# Spoken Question Answering on S-SQuAD (test) Source: [Spoken Question Answering on S-SQuAD (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:33.710Z Evaluation of model performance on the test split of the S-SQuAD dataset for Spoken Question Answering, reporting EM and F1 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 | Spoken Question Answering | | Dataset (including any stated split) | S-SQuAD (test) | | Metric | EM | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [EM](): Higher is better; unit: PERCENT. - [F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM | Result date | Report paper | | --- | --- | --- | --- | | ALBERT-base + DA + KD | 64.1 | Not recorded | 68fa6c631e209131cea33c54 | | BERT-base + DA + KD | 63.3 | Not recorded | 68fa6c631e209131cea33c54 | | ALBERT-base + KD | 61.9 | Not recorded | 68fa6c631e209131cea33c54 | | ALBERT-base + DA | 61.2 | Not recorded | 68fa6c631e209131cea33c54 | | BERT-base + DA | 61 | Not recorded | 68fa6c631e209131cea33c54 | | BERT-base + KD | 61 | Not recorded | 68fa6c631e209131cea33c54 | | SDNet + DA + KD | 60.9 | Not recorded | 68fa6c631e209131cea33c54 | | ALBERT-base | 59.4 | Not recorded | 68fa6c631e209131cea33c54 | | SDNet + DA | 59.3 | Not recorded | 68fa6c631e209131cea33c54 | | SDNet + KD | 59.2 | Not recorded | 68fa6c631e209131cea33c54 | | BERT-base | 58.6 | Not recorded | 68fa6c631e209131cea33c54 | | SDNet | 57.8 | Not recorded | 68fa6c631e209131cea33c54 | | FlowQA + DA + KD | 52.8 | Not recorded | 68fa6c631e209131cea33c54 | | FlowQA + KD | 50.9 | Not recorded | 68fa6c631e209131cea33c54 | | FlowQA + DA | 50.4 | Not recorded | 68fa6c631e209131cea33c54 | | FlowQA | 49.1 | Not recorded | 68fa6c631e209131cea33c54 | ### ALBERT-base + DA + KD EM: 64.1. Result ID: 698f0f643a6c314849f55940. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"ALBERT-base","Dual Attention":true,"Knowledge Distillation":true}. This record does not assert independent reproduction. ### BERT-base + DA + KD EM: 63.3. Result ID: 698f0f643a6c314849f5593c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"BERT-base","Dual Attention":true,"Knowledge Distillation":true}. This record does not assert independent reproduction. ### ALBERT-base + KD EM: 61.9. Result ID: 698f0f643a6c314849f5593f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"ALBERT-base","Knowledge Distillation":true}. This record does not assert independent reproduction. ### ALBERT-base + DA EM: 61.2. Result ID: 698f0f643a6c314849f5593e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"ALBERT-base","Dual Attention":true}. This record does not assert independent reproduction. ### BERT-base + DA EM: 61. Result ID: 698f0f643a6c314849f5593a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"BERT-base","Dual Attention":true}. This record does not assert independent reproduction. ### BERT-base + KD EM: 61. Result ID: 698f0f643a6c314849f5593b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"BERT-base","Knowledge Distillation":true}. This record does not assert independent reproduction. ### SDNet + DA + KD EM: 60.9. Result ID: 698f0f643a6c314849f55938. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"SDNet","Dual Attention":true,"Knowledge Distillation":true}. This record does not assert independent reproduction. ### ALBERT-base EM: 59.4. Result ID: 698f0f643a6c314849f5593d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"ALBERT-base"}. This record does not assert independent reproduction. ### SDNet + DA EM: 59.3. Result ID: 698f0f643a6c314849f55936. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"SDNet","Dual Attention":true}. This record does not assert independent reproduction. ### SDNet + KD EM: 59.2. Result ID: 698f0f643a6c314849f55937. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"SDNet","Knowledge Distillation":true}. This record does not assert independent reproduction. ### BERT-base EM: 58.6. Result ID: 698f0f643a6c314849f55939. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"BERT-base"}. This record does not assert independent reproduction. ### SDNet EM: 57.8. Result ID: 698f0f643a6c314849f55935. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"SDNet"}. This record does not assert independent reproduction. ### FlowQA + DA + KD EM: 52.8. Result ID: 698f0f643a6c314849f55934. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"FlowQA","Dual Attention":true,"Knowledge Distillation":true}. This record does not assert independent reproduction. ### FlowQA + KD EM: 50.9. Result ID: 698f0f643a6c314849f55933. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"FlowQA","Knowledge Distillation":true}. This record does not assert independent reproduction. ### FlowQA + DA EM: 50.4. Result ID: 698f0f643a6c314849f55932. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"FlowQA","Dual Attention":true}. This record does not assert independent reproduction. ### FlowQA EM: 49.1. Result ID: 698f0f643a6c314849f55931. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"FlowQA"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.