"Yes","Need Pre-trained ASR Model?":"Yes"}. This record does not assert independent reproduction.

### Proposed RecXi

EER (mean): 0.984. Result ID: 699194803a6c314849092122.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0cc.md>)

Recorded evaluation configuration: {"Params (Million)":"7.06","Need Speaker Labels?":"Yes","Need Pre-trained ASR Model?":"No"}. This record does not assert independent reproduction.

### MCL-DPP-C

EER (mean): 1.44. Result ID: 699194803a6c314849092121.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc61e209131cea3c112.md>)

Recorded evaluation configuration: {"Params (Million)":"10.5","Need Speaker Labels?":"Pseudo label","Need Pre-trained ASR Model?":"No"}. This record does not assert independent reproduction.

### ECAPA-TDNN

EER (mean): 1.61. Result ID: 698f14a23a6c314849f590dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c761e209131cea340cb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a81e209131cea1d81d.md>)

Recorded evaluation configuration: {"input":"40-dimensional filterbanks","loss":"AAM softmax"}. This record does not assert independent reproduction.

### Direct Enrollment

EER (mean): 1.72. Result ID: 69e0939847f34ce924c9925d.

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

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

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

### IPA

EER (mean): 1.81. Result ID: 699194803a6c31484909211d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0cc.md>)

Recorded evaluation configuration: {"Params (Million)":"\>60","Need Speaker Labels?":"Yes","Need Pre-trained ASR Model?":"Yes"}. This record does not assert independent reproduction.

### w2v2-aam

EER (mean): 1.91. Result ID: 698f14a23a6c314849f590df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c761e209131cea340cb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c761e209131cea340cb.md>)

[Implementation](<https://www.sota2.com/github.com/nikvaessen/w2v2-speaker>)

Recorded evaluation configuration: {"pooling":"mean&std","loss":"AAM softmax","feature encoder":"frozen"}. This record does not assert independent reproduction.

### w2v2-ce

EER (mean): 2.25. Result ID: 698f14a23a6c314849f590de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c761e209131cea340cb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c761e209131cea340cb.md>)

[Implementation](<https://www.sota2.com/github.com/nikvaessen/w2v2-speaker>)

Recorded evaluation configuration: {"pooling":"mean&std","feature encoder":"frozen"}. This record does not assert independent reproduction.

### MCL-DPP

EER (mean): 2.89. Result ID: 699194803a6c314849092120.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc61e209131cea3c112.md>)

Recorded evaluation configuration: {"Params (Million)":"10.5","Need Speaker Labels?":"No","Need Pre-trained ASR Model?":"No"}. This record does not assert independent reproduction.

### x-vector

EER (mean): 5.22. Result ID: 698f14a23a6c314849f590dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c761e209131cea340cb.md>)

Recorded evaluation configuration: {"input":"40-dimensional filterbanks"}. This record does not assert independent reproduction.

### w2v2-bce

EER (mean): 7.28. Result ID: 698f14a23a6c314849f590e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c761e209131cea340cb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c761e209131cea340cb.md>)

[Implementation](<https://www.sota2.com/github.com/nikvaessen/w2v2-speaker>)

Recorded evaluation configuration: {"scoring":"computes scores directly","feature encoder":"frozen"}. This record does not assert independent reproduction.

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