Presented By
O’Reilly + Cloudera
Make Data Work
29 April–2 May 2019
London, UK
Please log in

Deep learning for speech synthesis: The good news, the bad news, and the fake news

11:1511:55 Thursday, 2 May 2019
Data Science, Machine Learning & AI
Location: Capital Suite 17
Average rating: *****
(5.00, 4 ratings)

Who is this presentation for?

  • Data scientists, engineers, and business people



Prerequisite knowledge

  • Familiarity with machine learning terminology

What you'll learn

  • Understand the risks posed by the application of deep learning to political disinformation
  • Learn how to use deep learning to counter these risks


Mention speech synthesis and most people will think of robotic voices characteristic of historic systems such as that used by the late Stephen Hawking. However, modern developments in deep learning allow us to build end-to-end speech synthesis systems that not only require no linguistic domain expertise but can generate speech indistinguishable to the human ear from a real speaker.

While these technologies have myriad benevolent applications, they also usher in a new era of fake news. What if a malicious actor could generate an audio recording of a political adversary saying anything they want and leak this to the press for political gain?

Scott Stevenson discusses the technical developments in deep learning that make this possible and the potential impacts on public discourse of modern political disinformation. He then explores how the public can be inoculated against such disinformation campaigns and how to use additional modern machine learning techniques such as adversarial networks to build countermeasures against such disinformation campaigns.

Scott Stevenson



Comments on this page are now closed.


Picture of Scott Stevenson
Scott Stevenson | .
3/05/2019 14:07 BST

Lorenzo: I’ve uploaded them to the O’Reilly website, so I think they should appear on this page at some point.

3/05/2019 11:58 BST

Are the talk’s slides available somewhere?