# Speech-to-Portrait on VoxCeleb (test) Source: [Speech-to-Portrait on VoxCeleb (test)]() Collection index: [llms.txt]() Data updated: 2026-03-04T12:14:08.321Z Evaluation of Speech-to-Portrait generation performance on the test split of the VoxCeleb dataset, measured using metrics related to reconstruction quality (L1, L2, Cosine similarity) and demographic prediction accuracy (Gender, Age, Rank metrics). 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-to-Portrait | | Dataset (including any stated split) | VoxCeleb (test) | | Metric | L1 Error | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 14 of 14 | | 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 - [L1 Error](): Lower is better; unit: SCALAR. - [L2 Error](): Lower is better; unit: SCALAR. - [Cosine Similarity](): Higher is better; unit: SCALAR. - [Gender Accuracy](): Higher is better; unit: PERCENT. - [Age Accuracy](): Higher is better; unit: PERCENT. - [Rank-1 Accuracy](): Higher is better; unit: SCALAR. - [Rank-2 Accuracy](): Higher is better; unit: SCALAR. - [Rank-5 Accuracy](): Higher is better; unit: SCALAR. ## Recorded results | Method | L1 Error | Result date | Report paper | | --- | --- | --- | --- | | SCLDM | 25.24 | Not recorded | 690836f03ef7ccd74e5e5345 | | SCLDM | 25.24 | Not recorded | 690836f03ef7ccd74e5e5345 | | Kato et al. | 40.11 | Not recorded | 690836f03ef7ccd74e5e5345 | | Kato et al. | 40.11 | Not recorded | 690836f03ef7ccd74e5e5345 | | Choi et al. | 56.32 | Not recorded | 690836f03ef7ccd74e5e5345 | | Choi et al. | 56.32 | Not recorded | 690836f03ef7ccd74e5e5345 | | Wen et al. | 59.82 | Not recorded | 690836f03ef7ccd74e5e5345 | | Wen et al. | 59.82 | Not recorded | 690836f03ef7ccd74e5e5345 | | Speech2Face | 66.46 | Not recorded | 690836f03ef7ccd74e5e5345 | | Speech2Face | 66.46 | Not recorded | 690836f03ef7ccd74e5e5345 | | SF2F | 78.45 | Not recorded | 690836f03ef7ccd74e5e5345 | | SF2F | 78.45 | Not recorded | 690836f03ef7ccd74e5e5345 | | Wav2Pix | 137.58 | Not recorded | 690836f03ef7ccd74e5e5345 | | Wav2Pix | 137.58 | Not recorded | 690836f03ef7ccd74e5e5345 | ### SCLDM L1 Error: 25.24. Result ID: 69a821fc6dbb7075b94e33f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"-"}. This record does not assert independent reproduction. ### SCLDM L1 Error: 25.24. Result ID: 69a821fc6dbb7075b94e3404. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"-"}. This record does not assert independent reproduction. ### Kato et al. L1 Error: 40.11. Result ID: 69a821fc6dbb7075b94e33f6. [Reporting paper]() Recorded evaluation configuration: {"Year":"2023"}. This record does not assert independent reproduction. ### Kato et al. L1 Error: 40.11. Result ID: 69a821fc6dbb7075b94e3403. [Reporting paper]() Recorded evaluation configuration: {"Year":"2023"}. This record does not assert independent reproduction. ### Choi et al. L1 Error: 56.32. Result ID: 69a821fc6dbb7075b94e33f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2019"}. This record does not assert independent reproduction. ### Choi et al. L1 Error: 56.32. Result ID: 69a821fc6dbb7075b94e3401. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2019"}. This record does not assert independent reproduction. ### Wen et al. L1 Error: 59.82. Result ID: 69a821fc6dbb7075b94e33f3. [Reporting paper]() Recorded evaluation configuration: {"Year":"2019"}. This record does not assert independent reproduction. ### Wen et al. L1 Error: 59.82. Result ID: 69a821fc6dbb7075b94e3400. [Reporting paper]() Recorded evaluation configuration: {"Year":"2019"}. This record does not assert independent reproduction. ### Speech2Face L1 Error: 66.46. Result ID: 69a821fc6dbb7075b94e33f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2019"}. This record does not assert independent reproduction. ### Speech2Face L1 Error: 66.46. Result ID: 69a821fc6dbb7075b94e33ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2019"}. This record does not assert independent reproduction. ### SF2F L1 Error: 78.45. Result ID: 69a821fc6dbb7075b94e33f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2022"}. This record does not assert independent reproduction. ### SF2F L1 Error: 78.45. Result ID: 69a821fc6dbb7075b94e3402. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2022"}. This record does not assert independent reproduction. ### Wav2Pix L1 Error: 137.58. Result ID: 69a821fc6dbb7075b94e33f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2019"}. This record does not assert independent reproduction. ### Wav2Pix L1 Error: 137.58. Result ID: 69a821fc6dbb7075b94e33fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Year":"2019"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.