# Speech Reconstruction on Seed-TTS English

Source: [Speech Reconstruction on Seed-TTS English](<https://www.sota2.com/research/sota/speech-reconstruction-on-seed-tts-english>)

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

Data updated: 2026-05-28T08:07:07.102Z

Evaluation of speech reconstruction quality on the Seed-TTS English dataset using PESQ and STOI metrics.

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) | Seed-TTS English |
| Metric | PESQ |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [PESQ](<https://www.sota2.com/research/sota/speech-reconstruction-on-seed-tts-english.md?metric=PESQ>): Higher is better; unit: SCALAR.

- [STOI](<https://www.sota2.com/research/sota/speech-reconstruction-on-seed-tts-english.md?metric=STOI>): Higher is better; unit: SCALAR.

## Recorded results

| Method | PESQ | Result date | Report paper |
| --- | --- | --- | --- |
| DashengTokenizer | 4.125 | Not recorded | 69a5195d2d603e6de3e3c73d |
| DashengTokenizer | 4.122 | Not recorded | 6a17cc2bdbd7150506f813ec |
| MingTok-Audio | 4.04 | Not recorded | 69a5195d2d603e6de3e3c73d |
| Ming-UniAudio | 3.976 | Not recorded | 6a17cc2bdbd7150506f813ec |
| UniFlow-Audio | 3.858 | Not recorded | 69a5195d2d603e6de3e3c73d |
| UniFlow-Audio | 3.833 | Not recorded | 6a17cc2bdbd7150506f813ec |
| DAC | 3.786 | Not recorded | 6a17cc2bdbd7150506f813ec |
| DAC | 3.763 | Not recorded | 69a5195d2d603e6de3e3c73d |
| EzAudio | 3.668 | Not recorded | 69a5195d2d603e6de3e3c73d |
| EzAudio | 3.649 | Not recorded | 6a17cc2bdbd7150506f813ec |
| LoSATok | 3.051 | Not recorded | 6a17cc2bdbd7150506f813ec |
| XCodec 2.0 | 2.37 | Not recorded | 69a5195d2d603e6de3e3c73d |
| XY-Tokenizer | 2.173 | Not recorded | 6a17cc2bdbd7150506f813ec |
| XY-Tokenizer | 2.14 | Not recorded | 69a5195d2d603e6de3e3c73d |
| Mimi | 2.01 | Not recorded | 69a5195d2d603e6de3e3c73d |
| SNAC | 1.817 | Not recorded | 6a17cc2bdbd7150506f813ec |
| SNAC | 1.804 | Not recorded | 69a5195d2d603e6de3e3c73d |

### DashengTokenizer

PESQ: 4.125. Result ID: 69c68d8a47f34ce924b0cbe8.

[Reporting paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

Recorded evaluation configuration: {"Framerate":"25"}. This record does not assert independent reproduction.

### DashengTokenizer

PESQ: 4.122. Result ID: 6a17f796fbc373592c11900e.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

Recorded evaluation configuration: {"Frame Rate":"25","RTF":"0.0034"}. This record does not assert independent reproduction.

### MingTok-Audio

PESQ: 4.04. Result ID: 69c68d8a47f34ce924b0cbe7.

[Reporting paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6912c3042828b7cc6937dba6.md>)

Recorded evaluation configuration: {"Framerate":"50"}. This record does not assert independent reproduction.

### Ming-UniAudio

PESQ: 3.976. Result ID: 6a17f796fbc373592c11900d.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6912c3042828b7cc6937dba6.md>)

Recorded evaluation configuration: {"Frame Rate":"50","RTF":"0.0050"}. This record does not assert independent reproduction.

### UniFlow-Audio

PESQ: 3.858. Result ID: 69c68d8a47f34ce924b0cbe6.

[Reporting paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb71e209131cea8a1bf.md>)

Recorded evaluation configuration: {"Framerate":"50"}. This record does not assert independent reproduction.

### UniFlow-Audio

PESQ: 3.833. Result ID: 6a17f796fbc373592c11900c.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb71e209131cea8a1bf.md>)

Recorded evaluation configuration: {"Frame Rate":"50","RTF":"0.0167"}. This record does not assert independent reproduction.

### DAC

PESQ: 3.786. Result ID: 6a17f796fbc373592c119008.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ecde.md>)

[Implementation](<https://github.com/descriptinc/descript-audio-codec>)

Recorded evaluation configuration: {"Frame Rate":"50","RTF":"0.0043"}. This record does not assert independent reproduction.

### DAC

PESQ: 3.763. Result ID: 69c68d8a47f34ce924b0cbe4.

[Reporting paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ecde.md>)

[Implementation](<https://github.com/descriptinc/descript-audio-codec>)

Recorded evaluation configuration: {"Framerate":"50"}. This record does not assert independent reproduction.

### EzAudio

PESQ: 3.668. Result ID: 69c68d8a47f34ce924b0cbe5.

[Reporting paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de21.md>)

Recorded evaluation configuration: {"Framerate":"50"}. This record does not assert independent reproduction.

### EzAudio

PESQ: 3.649. Result ID: 6a17f796fbc373592c11900b.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de21.md>)

Recorded evaluation configuration: {"Frame Rate":"50","RTF":"0.0054"}. This record does not assert independent reproduction.

### LoSATok

PESQ: 3.051. Result ID: 6a17f796fbc373592c11900f.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813ec.md>)

Recorded evaluation configuration: {"Frame Rate":"25","RTF":"0.0033"}. This record does not assert independent reproduction.

### XCodec 2.0

PESQ: 2.37. Result ID: 69c68d8a47f34ce924b0cbe2.

[Reporting paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77211e209131cea7143b.md>)

Recorded evaluation configuration: {"Framerate":"50"}. This record does not assert independent reproduction.

### XY-Tokenizer

PESQ: 2.173. Result ID: 6a17f796fbc373592c11900a.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79e71e209131cea7fdf8.md>)

Recorded evaluation configuration: {"Frame Rate":"12.5","RTF":"0.0099"}. This record does not assert independent reproduction.

### XY-Tokenizer

PESQ: 2.14. Result ID: 69c68d8a47f34ce924b0cbe3.

[Reporting paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79e71e209131cea7fdf8.md>)

Recorded evaluation configuration: {"Framerate":"12.5"}. This record does not assert independent reproduction.

### Mimi

PESQ: 2.01. Result ID: 69c68d8a47f34ce924b0cbe1.

[Reporting paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75001e209131cea652b7.md>)

Recorded evaluation configuration: {"Framerate":"12.5"}. This record does not assert independent reproduction.

### SNAC

PESQ: 1.817. Result ID: 6a17f796fbc373592c119009.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b55.md>)

Recorded evaluation configuration: {"RTF":"0.0019"}. This record does not assert independent reproduction.

### SNAC

PESQ: 1.804. Result ID: 69c68d8a47f34ce924b0cbe0.

[Reporting paper](<https://www.sota2.com/research/paper/69a5195d2d603e6de3e3c73d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b55.md>)

Recorded evaluation configuration: {"Framerate":"-"}. This record does not assert independent reproduction.

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