Speech Synthesis On North American English
Metrics
Mean Opinion Score
Results
Performance results of various models on this benchmark
Model Name | Mean Opinion Score | Paper Title | Repository |
|---|---|---|---|
| LSTM-RNN parametric | 3.67 | WaveNet: A Generative Model for Raw Audio | |
| means | 0 | Merging $K$-means with hierarchical clustering for identifying general-shaped groups | - |
| WaveNet (L+F) | 4.21 | WaveNet: A Generative Model for Raw Audio | |
| Tacotron 2 | 4.526 | Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions | |
| Tacotron | 4.001 | Tacotron: Towards End-to-End Speech Synthesis | |
| WaveNet (Linguistic) | 4.341 | Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions | |
| HMM-driven concatenative | 3.86 | WaveNet: A Generative Model for Raw Audio |
0 of 7 row(s) selected.