# Text-to-Speech on LibriTTS zero-shot

Source: [Text-to-Speech on LibriTTS zero-shot](<https://www.sota2.com/research/sota/text-to-speech-on-libritts-zero-shot>)

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

Data updated: 2026-03-05T09:33:19.699Z

Evaluation of Text-to-Speech synthesis quality on the LibriTTS dataset under zero-shot conditions, typically measured using UTMOS and MOS.

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 | Text-to-Speech |
| Dataset (including any stated split) | LibriTTS zero-shot |
| Metric | UTMOS |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 20 of 20 |
| 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/text-to-speech-on-libritts-zero-shot.md?metric=UTMOS>): Higher is better; unit: SCALAR.

- [MOS](<https://www.sota2.com/research/sota/text-to-speech-on-libritts-zero-shot.md?metric=MOS>): Higher is better; unit: SCALAR.

- [CER](<https://www.sota2.com/research/sota/text-to-speech-on-libritts-zero-shot.md?metric=CER>): Lower is better; unit: SCALAR.

- [WER](<https://www.sota2.com/research/sota/text-to-speech-on-libritts-zero-shot.md?metric=WER>): Lower is better; unit: SCALAR.

- [WavLM Score](<https://www.sota2.com/research/sota/text-to-speech-on-libritts-zero-shot.md?metric=WavLM%20Score>): Higher is better; unit: SCALAR.

- [Resemblyzer Score](<https://www.sota2.com/research/sota/text-to-speech-on-libritts-zero-shot.md?metric=Resemblyzer%20Score>): Higher is better; unit: SCALAR.

- [MOS (Naturalness)](<https://www.sota2.com/research/sota/text-to-speech-on-libritts-zero-shot.md?metric=MOS%20(Naturalness)>): Higher is better; unit: SCALAR.

- [ABX Preference (%)](<https://www.sota2.com/research/sota/text-to-speech-on-libritts-zero-shot.md?metric=ABX%20Preference%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | UTMOS | Result date | Report paper |
| --- | --- | --- | --- |
| PeriodWave-Turbo-L | 4.3026 | Not recorded | 68fa74861e209131cea62328 |
| PeriodWave-Turbo-B | 4.2932 | Not recorded | 68fa74861e209131cea62328 |
| PeriodWave-Turbo-S | 4.2716 | Not recorded | 68fa74861e209131cea62328 |
| PeriodWave-L + FreeU | 4.2643 | Not recorded | 68fa74861e209131cea62328 |
| PeriodWave | 4.2621 | Not recorded | 68fa74841e209131cea6222e |
| PeriodWave-B + FreeU | 4.2621 | Not recorded | 68fa74861e209131cea62328 |
| PeriodWave-L | 4.2464 | Not recorded | 68fa74861e209131cea62328 |
| PeriodWave | 4.2209 | Not recorded | 68fa74841e209131cea6222e |
| PeriodWave-B | 4.2209 | Not recorded | 68fa74861e209131cea62328 |
| BigVGAN | 4.0424 | Not recorded | 68fa74841e209131cea6222e |
| BigVGAN | 4.0424 | Not recorded | 68fa74861e209131cea62328 |
| BigVGAN-v2 | 3.9894 | Not recorded | 68fa74861e209131cea62328 |
| BigVSAN | 3.9732 | Not recorded | 68fa74841e209131cea6222e |
| BigVSAN | 3.9732 | Not recorded | 68fa74861e209131cea62328 |

### PeriodWave-Turbo-L

UTMOS: 4.3026. Result ID: 69935fe13a6c314849157ba1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Implementation](<https://github.com/sh-lee-prml/PeriodWave>)

Recorded evaluation configuration: {"Sampling Steps":"4","ODE Solver":"Euler"}. This record does not assert independent reproduction.

### PeriodWave-Turbo-B

UTMOS: 4.2932. Result ID: 69935fe13a6c314849157ba0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Implementation](<https://github.com/sh-lee-prml/PeriodWave>)

Recorded evaluation configuration: {"Sampling Steps":"4","ODE Solver":"Euler"}. This record does not assert independent reproduction.

