An open source implementation of DeepVoice 3: 2000-Speaker Neural Text-to-Speech

An open source implementation of DeepVoice 3: 2000-Speaker Neural Text-to-Speech

  • April 27, 2018
Table of Contents

An open source implementation of DeepVoice 3: 2000-Speaker Neural Text-to-Speech

This page provides audio samples for the open source implementation of DeepVoice3. Samples from single speaker and multi-speaker models follow.

Source: github.io

Tags :
Share :
comments powered by Disqus

Related Posts

United Kingdom Plans $1.3 Billion Artificial Intelligence Push

United Kingdom Plans $1.3 Billion Artificial Intelligence Push

The U.K. government said Thursday that part of its multi-year AI investment–about £300 million, or more than $400 million–would come from U.K.-based corporations and investment firms and those located outside the country.

Read More
New AI Imaging Technique Reconstructs Photos with Realistic Results

New AI Imaging Technique Reconstructs Photos with Realistic Results

To prepare to train their neural network, the team first generated 55,116 masks of random streaks and holes of arbitrary shapes and sizes for training. They also generated nearly 25,000 for testing. These were further categorized into six categories based on sizes relative to the input image, in order to improve reconstruction accuracy.

Read More