# Speech-to-Speech Translation (en2fra) on CVSS-T Source: [Speech-to-Speech Translation (en2fra) on CVSS-T]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:37:10.542Z Evaluation of Speech-to-Speech Translation performance for the English-to-French (en2fra) direction on the CVSS-T dataset, reporting BLEU scores. 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-Speech Translation (en2fra) | | Dataset (including any stated split) | CVSS-T | | Metric | BLEU Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [BLEU Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | BLEU Score | Result date | Report paper | | --- | --- | --- | --- | | S2T+TTS | 25.37 | Not recorded | 6976f4e6a2b28e761d87c0c7 | | Chain of Modality | 22.54 | Not recorded | 6976f4e6a2b28e761d87c0c7 | | Chain of Modality | 22.24 | Not recorded | 6976f4e6a2b28e761d87c0c7 | | Chain of Modality | 18.61 | Not recorded | 6976f4e6a2b28e761d87c0c7 | | Tri-Task Learning | 17.11 | Not recorded | 6976f4e6a2b28e761d87c0c7 | | Vanilla | 16.95 | Not recorded | 6976f4e6a2b28e761d87c0c7 | | Tri-Task Learning | 16.95 | Not recorded | 6976f4e6a2b28e761d87c0c7 | | Vanilla | 16.75 | Not recorded | 6976f4e6a2b28e761d87c0c7 | | Tri-Task Learning | 14.14 | Not recorded | 6976f4e6a2b28e761d87c0c7 | | Vanilla | 12.53 | Not recorded | 6976f4e6a2b28e761d87c0c7 | ### S2T+TTS BLEU Score: 25.37. Result ID: 699671de5698665ec4b9095b. [Reporting paper]() Recorded evaluation configuration: {"System":"Cascaded"}. This record does not assert independent reproduction. ### Chain of Modality BLEU Score: 22.54. Result ID: 699671de5698665ec4b90964. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"System":"End-to-end","Optimization Stage":"After DPO","Back-translation Evaluation Metric":"BLEU"}. This record does not assert independent reproduction. ### Chain of Modality BLEU Score: 22.24. Result ID: 699671de5698665ec4b90961. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"System":"End-to-end","Optimization Stage":"After DPO","Back-translation Evaluation Metric":"METEOR"}. This record does not assert independent reproduction. ### Chain of Modality BLEU Score: 18.61. Result ID: 699671de5698665ec4b9095e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"System":"End-to-end","Optimization Stage":"Before DPO"}. This record does not assert independent reproduction. ### Tri-Task Learning BLEU Score: 17.11. Result ID: 699671de5698665ec4b90960. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"System":"End-to-end","Optimization Stage":"After DPO","Back-translation Evaluation Metric":"METEOR"}. This record does not assert independent reproduction. ### Vanilla BLEU Score: 16.95. Result ID: 699671de5698665ec4b9095f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"System":"End-to-end","Optimization Stage":"After DPO","Back-translation Evaluation Metric":"METEOR"}. This record does not assert independent reproduction. ### Tri-Task Learning BLEU Score: 16.95. Result ID: 699671de5698665ec4b90963. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"System":"End-to-end","Optimization Stage":"After DPO","Back-translation Evaluation Metric":"BLEU"}. This record does not assert independent reproduction. ### Vanilla BLEU Score: 16.75. Result ID: 699671de5698665ec4b90962. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"System":"End-to-end","Optimization Stage":"After DPO","Back-translation Evaluation Metric":"BLEU"}. This record does not assert independent reproduction. ### Tri-Task Learning BLEU Score: 14.14. Result ID: 699671de5698665ec4b9095d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"System":"End-to-end","Optimization Stage":"Before DPO"}. This record does not assert independent reproduction. ### Vanilla BLEU Score: 12.53. Result ID: 699671de5698665ec4b9095c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"System":"End-to-end","Optimization Stage":"Before DPO"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.