# Spoken Question Answering on SQuAD lost (test)

Source: [Spoken Question Answering on SQuAD lost (test)](<https://www.sota2.com/research/sota/spoken-question-answering-on-squad-lost-test>)

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

Data updated: 2026-02-26T05:43:02.324Z

Evaluation of model performance on the test split of the SQuAD lost dataset for Spoken Question Answering, reporting F1 and AOS 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) | SQuAD lost (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/spoken-question-answering-on-squad-lost-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [AOS](<https://www.sota2.com/research/sota/spoken-question-answering-on-squad-lost-test.md?metric=AOS>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| SpeechBERT | 37.31 | Not recorded | 68fa682b1e209131cea1a7b9 |
| BERT | 30.78 | Not recorded | 68fa682b1e209131cea1a7b9 |

### SpeechBERT

F1 Score: 37.31. Result ID: 698d5f148b517eb43320ff2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa682b1e209131cea1a7b9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682b1e209131cea1a7b9.md>)

Recorded evaluation configuration: {"Architecture":"End-to-end","Training Set":"Audio"}. This record does not assert independent reproduction.

### BERT

F1 Score: 30.78. Result ID: 698d5f148b517eb43320ff29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa682b1e209131cea1a7b9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Architecture":"Cascade","Training Set":"ASR"}. This record does not assert independent reproduction.

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