Text To Speech Synthesis On Ljspeech
評価指標
Audio Quality MOS
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Audio Quality MOS |
|---|---|
| fastspeech-fast-robust-and-controllable-text | 3.84 |
| fastdiff-a-fast-conditional-diffusion-model | 4.03 |
| naturalspeech-end-to-end-text-to-speech | 4.34 |
| grad-tts-a-diffusion-probabilistic-model-for | 4.37 |
| flowtron-an-autoregressive-flow-based | - |
| neural-speech-synthesis-with-transformer | 3.88 |
| naturalspeech-end-to-end-text-to-speech | 4.43 |
| matcha-tts-a-fast-tts-architecture-with | - |
| flowtron-an-autoregressive-flow-based | - |
| fastspeech-2-fast-and-high-quality-end-to-end | 4.32 |
| モデル 11 | 1.25 |
| fastdiff-a-fast-conditional-diffusion-model | 4.28 |
| overflow-putting-flows-on-top-of-neural | 3.37 |
| naturalspeech-end-to-end-text-to-speech | 4.56 |
| fastspeech-fast-robust-and-controllable-text | 2.4 |
| glow-tts-a-generative-flow-for-text-to-speech | 4.34 |