Fifty five years after he was assassinated, President John F. Kennedy has delivered his final speech-- thanks to artificial intelligence.
The Times of London has brought the ambitious project to life, using technology to recreate his voice speaking the words he was set to speak on the day he was killed in Dallas. The speech aired on the Times website as a 22-minute video today.
The project was originally the brainchid of Alan Kelly, executive creative director at Irish agency Rothco, who had a lifelong fascination with Kennedy. "I was watching a documentary about the president's Dallas trip and I had never really thought about where he was on his way to when he was shot," he told the Times in today's article. He discovered the existence of the speech, looked it up online and "was blown away by how prescient it is to today."
Rothco and The Times worked with CereProc, a British audio tech company, to analyze recordings from Kennedy and build a database to deliver the words of the Dallas speech. The process included reviewing 831 analog recordings of JFK speeches and interviews, applying spectrum analysis tools to improve acoustic environment and match them across samples and 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.
The speech will be supported by a wider campaign including cutdowns, teasers and promotional material on social, radio, digital, and print.