# Spoken Question Answering on Spoken SQuAD (test)

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

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

Data updated: 2026-02-26T05:30:57.033Z

Evaluation of model performance on the test split of the Spoken SQuAD 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) | Spoken SQuAD (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

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

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

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Transcripts + EuroLLM 9B | 91.1 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| Transcripts + Llama 3.1 8B | 89.2 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| Seamless ASR + EuroLLM 9B | 89.2 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| SpeechMapper | 87.9 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| BEST-IWSLT25-IF | 87.4 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| SpeechMapper | 87.4 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| Seamless ASR + Llama 3.1 8B | 85.6 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| SpeechMapper | 75.1 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| SpeechMapper | 72.3 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| SpeechMapper | 62.3 | Not recorded | 697ae9afa2b28e761d87d0a0 |
| SpeechMapper | 61.9 | Not recorded | 697ae9afa2b28e761d87d0a0 |

### Transcripts + EuroLLM 9B

Accuracy: 91.1. Result ID: 699666be5698665ec4ad1b75.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c25.md>)

Recorded evaluation configuration: {"Backbone":"EuroLLM 9B","Input Mode":"Transcripts","Evaluation Protocol":"topline"}. This record does not assert independent reproduction.

### Transcripts + Llama 3.1 8B

Accuracy: 89.2. Result ID: 699666be5698665ec4ad1b76.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eae1e209131cea41685.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B","Input Mode":"Transcripts","Evaluation Protocol":"topline"}. This record does not assert independent reproduction.

### Seamless ASR + EuroLLM 9B

Accuracy: 89.2. Result ID: 699666be5698665ec4ad1b77.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e39a.md>)

Recorded evaluation configuration: {"Backbone":"EuroLLM 9B","Input Mode":"Seamless ASR","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### SpeechMapper

Accuracy: 87.9. Result ID: 699666be5698665ec4ad1b7f.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

Recorded evaluation configuration: {"Backbone":"Llama 3.1","Training Stage":"Stage 2 \[ASR/SQA CE\]","Evaluation Protocol":"in-domain"}. This record does not assert independent reproduction.

### BEST-IWSLT25-IF

Accuracy: 87.4. Result ID: 699666be5698665ec4ad1b79.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"in-domain"}. This record does not assert independent reproduction.

### SpeechMapper

Accuracy: 87.4. Result ID: 699666be5698665ec4ad1b7c.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

Recorded evaluation configuration: {"Backbone":"EuroLLM","Training Stage":"Stage 2 \[ASR/SQA CE\]","Evaluation Protocol":"in-domain"}. This record does not assert independent reproduction.

### Seamless ASR + Llama 3.1 8B

Accuracy: 85.6. Result ID: 699666be5698665ec4ad1b78.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e39a.md>)

Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B","Input Mode":"Seamless ASR","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### SpeechMapper

Accuracy: 75.1. Result ID: 699666be5698665ec4ad1b7b.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

Recorded evaluation configuration: {"Backbone":"EuroLLM","Training Stage":"Stage 2 \[ASR CE+MSE\]","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### SpeechMapper

Accuracy: 72.3. Result ID: 699666be5698665ec4ad1b7e.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

Recorded evaluation configuration: {"Backbone":"Llama 3.1","Training Stage":"Stage 2 \[ASR CE+MSE\]","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### SpeechMapper

Accuracy: 62.3. Result ID: 699666be5698665ec4ad1b7d.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

Recorded evaluation configuration: {"Backbone":"Llama 3.1","Training Stage":"Stage 1","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### SpeechMapper

Accuracy: 61.9. Result ID: 699666be5698665ec4ad1b7a.

[Reporting paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697ae9afa2b28e761d87d0a0.md>)

Recorded evaluation configuration: {"Backbone":"EuroLLM","Training Stage":"Stage 1","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

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