# Spoken Question Answering Retrieval on LibriSQA

Source: [Spoken Question Answering Retrieval on LibriSQA](<https://www.sota2.com/research/sota/spoken-question-answering-retrieval-on-librisqa>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T08:40:55.552Z

Evaluation of spoken question answering retrieval performance on the LibriSQA dataset, including Word Error Rate (WER) and Retrieval metrics (R@K).

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) | LibriSQA |
| Metric | R@1 (Q-C) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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@1 (Q-C)](<https://www.sota2.com/research/sota/spoken-question-answering-retrieval-on-librisqa.md?metric=R%401%20(Q-C)>): Higher is better; unit: PERCENT.

- [WER](<https://www.sota2.com/research/sota/spoken-question-answering-retrieval-on-librisqa.md?metric=WER>): Lower is better; unit: SCALAR.

- [R@5 (Q-C)](<https://www.sota2.com/research/sota/spoken-question-answering-retrieval-on-librisqa.md?metric=R%405%20(Q-C)>): Higher is better; unit: PERCENT.

- [R@10 (Q-C)](<https://www.sota2.com/research/sota/spoken-question-answering-retrieval-on-librisqa.md?metric=R%4010%20(Q-C)>): Higher is better; unit: PERCENT.

- [R@1 (C-Q)](<https://www.sota2.com/research/sota/spoken-question-answering-retrieval-on-librisqa.md?metric=R%401%20(C-Q)>): Higher is better; unit: PERCENT.

- [R@5 (C-Q)](<https://www.sota2.com/research/sota/spoken-question-answering-retrieval-on-librisqa.md?metric=R%405%20(C-Q)>): Higher is better; unit: PERCENT.

- [R@10 (C-Q)](<https://www.sota2.com/research/sota/spoken-question-answering-retrieval-on-librisqa.md?metric=R%4010%20(C-Q)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | R@1 (Q-C) | Result date | Report paper |
| --- | --- | --- | --- |
| BGE | 86.91 | Not recorded | 691565f90052cac1dc65d7e3 |
| CLSR | 85.04 | Not recorded | 691565f90052cac1dc65d7e3 |
| Whisper+BGE | 83.7 | Not recorded | 691565f90052cac1dc65d7e3 |
| CLAP | 0.04 | Not recorded | 691565f90052cac1dc65d7e3 |

### BGE

R@1 (Q-C): 86.91. Result ID: 69ddfbf547f34ce924c56c6c.

[Reporting paper](<https://www.sota2.com/research/paper/691565f90052cac1dc65d7e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d91e209131cea5e7ab.md>)

[Implementation](<https://github.com/FlagOpen/FlagEmbedding>)

Recorded evaluation configuration: {"Paradigm":"E2E","Question Type":"Text","Context Type":"Text"}. This record does not assert independent reproduction.

### CLSR

R@1 (Q-C): 85.04. Result ID: 69ddfbf547f34ce924c56c6f.

[Reporting paper](<https://www.sota2.com/research/paper/691565f90052cac1dc65d7e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691565f90052cac1dc65d7e3.md>)

Recorded evaluation configuration: {"Paradigm":"E2E","Question Type":"Text","Context Type":"Speech"}. This record does not assert independent reproduction.

### Whisper+BGE

R@1 (Q-C): 83.7. Result ID: 69ddfbf547f34ce924c56c6e.

[Reporting paper](<https://www.sota2.com/research/paper/691565f90052cac1dc65d7e3.md>)

Recorded evaluation configuration: {"Paradigm":"Pipeline","Question Type":"Text","Context Type":"Transcript"}. This record does not assert independent reproduction.

### CLAP

R@1 (Q-C): 0.04. Result ID: 69ddfbf547f34ce924c56c6d.

[Reporting paper](<https://www.sota2.com/research/paper/691565f90052cac1dc65d7e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729e1e209131cea57959.md>)

Recorded evaluation configuration: {"Paradigm":"E2E","Question Type":"Text","Context Type":"Speech"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.