Connect with us

Technology

AI solves the ‘cocktail party problem’ and proves useful in court

Published

on

AI solves the 'cocktail party problem' and proves useful in court
Getty Images Four women in their thirties chatting with drinks in their handsGetty Images

In groups people screen out chatter around them – and now technology can do the same

It’s the perennial “cocktail party problem” – standing in a room full of people, drink in hand, trying to hear what your fellow guest is saying.

In fact, human beings are remarkably adept at holding a conversation with one person while filtering out competing voices.

However, perhaps surprisingly, it’s a skill that technology has until recently been unable to replicate.

And that matters when it comes to using audio evidence in court cases. Voices in the background can make it hard to be certain who’s speaking and what’s being said, potentially making recordings useless.

Advertisement

Electrical engineer Keith McElveen, founder and chief technology officer of Wave Sciences, became interested in the problem when he was working for the US government on a war crimes case.

“What we were trying to figure out was who ordered the massacre of civilians. Some of the evidence included recordings with a bunch of voices all talking at once – and that’s when I learned what the “cocktail party problem” was,” he says.

“I had been successful in removing noise like automobile sounds or air conditioners or fans from speech, but when I started trying to remove speech from speech, it turned out not only to be a very difficult problem, it was one of the classic hard problems in acoustics.

“Sounds are bouncing round a room, and it is mathematically horrible to solve.”

Advertisement
Paul Cheney Keith McElveen stands in front of a white board holding a marker penPaul Cheney

Keith McElveen founded Wave Sciences in 2008 to focus on the “cocktail party problem”

The answer, he says, was to use AI to try to pinpoint and screen out all competing sounds based on where they originally came from in a room.

This doesn’t just mean other people who may be speaking – there’s also a significant amount of interference from the way sounds are reflected around a room, with the target speaker’s voice being heard both directly and indirectly.

In a perfect anechoic chamber – one totally free from echoes – one microphone per speaker would be enough to pick up what everyone was saying; but in a real room, the problem requires a microphone for every reflected sound too.

Mr McElveen founded Wave Sciences in 2009, hoping to develop a technology which could separate overlapping voices. Initially the firm used large numbers of microphones in what’s known as array beamforming.

Advertisement

However, feedback from potential commercial partners was that the system required too many microphones for the cost involved to give good results in many situations – and wouldn’t perform at all in many others.

“The common refrain was that if we could come up with a solution that addressed those concerns, they’d be very interested,” says Mr McElveen.

And, he adds: “We knew there had to be a solution, because you can do it with just two ears.”

The company finally solved the problem after 10 years of internally funded research and filed a patent application in September 2019.

Advertisement
Keith McElveen Sound waves on Keith McElveen's computer screenKeith McElveen

It took Wave Sciences 10 years to solve the “cocktail party problem”

What they had come up with was an AI that can analyse how sound bounces around a room before reaching the microphone or ear.

“We catch the sound as it arrives at each microphone, backtrack to figure out where it came from, and then, in essence, we suppress any sound that couldn’t have come from where the person is sitting,” says Mr McElveen.

The effect is comparable in certain respects to when a camera focusses on one subject and blurs out the foreground and background.

“The results don’t sound crystal clear when you can only use a very noisy recording to learn from, but they’re still stunning.”

Advertisement

The technology had its first real-world forensic use in a US murder case, where the evidence it was able to provide proved central to the convictions.

After two hitmen were arrested for killing a man, the FBI wanted to prove that they’d been hired by a family going through a child custody dispute. The FBI arranged to trick the family into believing that they were being blackmailed for their involvement – and then sat back to see the reaction.

While texts and phone calls were reasonably easy for the FBI to access, in-person meetings in two restaurants were a different matter. But the court authorised the use of Wave Sciences’ algorithm, meaning that the audio went from being inadmissible to a pivotal piece of evidence.

Since then, other government laboratories, including in the UK, have put it through a battery of tests. The company is now marketing the technology to the US military, which has used it to analyse sonar signals.

Advertisement

It could also have applications in hostage negotiations and suicide scenarios, says Mr McElveen, to make sure both sides of a conversation can be heard – not just the negotiator with a megaphone.

Late last year, the company released a software application using its learning algorithm for use by government labs performing audio forensics and acoustic analysis.

