Nancy Sinatra: ‘I’ll never forgive Trump voters. I hope the anger doesn’t kill me’

She may be 80 and cut off by Covid, but she’s still ready to walk all over Donald Trump. As her greatest songs are reissued, she reflects on the sexual politics of the 60s, her friendship with Elvis and her hopes for peace in the US

Nancy Sinatra has one of the most famous surnames in America, but she has struggled to feel proudly American of late. It’s a couple of weeks away from the inauguration of Joe Biden, and the singer and film star is recalling Donald Trump’s preparations for his own inauguration in 2017: his first dance with his wife Melania would be to her father’s signature hit, My Way.

Sinatra was disgusted. Her father was no fan of Trump: according to Frank’s former manager, he told Trump to “go fuck himself” after the billionaire refused to meet Frank’s fee for a 1990 performance at an Atlantic City casino. Nancy, in a since deleted tweet to Trump, wrote: “Just remember the first line of the song.” My Way begins: “And now the end is near.”

Continue reading...

‘It’s the screams of the damned!’ The eerie AI world of deepfake music

Artificial intelligence is being used to create new songs seemingly performed by Frank Sinatra and other dead stars. ‘Deepfakes’ are cute tricks – but they could change pop for ever

‘It’s Christmas time! It’s hot tub time!” sings Frank Sinatra. At least, it sounds like him. With an easy swing, cheery bonhomie, and understated brass and string flourishes, this could just about pass as some long lost Sinatra demo. Even the voice – that rich tone once described as “all legato and regrets” – is eerily familiar, even if it does lurch between keys and, at times, sounds as if it was recorded at the bottom of a swimming pool.

The song in question not a genuine track, but a convincing fake created by “research and deployment company” OpenAI, whose Jukebox project uses artificial intelligence to generate music, complete with lyrics, in a variety of genres and artist styles. Along with Sinatra, they’ve done what are known as “deepfakes” of Katy Perry, Elvis, Simon and Garfunkel, 2Pac, Céline Dion and more. Having trained the model using 1.2m songs scraped from the web, complete with the corresponding lyrics and metadata, it can output raw audio several minutes long based on whatever you feed it. Input, say, Queen or Dolly Parton or Mozart, and you’ll get an approximation out the other end.

Continue reading...

Friday US briefing: Trump escalates feud with Pelosi amid shutdown

How the president’s two years in power have changed key US policies ... North Korean envoy to meet Pompeo ... Democrat takes charge of Flint water crisis investigation

Good morning, I’m Tim Walker with today’s essential stories.

Continue reading...