This paper addresses the problem of localizing audio sources using binaural measurements. We propose a supervised formulation that simultaneously localizes multiple sources at different locations. The approach is intrinsically efficient because, contrary to prior work, it relies neither on source separation, nor on monaural segregation. The method starts with a training stage that establishes a locally-linear Gaussian regression model between the directional coordinates of all the sources and the auditory features extracted from binaural measurements. While fixed-length wide-spectrum sounds (white noise) are used for training to reliably estimate the model parameters, we show that the testing (localization) can be extended to variable-length sparse-spectrum sounds (such as speech), thus enabling a wide range of realistic applications. Indeed, we demonstrate that the method can be used for audio-visual fusion, namely to map speech signals onto images and hence to spatially align the audio and visual modalities, thus enabling to discriminate between speaking and non-speaking faces. We release a novel corpus of real-room recordings that allow quantitative evaluation of the co-localization method in the presence of one or two sound sources. Experiments demonstrate increased accuracy and speed relative to several state-of-the-art methods.

New lip-reading technology developed at the University of East Anglia could help in solving crimes and provide communication assistance for people with hearing and speech impairments. The visual speech recognition technology, created by Helen L. Bear, PhD, and Prof Richard Harvey of UEA's School of Computing Sciences, can be applied "any place where the audio isn't good enough to determine what people are saying," Bear said. Those include criminal investigations, entertainment, and especially where are there are high levels of noise, such as in cars or aircraft cockpits, she said. Bear said unique problems with determining speech arise when sound isn't available -- such as on video footage -- or if the audio is inadequate and there aren't clues to give the context of a conversation. The sounds '/p/,' '/b/,' and '/m/' all look similar on the lips, but now the machine lip-reading classification technology can differentiate between the sounds for a more accurate translation.

Vast swarms of miniature robots are coming -- and they might be the answer to scrubbing our waters clean of lead. "Microbots" smaller than the width of a human hair could be highly effective and cost-efficient tools for removing lead and other contaminants from industrial wastewater, according to a new study published in the journal Nano Letters last month. In the space of a single hour, the study showed, self-propelled microbots could remove up to 95 percent of lead from water. Lead is commonly found in wastewater from mines or factories that make batteries and electronic devices, and can pose a serious risk to public health, as the water crisis in Flint, Michigan demonstrates. Heavy metal pollution can cost big cities billions of dollars a year, said Samuel Sánchez, co-author of the study and a research group leader at the Max Planck Institute for Intelligent Systems in Germany.

A blockchain intelligence vendor focused on combining the technology used to record and verify transactions with big data and artificial intelligence has attracted a pair of top technologist to serve in senior positions. Skry Inc., formerly Coinalytics, unveiled a name change this week along with the addition of new CTO and chief data scientist. The block chain analytics and intelligence firm based in Silicon Valley said Akash Singh, former CTO for data science at Chinese telecommunications giant Huawei (SHE: 002502) will serve as Skry's CTO. Singh also worked at IBM (NYSE: IBM), contributing to the development of its Watson cognitive computing platform. Also joining Skry is artificial intelligence researcher Masoud Nikravesh, former director of computational science and engineering at the University of California at Berkeley's Center for Information Technology Research in the Interest of Society.

Mark Zuckerberg wants to overtake Elon Musk to become the real-world version of Marvel superhero Tony Stark. The billionaire Facebook founder has expressed his desire (in a Facebook post, of course) to spend 2016 building an artificially intelligent assistant to help run his life at home and work – and directly compared it to Jarvis, the AI companion developed by Stark in the Iron Man films. Previous aims have included spending a year eating only meat from animals he killed himself in 2011, to read two books a month in 2015, and to learn Mandarin in a year in 2010. And when he declares one of the challenges, he goes hard on it: in October last year, he showed off his language abilities, delivering a 20-minute speech to students at Beijing's Tsinghua University entirely in Mandarin. Zuckerberg will start the project by "exploring what technology is already out there". Existing home-automation tools from companies such as Google's Nest, Phillips and Samsung all allow a fairly high level of control of a "smart home", and can be paired with voice control software, including that from Apple, Amazon and Massachusetts-based specialists Nuance.

If you close your eyes and imagine a brick wall, you can probably come up with a pretty good mental image. After seeing many such walls, your brain knows what one should look like. A startup in the U.K. is using machine learning to enable computers and smartphones to model visual information in a similar way. A computer could use these visual models for various tasks, from improving video streaming to automatically generating elements of a realistic virtual world. Magic Pony Technology, created by graduates of Imperial College London with expertise in statistics, computer vision, and neuroscience, trains large neural networks to process visual information.

Secretive electric car company Faraday Future hopes to have its first vehicles rolling off the assembly line in 2018. The announcement was made as officials marked the start of construction on a planned 1 billion Las Vegas-area production plant, not far from rival Tesla's Gigafactory. While it's clear the company plans to create an electric car, a prototype has yet to be unveiled and there are no specifics yet on what kinds of cars it might manufacture. The company, backed by Chinese entrepreneur Jia Yueting, currently has about 700 employees in the U.S. It unveiled a concept car in January, but hasn't put a vehicle on the market. Faraday Future puts the size of the Apex Industrial Park facility at 3 million square feet, or nearly the size of the sprawling Las Vegas Convention Center close to the Las Vegas Strip.

It is the luxury speedboat that could leave you shaken, but not stirred. Luxury car maker Aston Martin, the supplier of James Bond's cars, has revealed the design for its first foray onto water. The firm hopes to produce a series of powerboats, which is boasts will be as luxurious and hi-tech as its cars. The AM37 yacht will enter production later this year, and will be launched in Monaco. There will be two captains chairs and a wrap-around bench set to accommodate 8 of your friends to take along for the journey.

There has been some grumbling amongst industry folk who traveled to CinemaCon this year that studios aren't really showing anything new. In an age where fans clamor for teasers and trailers to debut earlier and earlier online, Hollywood has started giving sneak peeks of their films many months -- and sometimes years -- in advance of a movie's release. That wasn't the case with Universal Pictures, whose chairman Donna Langley told the crowd of movie theater owners gathered here on Wednesday that all material the studio would be sharing was "created specifically for CinemaCon." A majority of that material involved the studio's animated slate -- more on that here. But Universal also gave conference-goers a first glimpse at some of its most anticipated live-action releases.

Pop quiz: is the following statement true or false? Canada is the birthplace of a transformative technology set to disrupt countless industries and potentially lead the next wave of global economic growth. Most Canadians aren't aware of it, but artificial intelligence (more specifically its subset, deep learning) -- the inspiration for scores of dystopian science-fiction movies -- is a made-in-Canada technology that will become profoundly important over the next few years. Deep learning was the name given to a group of complex mathematical models that came out of the University of Toronto in 2006. In a nutshell, the technology mimics the neural networks of a human brain, giving machines the capacity to learn on their own and discover previously undetectable patterns within massive data sets.