### PeriodWave-Turbo-S

UTMOS: 4.2716. Result ID: 69935fe13a6c314849157b9f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Implementation](<https://github.com/sh-lee-prml/PeriodWave>)

Recorded evaluation configuration: {"Sampling Steps":"4","ODE Solver":"Euler"}. This record does not assert independent reproduction.

### PeriodWave-L + FreeU

UTMOS: 4.2643. Result ID: 69935fe13a6c314849157b9e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Implementation](<https://github.com/sh-lee-prml/PeriodWave>)

Recorded evaluation configuration: {"Sampling Steps":"16","ODE Solver":"Midpoint","FreeU":"true"}. This record does not assert independent reproduction.

### PeriodWave

UTMOS: 4.2621. Result ID: 69934a2b3a6c31484914f3c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74841e209131cea6222e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74841e209131cea6222e.md>)

[Implementation](<https://github.com/sh-lee-prml/PeriodWave>)

Recorded evaluation configuration: {"sampling steps":16,"zero-shot":true,"FreeU":true}. This record does not assert independent reproduction.

### PeriodWave-B + FreeU

UTMOS: 4.2621. Result ID: 69935fe13a6c314849157b9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Implementation](<https://github.com/sh-lee-prml/PeriodWave>)

Recorded evaluation configuration: {"Sampling Steps":"16","ODE Solver":"Midpoint","FreeU":"true"}. This record does not assert independent reproduction.

### PeriodWave-L

UTMOS: 4.2464. Result ID: 69935fe13a6c314849157b9c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Implementation](<https://github.com/sh-lee-prml/PeriodWave>)

Recorded evaluation configuration: {"Sampling Steps":"16","ODE Solver":"Midpoint"}. This record does not assert independent reproduction.

### PeriodWave

UTMOS: 4.2209. Result ID: 69934a2b3a6c31484914f3c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74841e209131cea6222e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74841e209131cea6222e.md>)

[Implementation](<https://github.com/sh-lee-prml/PeriodWave>)

Recorded evaluation configuration: {"sampling steps":16,"zero-shot":true}. This record does not assert independent reproduction.

### PeriodWave-B

UTMOS: 4.2209. Result ID: 69935fe13a6c314849157b9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74841e209131cea6222e.md>)

[Implementation](<https://github.com/sh-lee-prml/PeriodWave>)

Recorded evaluation configuration: {"Sampling Steps":"16","ODE Solver":"Midpoint"}. This record does not assert independent reproduction.

### BigVGAN

UTMOS: 4.0424. Result ID: 69934a2b3a6c31484914f3c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74841e209131cea6222e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a21e209131cea57b3c.md>)

[Implementation](<https://github.com/sony/bigvsan>)

Recorded evaluation configuration: {"zero-shot":true,"training\_steps":"5M"}. This record does not assert independent reproduction.

### BigVGAN

UTMOS: 4.0424. Result ID: 69935fe13a6c314849157b99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8c1e209131cea407ef.md>)

[Implementation](<https://github.com/NVIDIA/BigVGAN>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BigVGAN-v2

UTMOS: 3.9894. Result ID: 69935fe13a6c314849157b9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a21e209131cea57b3c.md>)

[Implementation](<https://github.com/sony/bigvsan>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BigVSAN

UTMOS: 3.9732. Result ID: 69934a2b3a6c31484914f3c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74841e209131cea6222e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a21e209131cea57b3c.md>)

[Implementation](<https://github.com/sony/bigvsan>)

Recorded evaluation configuration: {"zero-shot":true,"training\_steps":"10M"}. This record does not assert independent reproduction.

### BigVSAN

UTMOS: 3.9732. Result ID: 69935fe13a6c314849157b98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74861e209131cea62328.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a21e209131cea57b3c.md>)

[Implementation](<https://github.com/sony/bigvsan>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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