# Spoken Question Answering on LibriSQA (Accuracy and ALAS Metrics)

Source: [Spoken Question Answering on LibriSQA (Accuracy and ALAS Metrics)](<https://www.sota2.com/research/sota/spoken-question-answering-on-librisqa-accuracy-and-alas-metrics>)

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

Data updated: 2026-06-17T07:33:00.372Z

Evaluation of Spoken Question Answering performance on the LibriSQA dataset, focusing on verification accuracy (n\_vv, a-acc, t-acc) and ALAS similarity 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) | LibriSQA |
| Metric | N Verified Verifications Count |
| Unit | SCALAR |
| 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

- [N Verified Verifications Count](<https://www.sota2.com/research/sota/spoken-question-answering-on-librisqa-accuracy-and-alas-metrics.md?metric=N%20Verified%20Verifications%20Count>): Higher is better; unit: SCALAR.

- [Answer Accuracy (a-acc)](<https://www.sota2.com/research/sota/spoken-question-answering-on-librisqa-accuracy-and-alas-metrics.md?metric=Answer%20Accuracy%20(a-acc)>): Higher is better; unit: PERCENT.

- [Transcript Accuracy (t-acc)](<https://www.sota2.com/research/sota/spoken-question-answering-on-librisqa-accuracy-and-alas-metrics.md?metric=Transcript%20Accuracy%20(t-acc)>): Higher is better; unit: PERCENT.

- [L\* Score](<https://www.sota2.com/research/sota/spoken-question-answering-on-librisqa-accuracy-and-alas-metrics.md?metric=L*%20Score>): Higher is better; unit: SCALAR.

- [ALAS Soft Similarity (Verified Verifications)](<https://www.sota2.com/research/sota/spoken-question-answering-on-librisqa-accuracy-and-alas-metrics.md?metric=ALAS%20Soft%20Similarity%20(Verified%20Verifications)>): Higher is better; unit: SCALAR.

- [ALAS Soft Similarity (All)](<https://www.sota2.com/research/sota/spoken-question-answering-on-librisqa-accuracy-and-alas-metrics.md?metric=ALAS%20Soft%20Similarity%20(All)>): Higher is better; unit: SCALAR.

- [ALAS Hard Similarity (Verified Verifications)](<https://www.sota2.com/research/sota/spoken-question-answering-on-librisqa-accuracy-and-alas-metrics.md?metric=ALAS%20Hard%20Similarity%20(Verified%20Verifications)>): Higher is better; unit: PERCENT.

- [ALAS Hard Similarity (All)](<https://www.sota2.com/research/sota/spoken-question-answering-on-librisqa-accuracy-and-alas-metrics.md?metric=ALAS%20Hard%20Similarity%20(All)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | N Verified Verifications Count | Result date | Report paper |
| --- | --- | --- | --- |
| AF3 | 1750 | Not recorded | 68fa79d91e209131cea7fbe6 |
| SALMONN | 1382 | Not recorded | 68fa79d91e209131cea7fbe6 |
| Qwen2-Audio | 1174 | Not recorded | 68fa79d91e209131cea7fbe6 |
| Qwen-Omni | 1167 | Not recorded | 68fa79d91e209131cea7fbe6 |

### AF3

N Verified Verifications Count: 1750. Result ID: 6a324d93fbc373592c2f8094.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d91e209131cea7fbe6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4d1e209131cea82504.md>)

Recorded evaluation configuration: {"Backbone":"AF-Whisper","LLM":"Qwen2.5-7B"}. This record does not assert independent reproduction.

### SALMONN

N Verified Verifications Count: 1382. Result ID: 6a324d93fbc373592c2f8097.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d91e209131cea7fbe6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d71e209131cea58d8a.md>)

Recorded evaluation configuration: {"Backbone":"Whisper-v2 + BEATs","LLM":"Vicuna-13B","Adapter":"Q-Former"}. This record does not assert independent reproduction.

### Qwen2-Audio

N Verified Verifications Count: 1174. Result ID: 6a324d93fbc373592c2f8095.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d91e209131cea7fbe6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6017e.md>)

Recorded evaluation configuration: {"Backbone":"Whisper-large-v3","LLM":"Qwen-7B","Adapter":"None"}. This record does not assert independent reproduction.

### Qwen-Omni

N Verified Verifications Count: 1167. Result ID: 6a324d93fbc373592c2f8096.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d91e209131cea7fbe6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.md>)

Recorded evaluation configuration: {"Backbone":"Streaming-modified Whisper","LLM":"Qwen2.5 Thinker","Adapter":"Learned projection"}. This record does not assert independent reproduction.

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