| MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis | 2 | 0.37 | 2019 |
| ObamaNet: Photo-realistic lip-sync from text. | 3 | 0.39 | 2018 |
| SampleRNN: An Unconditional End-to-End Neural Audio Generation Model. | 0 | 0.34 | 2017 |
| Char2Wav - End-to-End Speech Synthesis. | 1 | 0.35 | 2017 |
| Char2Wav: End-to-End Speech Synthesis. | 0 | 0.34 | 2017 |
| SampleRNN: An Unconditional End-to-End Neural Audio Generation Model. | 3 | 0.38 | 2016 |
