×
You will be redirected back to your article in seconds

How AI Tech Is Changing Dubbing, Making Stars Like David Beckham Multilingual

David Beckham does not speak Arabic, Hindi or Mandarin. But when the soccer legend starred in a PSA for malaria awareness this spring, he effortlessly switched among these and six other languages, thanks to cutting-edge technology that could soon change how Hollywood localizes its movies and TV shows.

The PSA in question was produced with technology from Synthesia, a London-based startup that uses artificial intelligence for dubbing. In Beckham’s case, the company recorded video footage of the soccer star as well as native speakers in each of the languages it wanted to use.

Then it fed all that raw footage to an algorithm that “learned” the facial expressions for each word in languages like Spanish and Yoruba, and tweaked video of Beckham’s face accordingly. “You puppeteer video,” explains Synthesia co-founder and chief operating officer Steffen Tjerrild. “We have actual lip-sync.”

AI-based video editing has gotten a lot of attention for its darker side, best known as the “deep fake” phenomenon — porn videos that have been altered by so-called deep learning-based algorithms to convincingly feature the faces of celebrities. However, Synthesia’s work shows that the technology also has a lot of potential for Hollywood, with dubbing being a key area of interest.

Traditionally, dubbing has been done without altering the source video. Instead, local script writers aim to match translated dialogue to the action on screen. “It takes a lot to prepare those scripts,” says Tjerrild. What’s more, voice actors have to time their delivery perfectly to make sure the dub doesn’t feel off, a process that can take weeks for feature films.

Artificial intelligence that tweaks an actor’s mouth movements to fit the local language could significantly shorten those timelines and make dubs even more accurate, agrees Markus Gross, vice president of research at Disney Research. “If we had the possibility to change lip movement in post-production, that would be a huge deal,” he says. “It points to ways to make the lip-sync indistinguishable from what the actor would do if he spoke that language.”

Disney Research has done some work on using deep learning for speech animation, and is looking at ways to apply the tech to special effects. While dubbing isn’t a high priority for the studio’s research arm, Gross signals that he is intrigued by the possibilities. “It is definitely on the horizon for us,” he says.

Dubbing is becoming ever more important for Hollywood as media companies target consumers worldwide with their own streaming services. Netflix, for instance, is dubbing in 31 languages, and began to target English-language audiences with dubbed versions of foreign originals last year. “We are taking this new initiative very seriously,” says the company’s head of international dubbing, Debra Chinn, about its efforts to unlock global stories for the English-speaking world. 

The streaming giant has been exploring methods for automating some aspects of dubbing, but Chinn cautions that there may be limits to what technology can do. “Dubbing is an art,” she says. “It’s a creative process.”

There are indeed technical issues. Synthesia’s tech works best when actors look directly into the camera and is less effective with profile shots or action scenes.

Teaching the algorithms the facial idiosyncrasies of each individual actor is also challenging. “No actor can speak 20 languages,” says Gross. And while an algorithm can do a good job of making it look like someone’s mouth forms foreign-language words, it doesn’t know how an actor such as Leonardo DiCaprio would deliver a line in Mandarin.

Ultimately, studios might have to test their dubs with actual users, suggests Gross. “We have to expose the results to a lot of people and then ask them if they feel it’s authentic or if it looks weird.”

Employing AI for dubbing will be less demanding in animation, where the technology can also be used to better match the mouth movements of a character to the original language. “It is one important step to produce high-quality animation at a lower price tag,” says Gross. 

Those savings could help convince Hollywood to embrace this kind of technology in the near future. “Within the next two, three years,” Gross says, “we could see first applications.”

Popular on Variety

More Biz

  • Spotify

    Spotify Dismisses Amazon’s High-Definition Audio: ‘It’s Not a Big Differentiator’

    At the moment Amazon Music launched its new high-definition audio service on Tuesday morning, which it says offers the best streaming audio fidelity available, Spotify VP and head of investor relations Paul Vogel was speaking at Goldman Sachs’ Communicopia conference in Lower Manhattan. While Tidal and Deezer have long offered a high-fidelity service and Apple [...]

  • Randall Stephenson

    AT&T CEO Defends WarnerMedia Strategy, Addresses Activist Investor's Letter

    AT&T chairman and CEO Randall Stephenson defended the $85 billion deal for Time Warner as the right strategy for the company in response to criticism from an activist investor. Consumers are watching more content and more of that viewing is digital, so combining a telecommunications company like AT&T with a content powerhouse like WarnerMedia is [...]

  • Whistle Sports

    Whistle and OTRO Announce Multi-Year Commercial Partnership

    The entertainment and sports media company Whistle and the digital content studio OTRO have announced a multi-year commercial partnership. Together, the two companies will collaborate on programming strategy, co-creating premium original content and developing experiential activations. They will also work together on the development and monetization of content and IP formats globally. “With Whistle’s deep understanding [...]

  • Amazon Music

    Amazon Music Unveils HD: the ‘Highest Quality Audio’ for Streaming

    Amazon Music today became the first of the three major streaming services to offer high-definition sound with the launch of Amazon Music HD. According to the announcement, the service offers recordings that are encoded with FLAC (free lossless audio codec, which means they can be compressed without a loss in quality) with more than 50 [...]

  • Sony Corp USA Building Placeholder Logo

    Sony Rejects Breakup Proposal From Dan Loeb

    Sony has rejected the corporate breakup proposal that it received three months ago from activist investor Dan Loeb and his Third Point Capital. Loeb, who in June built up a $1.5 billion stake in the company, had called on Sony to divest its image-sensors business in order to focus more on entertainment, release value and [...]

More From Our Brands

Access exclusive content