# Speech Reconstruction on MLS non-English OOD (700 utterances (7 languages))

Source: [Speech Reconstruction on MLS non-English OOD (700 utterances (7 languages))](<https://www.sota2.com/research/sota/speech-reconstruction-on-mls-non-english-ood-700-utterances-7-languages>)

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

Data updated: 2026-06-30T08:27:03.319Z

Evaluation of speech reconstruction performance on the Out-of-Distribution (OOD) subset of the MLS non-English dataset (700 utterances across 7 languages), measured using UTMOS, PESQ, STOI, and Speaker Similarity (Spk-Sim).

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 | Speech Reconstruction |
| Dataset (including any stated split) | MLS non-English OOD (700 utterances (7 languages)) |
| Metric | UTMOS |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [UTMOS](<https://www.sota2.com/research/sota/speech-reconstruction-on-mls-non-english-ood-700-utterances-7-languages.md?metric=UTMOS>): Higher is better; unit: SCALAR.

- [PESQ](<https://www.sota2.com/research/sota/speech-reconstruction-on-mls-non-english-ood-700-utterances-7-languages.md?metric=PESQ>): Higher is better; unit: SCALAR.

- [STOI](<https://www.sota2.com/research/sota/speech-reconstruction-on-mls-non-english-ood-700-utterances-7-languages.md?metric=STOI>): Higher is better; unit: PERCENT.

- [Spk-Sim](<https://www.sota2.com/research/sota/speech-reconstruction-on-mls-non-english-ood-700-utterances-7-languages.md?metric=Spk-Sim>): Higher is better; unit: PERCENT.

## Recorded results

| Method | UTMOS | Result date | Report paper |
| --- | --- | --- | --- |
| DTM-Codec | 3.16 | Not recorded | 6a434d7dba73165dbb743978 |
| DTM-Codec | 3.15 | Not recorded | 6a434d7dba73165dbb743978 |
| DTM-Codec | 3.09 | Not recorded | 6a434d7dba73165dbb743978 |
| DTM-Codec | 3.07 | Not recorded | 6a434d7dba73165dbb743978 |
| DTM-Codec | 3.05 | Not recorded | 6a434d7dba73165dbb743978 |
| DTM-Codec | 3.04 | Not recorded | 6a434d7dba73165dbb743978 |
| DTM-Codec | 3 | Not recorded | 6a434d7dba73165dbb743978 |
| FlexiCodec | 2.99 | Not recorded | 6a434d7dba73165dbb743978 |
| DTM-Codec | 2.97 | Not recorded | 6a434d7dba73165dbb743978 |
| VARSTok | 2.6 | Not recorded | 6a434d7dba73165dbb743978 |

### DTM-Codec

UTMOS: 3.16. Result ID: 6a437dbcfbc373592c948c99.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

Recorded evaluation configuration: {"bps":"800","Frame Rate (Hz)":"50Hz","Rate Control Strategy (FFR/VFR)":"VFR"}. This record does not assert independent reproduction.

### DTM-Codec

UTMOS: 3.15. Result ID: 6a437dbcfbc373592c948c97.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

Recorded evaluation configuration: {"bps":"640","Frame Rate (Hz)":"40Hz","Rate Control Strategy (FFR/VFR)":"VFR"}. This record does not assert independent reproduction.

### DTM-Codec

UTMOS: 3.09. Result ID: 6a437dbcfbc373592c948c95.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

Recorded evaluation configuration: {"bps":"400","Frame Rate (Hz)":"25Hz","Rate Control Strategy (FFR/VFR)":"VFR"}. This record does not assert independent reproduction.

### DTM-Codec

UTMOS: 3.07. Result ID: 6a437dbcfbc373592c948c9a.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

Recorded evaluation configuration: {"bps":"1280","Frame Rate (Hz)":"80Hz","Rate Control Strategy (FFR/VFR)":"FFR"}. This record does not assert independent reproduction.

### DTM-Codec

UTMOS: 3.05. Result ID: 6a437dbcfbc373592c948c96.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

Recorded evaluation configuration: {"bps":"640","Frame Rate (Hz)":"40Hz","Rate Control Strategy (FFR/VFR)":"FFR"}. This record does not assert independent reproduction.

### DTM-Codec

UTMOS: 3.04. Result ID: 6a437dbcfbc373592c948c98.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

Recorded evaluation configuration: {"bps":"800","Frame Rate (Hz)":"50Hz","Rate Control Strategy (FFR/VFR)":"FFR"}. This record does not assert independent reproduction.

### DTM-Codec

UTMOS: 3. Result ID: 6a437dbcfbc373592c948c9b.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

Recorded evaluation configuration: {"bps":"1280","Frame Rate (Hz)":"80Hz","Rate Control Strategy (FFR/VFR)":"VFR"}. This record does not assert independent reproduction.

### FlexiCodec

UTMOS: 2.99. Result ID: 6a437dbcfbc373592c948c9c.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd21e209131cea8ab31.md>)

Recorded evaluation configuration: {"bps":"905"}. This record does not assert independent reproduction.

### DTM-Codec

UTMOS: 2.97. Result ID: 6a437dbcfbc373592c948c94.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

Recorded evaluation configuration: {"bps":"400","Frame Rate (Hz)":"25Hz","Rate Control Strategy (FFR/VFR)":"FFR"}. This record does not assert independent reproduction.

### VARSTok

UTMOS: 2.6. Result ID: 6a437dbcfbc373592c948c9d.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d7dba73165dbb743978.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b1d1e209131cea869d0.md>)

Recorded evaluation configuration: {"bps":"402"}. This record does not assert independent reproduction.

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