Samples predicted on LJ Speech Dataset

• Samples on the left are targets.
• Samples on the right are generated by a vocoder trained for 680K steps on the dataset.

Samples predicted using mel-spectrum of the samples generated from Tacotron

• Samples on the left are collected from Keithito's demo page for Tacotron.
• Samples on the right are generated by the vocoder using mel-spectrum of the collected sample.

Scientists at the CERN laboratory say they have discovered a new particle.

There’s a way to measure the acute emotional intelligence that has never gone out of style.

President Trump met with other leaders at the Group of 20 conference.

The Senate’s bill to repeal and replace the Affordable Care Act is now imperiled.

Generative adversarial network or variational auto-encoder.

The buses aren't the problem, they actually provide a solution.