Faster high-quality speech synthesis.

  • 0 Replies
  • 358 Views
*

infurl

  • Trusty Member
  • ********
  • Replicant
  • *
  • 612
  • Humans will disappoint you.
    • Home Page
Faster high-quality speech synthesis.
« on: March 01, 2018, 10:41:47 pm »


A new kind of adversarial network allows high-quality speech synthesis to take advantage of parallel hardware obtaining a thousand-fold increase in performance. This technology is already being used in Google Assistant.

https://arxiv.org/abs/1711.10433

The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is poorly suited to today's massively parallel computers, and therefore hard to deploy in a real-time production setting. This paper introduces Probability Density Distillation, a new method for training a parallel feed-forward network from a trained WaveNet with no significant difference in quality. The resulting system is capable of generating high-fidelity speech samples at more than 20 times faster than real-time, and is deployed online by Google Assistant, including serving multiple English and Japanese voices.

 


Friday Funny
by LOCKSUIT (General Chat)
August 17, 2018, 04:10:47 pm
Ten Commandments of Logic
by RoyMac (General Chat)
August 17, 2018, 12:01:02 pm
XKCD Comic : Equations
by Tyler (XKCD Comic)
August 17, 2018, 12:00:14 pm
XKCD Comic : Repair or Replace
by Tyler (XKCD Comic)
August 16, 2018, 12:01:05 pm
Simple AI Website to let you know what is AI
by LOCKSUIT (General AI Discussion)
August 16, 2018, 01:23:19 am
The last invention.
by korrelan (General Project Discussion)
August 15, 2018, 11:06:53 pm
Hi there
by Art (New Users Please Post Here)
August 15, 2018, 08:06:54 pm
Funny Mitsuku reactions
by ranch vermin (Bot Conversations)
August 15, 2018, 12:53:39 pm

Users Online

38 Guests, 0 Users

Most Online Today: 51. Most Online Ever: 208 (August 27, 2008, 09:36:30 am)

Articles