# Spoken Question Answering Retrieval on SLUE SQA-5 Source: [Spoken Question Answering Retrieval on SLUE SQA-5]() Collection index: [llms.txt]() Data updated: 2026-04-14T08:40:55.583Z Evaluation of Spoken Question Answering Retrieval performance on the SLUE SQA-5 dataset, reporting Word Error Rate (WER) and Retrieval R@K metrics (R@1, R@5, R@10) for both Question-to-Context and Context-to-Question directions. 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 Retrieval | | Dataset (including any stated split) | SLUE SQA-5 | | Metric | R@10 (Q-C) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [R@10 (Q-C)](): Higher is better; unit: PERCENT. - [WER](): Lower is better; unit: PERCENT. - [R@1 (Q-C)](): Higher is better; unit: PERCENT. - [R@5 (Q-C)](): Higher is better; unit: PERCENT. - [R@1 (C-Q)](): Higher is better; unit: PERCENT. - [R@5 (C-Q)](): Higher is better; unit: PERCENT. - [R@10 (C-Q)](): Higher is better; unit: PERCENT. ## Recorded results | Method | R@10 (Q-C) | Result date | Report paper | | --- | --- | --- | --- | | BGE | 84.34 | Not recorded | 691565f90052cac1dc65d7e3 | | CLSR | 74.43 | Not recorded | 691565f90052cac1dc65d7e3 | | Whisper+BGE | 72.71 | Not recorded | 691565f90052cac1dc65d7e3 | | CLAP | 38.16 | Not recorded | 691565f90052cac1dc65d7e3 | | SpeechDPR | 19.94 | Not recorded | 691565f90052cac1dc65d7e3 | ### BGE R@10 (Q-C): 84.34. Result ID: 69ddfbf547f34ce924c56c70. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Paradigm":"E2E","Question Type":"Text","Context Type":"Text"}. This record does not assert independent reproduction. ### CLSR R@10 (Q-C): 74.43. Result ID: 69ddfbf547f34ce924c56c74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paradigm":"E2E","Question Type":"Speech","Context Type":"Speech"}. This record does not assert independent reproduction. ### Whisper+BGE R@10 (Q-C): 72.71. Result ID: 69ddfbf547f34ce924c56c73. [Reporting paper]() Recorded evaluation configuration: {"Paradigm":"Pipeline","Question Type":"Transcript","Context Type":"Transcript"}. This record does not assert independent reproduction. ### CLAP R@10 (Q-C): 38.16. Result ID: 69ddfbf547f34ce924c56c71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paradigm":"E2E","Question Type":"Text","Context Type":"Speech"}. This record does not assert independent reproduction. ### SpeechDPR R@10 (Q-C): 19.94. Result ID: 69ddfbf547f34ce924c56c72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paradigm":"E2E","Question Type":"Speech","Context Type":"Speech"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.