# Dysarthric Speech Intelligibility Assessment on SAP

Source: [Dysarthric Speech Intelligibility Assessment on SAP](<https://www.sota2.com/research/sota/dysarthric-speech-intelligibility-assessment-on-sap>)

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

Data updated: 2026-06-18T07:42:21.644Z

Evaluation of models assessing the intelligibility of dysarthric speech using the SAP (Speech Accessibility Project) dataset, measured by MSE, LCC, and SRCC.

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 | Dysarthric Speech Intelligibility Assessment |
| Dataset (including any stated split) | SAP (Speech Accessibility Project) |
| Metric | MSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 25 of 25 |
| 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

- [MSE](<https://www.sota2.com/research/sota/dysarthric-speech-intelligibility-assessment-on-sap.md?metric=MSE>): Lower is better; unit: SCALAR.

- [LCC](<https://www.sota2.com/research/sota/dysarthric-speech-intelligibility-assessment-on-sap.md?metric=LCC>): Higher is better; unit: SCALAR.

- [SRCC](<https://www.sota2.com/research/sota/dysarthric-speech-intelligibility-assessment-on-sap.md?metric=SRCC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | MSE | Result date | Report paper |
| --- | --- | --- | --- |
| Fine-Tuning (FT) | 0.272 | Not recorded | 6a337bbc206542251d7c5184 |
| Fine-Tuning (FT) | 0.303 | Not recorded | 6a337bbc206542251d7c5184 |
| Fine-Tuning (FT) | 0.308 | Not recorded | 6a337bbc206542251d7c5184 |
| IDT (In-Domain Training) | 0.348 | Not recorded | 6a337bbc206542251d7c5184 |
| Fine-Tuning (FT) | 0.351 | Not recorded | 6a337bbc206542251d7c5184 |
| Fine-Tuning (FT) | 0.379 | Not recorded | 6a337bbc206542251d7c5184 |
| Fine-Tuning (FT) | 0.379 | Not recorded | 6a337bbc206542251d7c5184 |
| Fine-Tuning (FT) | 0.387 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.408 | Not recorded | 6a337bbc206542251d7c5184 |
| IDT (In-Domain Training) | 0.421 | Not recorded | 6a337bbc206542251d7c5184 |
| Fine-Tuning (FT) | 0.431 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.433 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.451 | Not recorded | 6a337bbc206542251d7c5184 |
| IDT (In-Domain Training) | 0.461 | Not recorded | 6a337bbc206542251d7c5184 |
| IDT (In-Domain Training) | 0.475 | Not recorded | 6a337bbc206542251d7c5184 |
| Fine-Tuning (FT) | 0.487 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.489 | Not recorded | 6a337bbc206542251d7c5184 |
| Fine-Tuning (FT) | 0.495 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.526 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.528 | Not recorded | 6a337bbc206542251d7c5184 |
| IDT (In-Domain Training) | 0.547 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.56 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.604 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.612 | Not recorded | 6a337bbc206542251d7c5184 |
| Joint Training (JT) | 0.627 | Not recorded | 6a337bbc206542251d7c5184 |

### Fine-Tuning (FT)

MSE: 0.272. Result ID: 6a33a10dfbc373592c309b75.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Base","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

### Fine-Tuning (FT)

MSE: 0.303. Result ID: 6a33a10dfbc373592c309b7f.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Base","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### Fine-Tuning (FT)

MSE: 0.308. Result ID: 6a33a10dfbc373592c309b77.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large+","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

### IDT (In-Domain Training)

MSE: 0.348. Result ID: 6a33a10dfbc373592c309b70.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Base","QualiSpeech Auxiliary Supervision":"–"}. This record does not assert independent reproduction.

### Fine-Tuning (FT)

MSE: 0.351. Result ID: 6a33a10dfbc373592c309b76.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large\*","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

### Fine-Tuning (FT)

MSE: 0.379. Result ID: 6a33a10dfbc373592c309b82.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Base","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### Fine-Tuning (FT)

MSE: 0.379. Result ID: 6a33a10dfbc373592c309b83.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Large","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### Fine-Tuning (FT)

MSE: 0.387. Result ID: 6a33a10dfbc373592c309b80.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large\*","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.408. Result ID: 6a33a10dfbc373592c309b7a.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Base","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

### IDT (In-Domain Training)

MSE: 0.421. Result ID: 6a33a10dfbc373592c309b71.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large\*","QualiSpeech Auxiliary Supervision":"–"}. This record does not assert independent reproduction.

### Fine-Tuning (FT)

MSE: 0.431. Result ID: 6a33a10dfbc373592c309b79.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Large","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.433. Result ID: 6a33a10dfbc373592c309b84.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Base","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.451. Result ID: 6a33a10dfbc373592c309b88.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Large","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### IDT (In-Domain Training)

MSE: 0.461. Result ID: 6a33a10dfbc373592c309b73.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Base","QualiSpeech Auxiliary Supervision":"–"}. This record does not assert independent reproduction.

### IDT (In-Domain Training)

MSE: 0.475. Result ID: 6a33a10dfbc373592c309b74.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Large","QualiSpeech Auxiliary Supervision":"–"}. This record does not assert independent reproduction.

### Fine-Tuning (FT)

MSE: 0.487. Result ID: 6a33a10dfbc373592c309b78.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Base","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.489. Result ID: 6a33a10dfbc373592c309b87.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Base","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### Fine-Tuning (FT)

MSE: 0.495. Result ID: 6a33a10dfbc373592c309b81.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large+","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.526. Result ID: 6a33a10dfbc373592c309b7e.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Large","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.528. Result ID: 6a33a10dfbc373592c309b86.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large+","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### IDT (In-Domain Training)

MSE: 0.547. Result ID: 6a33a10dfbc373592c309b72.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large+","QualiSpeech Auxiliary Supervision":"–"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.56. Result ID: 6a33a10dfbc373592c309b7b.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large\*","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.604. Result ID: 6a33a10dfbc373592c309b85.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large\*","QualiSpeech Auxiliary Supervision":"Naturalness"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.612. Result ID: 6a33a10dfbc373592c309b7d.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"HuBERT Base","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

### Joint Training (JT)

MSE: 0.627. Result ID: 6a33a10dfbc373592c309b7c.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bbc206542251d7c5184.md>)

Recorded evaluation configuration: {"SSL Encoder":"wav2vec 2.0 Large+","QualiSpeech Auxiliary Supervision":"Overall"}. This record does not assert independent reproduction.

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