# Speech Synthesis on Internal US English female (evaluation)

Source: [Speech Synthesis on Internal US English female (evaluation)](<https://www.sota2.com/research/sota/speech-synthesis-on-internal-us-english-female-evaluation>)

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

Data updated: 2026-02-26T05:38:38.712Z

Evaluation of Speech Synthesis quality on the Internal US English female evaluation split, typically measured using Mean Opinion Score (MOS) and Comparative MOS (CMOS).

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 Synthesis |
| Dataset (including any stated split) | Internal US English female (evaluation) |
| Metric | CMOS |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [CMOS](<https://www.sota2.com/research/sota/speech-synthesis-on-internal-us-english-female-evaluation.md?metric=CMOS>): Higher is better; unit: SCALAR.

- [MOS](<https://www.sota2.com/research/sota/speech-synthesis-on-internal-us-english-female-evaluation.md?metric=MOS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | CMOS | Result date | Report paper |
| --- | --- | --- | --- |
| Our Model | 0.048 | Not recorded | 68fa654d1e209131cea0972b |
| Tacotron2 | 0 | Not recorded | 68fa654d1e209131cea0972b |

### Our Model

CMOS: 0.048. Result ID: 698ca5723ce6cd2163e110a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa654d1e209131cea0972b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa654d1e209131cea0972b.md>)

[Implementation](<https://neuraltts.github.io/transformertts/>)

Recorded evaluation configuration: {"Input":"phonemes","Vocoder":"WaveNet"}. This record does not assert independent reproduction.

### Tacotron2

CMOS: 0. Result ID: 698ca5723ce6cd2163e110a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa654d1e209131cea0972b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64091e209131cea022df.md>)

[Implementation](<https://google.github.io/tacotron/publications/tacotron2>)

Recorded evaluation configuration: {"Input":"phonemes","Vocoder":"WaveNet"}. This record does not assert independent reproduction.

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