Download RSS feed: News Articles / In the Media / Audio
In an article for Wired, Tim Moynihan writes that a team of CSAIL researchers has created a machine-learning system that can produce sound effects for silent videos. The researchers hope that the system could be used to “help robots identify the materials and physical properties of an object by analyzing the sounds it makes.”
Writing for the Financial Times, Clive Cookson reports that MIT researchers have developed an artificial intelligence system capable of producing realistic sounds for silent movies. Cookson explains that another application for the system could be “to help robots understand objects’ physical properties and interact better with their surroundings."
Washington Post reporter Matt McFarland writes that MIT researchers have created an algorithm that can produce realistic sounds. “The findings are an example of the power of deep learning,” explains McFarland. “With deep learning, a computer system learns to recognize patterns in huge piles of data and applies what it learns in useful ways.”
Popular Science reporter Mary Beth Griggs writes that MIT researchers have developed an algorithm that can learn how to predict sound. The algorithm “can watch a silent movie and create sounds that go along with the motions on screen. It's so good, it even fooled people into thinking they were actual, recorded sounds from the environment.”
TIME reporter Jeffrey Kluger writes that MIT researchers have designed an algorithm to produce an image of a black hole. Kluger explains that the algorithm will allow researchers “visualize the event horizon that surrounds the black hole at the center of our own galaxy.”
MIT graduate student Katie Bouman speaks with Ben Johnson of Marketplace about the algorithm she and her colleagues developed to allow people “to see the first image of a black hole.” Johnson notes the algorithm has uses beyond space exploration and could also potentially be used for MRI imaging.
MIT researchers have developed a new algorithm to compile data gathered by the Event Horizon Telescope and create an image of a black hole, reports James Griffiths for CNN. The algorithm will “fill in the gaps and filter out the interference and noise caused by our own atmosphere,” Griffiths explains.
Washington Post reporter Brian Fung writes that MIT researchers have developed an algorithm to create images of black holes by compiling data from radio telescopes around the world. Fung writes that the algorithm “could give us the first true images of a celestial phenomenon that, for decades, we've left to artists to imagine and describe with pictures.”
An algorithm developed by MIT researchers could help produce the first image of a black hole, reports Ryan Mandelbaum for Popular Science. Mandelbaum explains that the algorithm gathers data from radio telescopes around the globe and then uses “other images from space as references to craft a sort of mosaic that best matches the data from the telescopes.”
Boston Globe reporters J.D. Capelouto and Olivia Arnold write that MIT researchers have developed an algorithm aimed at producing images of black holes. MIT graduate student Katie Bouman notes that while there are predictions of what a black hole might look like, “it’s great to actually be able to probe it and…construct those images.”
Prof. Daniela Rus speaks with The Boston Globe’s Kevin Hartnett about her goal to create customizable, printable robots. “The idea is anyone could walk into a 24-hour robot manufacturing store with some idea of what they want,” Rus says. “Maybe a robot to entertain the cat while you’re at work or play chess with you or fold your laundry.”
Boston.com reporter Sanjay Salomon writes about how “Duckietown,” a model city developed by MIT researchers, could help make self-driving cars a reality. “We realized if you scale down autonomous driving to something very small there’s lots of research to do on a smaller scale with none of the logistical challenges of real autonomous vehicle research,” explains postdoc Liam Paull.
A new analysis by MIT researchers verifies the difficulty of the popular video game “Super Mario Brothers.” MIT researchers found that the game’s challenges belong to the “PSPACE” category of equations, “requiring exponential time to both solve, and to prove algorithmically,” G. Clay Whittaker of Popular Science explains.
The Economist reports that Prof. Daniela Rus and Dr. Shuhei Miyashita have developed a tiny origami robot that can be swallowed and used to collect dangerous items that have been accidentally ingested. “The device is based on foldable robot technology that their team of researchers have been working on for years.”
Prof. Daniela Rus speaks on Marketplace Tech about the origami robot that her group developed to serve as a microsurgeon. “This robot is ingestible in the form of a capsule,” explains Rus. “Once the robot reaches the stomach, the robot unfolds and can do interesting tasks.”