# Speech Representation Evaluation on VoxCeleb 1 (test) Source: [Speech Representation Evaluation on VoxCeleb 1 (test)]() Collection index: [llms.txt]() Data updated: 2026-04-28T06:40:00.362Z Evaluation of general speech model quality using the SUPERBS benchmark suite on the test split of the VoxCeleb 1 dataset. 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 Representation Evaluation | | Dataset (including any stated split) | VoxCeleb 1 (test) | | Metric | SUPERB Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [SUPERB Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | SUPERB Score | Result date | Report paper | | --- | --- | --- | --- | | Speech-FT | 876.1 | Not recorded | 68fa78c51e209131cea7a6a1 | | Pre-trained | 870.2 | Not recorded | 68fa78c51e209131cea7a6a1 | | Speech-FT | 868.26 | Not recorded | 68fa78c51e209131cea7a6a1 | | Stable-FT | 867.96 | Not recorded | 68fa78c51e209131cea7a6a1 | | Speech-FT | 866.51 | Not recorded | 68fa78c51e209131cea7a6a1 | | Stable-FT (20%) | 832.37 | Not recorded | 68fa78c51e209131cea7a6a1 | | Stable-FT | 789.88 | Not recorded | 68fa78c51e209131cea7a6a1 | | Stable-FT | 747.5 | Not recorded | 68fa78c51e209131cea7a6a1 | ### Speech-FT SUPERB Score: 876.1. Result ID: 69f0555b47f34ce924d58408. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning Source":"English (mono-lingual)"}. This record does not assert independent reproduction. ### Pre-trained SUPERB Score: 870.2. Result ID: 69f0555b47f34ce924d5840a. [Reporting paper]() Recorded evaluation configuration: {"Note":"Original HuBERT model"}. This record does not assert independent reproduction. ### Speech-FT SUPERB Score: 868.26. Result ID: 69f0555b47f34ce924d58406. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning Source":"Spanish (cross-lingual)"}. This record does not assert independent reproduction. ### Stable-FT SUPERB Score: 867.96. Result ID: 69f0555b47f34ce924d58409. [Reporting paper]() Recorded evaluation configuration: {"Fine-tuning Source":"English (mono-lingual)"}. This record does not assert independent reproduction. ### Speech-FT SUPERB Score: 866.51. Result ID: 69f0555b47f34ce924d58403. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning Source":"Chinese (cross-lingual)"}. This record does not assert independent reproduction. ### Stable-FT (20%) SUPERB Score: 832.37. Result ID: 69f0555b47f34ce924d58405. [Reporting paper]() Recorded evaluation configuration: {"Fine-tuning Source":"Chinese (cross-lingual)","Snapshot":"20% of total fine-tuning steps"}. This record does not assert independent reproduction. ### Stable-FT SUPERB Score: 789.88. Result ID: 69f0555b47f34ce924d58404. [Reporting paper]() Recorded evaluation configuration: {"Fine-tuning Source":"Chinese (cross-lingual)"}. This record does not assert independent reproduction. ### Stable-FT SUPERB Score: 747.5. Result ID: 69f0555b47f34ce924d58407. [Reporting paper]() Recorded evaluation configuration: {"Fine-tuning Source":"Spanish (cross-lingual)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.