'JFK Unsilenced' allows audiences to hear the speech delivered in the president's own voice

"Created by Irish agency Rothco for the Times of London, 'JFK Unsilenced' used artificial intelligence to stitch Kennedy's voice into the speech he had been set to deliver on the day he was killed in Dallas," reports Alexandra Jardine. "Rothco and the Times worked with CereProc, a British audio tech company, to analyze recordings from over 800 Kennedy speeches and build a database from them. The 22-minute video appeared on the Times website." To read the full article, click here.

In order to put the President's voice to the 22-minutes of words he had prepared to deliver, with the help of tech company Cereproc, Rothco built the monologue entirely out of data, using AI. The speech was meticulously pieced together by analyzing analog recordings. The audio was then finessed at postproduction company Screen Scene.

JFK-unsilenced03

Read more: Unsilencing JFK to Make the Greatest Speech Never Made

Read more: JFK Finally Recites His Last Speech – 55 Years After his Death – Thanks to AI

The process involved isolating 41 phonemes for American English (the sounds that can be used to make any word) and stitching the small units of speech back together; reviewing 831 analog recordings of JFK speeches and interviews; analyzing speeches for noise, crosstalk and underlying sample rate; applying audio processing to remove noise; and applying spectrum analysis tools to improve acoustic environment and match them across samples.

JFK-unsilenced02

The sounds were then carefully analyzed for pitch, energy, and spectral features. AI techniques such as Deep Neural Networks (DNNs) were applied to learn a model of JFK's audio, and how he uses intonation in his speech. At synthesis time, DNN models and high-dimensional search were used to find the best set of units to create new speech audio. Finally, the speech was enhanced by months of painstaking sound engineering—allowing audiences to hear the Trade Mart Speech delivered in JFK's own voice.

Related

SMPTE-JoelWelchHeadshot

SMPTE at Government Video Expo 2018

The Society is excited to co-present the SMPTE in D.C. conference with Government Video Expo and to share the latest technology trends on hot industry topics such as the transition to IP and HDR. The industry is experiencing a radical transformation, and we're delighted to provide attendees with continued education and the latest information on important developments affecting broadcast and video professionals.

Blackmagic Design Announces New Blackmagic Audio Monitor 12G

Blackmagic Design Announces New Blackmagic Audio Monitor 12G

Blackmagic Design today announced Blackmagic Audio Monitor 12G, a new, upgraded model of its extremely popular rack mount audio monitoring solution. The new Blackmagic Audio Monitor 12G features 12G-SDI video input, HDMI output, analog and AES/EBU inputs, a powerful class D amplifier, dual subwoofers, extended range speakers, an LCD and precision meters that can display VU, PPM and Loudness ballistic scales.

Blackmagic Design Announces DaVinci Resolve 15.2

Blackmagic Design Announces DaVinci Resolve 15.2

Blackmagic Design today announced DaVinci Resolve 15.2, a major update to its editing, color correction, visual effects and professional audio post production software. DaVinci Resolve 15.2 has been designed based on feedback from professional customers around the world. It includes over 30 new features that simplify and streamline everyday tasks so editors, colorists and sound engineers can work even faster.