Getty Images A young mother and her young son speak to a smart speaker on the table in front of themGetty Images

Eventually Wave wants to launch versions of its product for use in smart speakers

Eventually it aims to introduce tailored versions of its product for use in audio recording kit, voice interfaces for cars, smart speakers, augmented and virtual reality, sonar and hearing aid devices.

So, for example, if you speak to your car or smart speaker it wouldn’t matter if there was a lot of noise going on around you, the device would still be able to make out what you were saying.

Advertisement

AI is already being used in other areas of forensics too, according to forensic educator Terri Armenta of the Forensic Science Academy.

“ML [machine learning] models analyse voice patterns to determine the identity of speakers, a process particularly useful in criminal investigations where voice evidence needs to be authenticated,” she says.

“Additionally, AI tools can detect manipulations or alterations in audio recordings, ensuring the integrity of evidence presented in court.”

And AI has also been making its way into other aspects of audio analysis too.

Advertisement
Bosch Samarjit Das holding the Bosch SoundSeeBosch

Samarjit Das with the SoundSee which can predict a car’s malfunction before it happens

Bosch has a technology called SoundSee, that uses audio signal processing algorithms to analyse, for instance, a motor’s sound to predict a malfunction before it happens.

“Traditional audio signal processing capabilities lack the ability to understand sound the way we humans do,” says Dr Samarjit Das, director of research and technology at Bosch USA.

“Audio AI enables deeper understanding and semantic interpretation of the sound of things around us better than ever before – for example, environmental sounds or sound cues emanating from machines.”

More recent tests of the Wave Sciences algorithm have shown that, even with just two microphones, the technology can perform as well as the human ear – better, when more microphones are added.

Advertisement

And they also revealed something else.

“The math in all our tests shows remarkable similarities with human hearing. There’s little oddities about what our algorithm can do, and how accurately it can do it, that are astonishingly similar to some of the oddities that exist in human hearing,” says McElveen.

“We suspect that the human brain may be using the same math – that in solving the cocktail party problem, we may have stumbled upon what’s really happening in the brain.”

Source link

Advertisement
Continue Reading
Advertisement
Click to comment

You must be logged in to post a comment Login

Leave a Reply

Technology

Netflix teases its animated Splinter Cell series

Published

on

Netflix teases its animated Splinter Cell series

It’s been quite some time since we heard anything about Netflix’s animated adaptation of Splinter Cell — but the streamer has finally provided some details on the show. The reveal comes in the form of a very brief teaser trailer, which shows a little bit of the show, but mostly showcases Liev Schreiber’s gravelly take on lead character Sam Fisher. We also have a proper name now: it’s called Splinter Cell: Deathwatch.

Source link

Continue Reading

Science & Environment

Horseshoe crabs: Ancient creatures who are a medical marvel

Published

on

Horseshoe crabs: Ancient creatures who are a medical marvel


Horseshoe crabs: Ancient creatures who are a medical marvel – CBS News

Watch CBS News

Advertisement



Correspondent Conor Knighton visits New Jersey beaches along the Delaware Bay to learn about horseshoe crabs – mysterious creatures that predate dinosaurs – whose very blood has proved vital to keeping humans healthy by helping detect bacterial endotoxins. He talks with environmentalists about the decline in the horseshoe crab population, and with researchers who are pushing the pharmaceutical industry to switch its use of horseshoe crab blood with a synthetic alternative used in medical testing.

Advertisement

Be the first to know

Get browser notifications for breaking news, live events, and exclusive reporting.




Source link

Advertisement
Continue Reading

Technology

NYT Strands today — hints, answers and spangram for Friday, September 20 (game #201)

Published

on

NYT Strands homescreen on a mobile phone screen, on a light blue background

Strands is the NYT’s latest word game after the likes of Wordle, Spelling Bee and Connections – and it’s great fun. It can be difficult, though, so read on for my Strands hints.

Want more word-based fun? Then check out my Wordle today, NYT Connections today and Quordle today pages for hints and answers for those games.

Source link

Continue Reading

Science & Environment

SpaceX to launch bitcoin entrepreneur and three crewmates on flight around Earth’s poles

Published

on

SpaceX to launch bitcoin entrepreneur and three crewmates on flight around Earth's poles


A blockchain entrepreneur, a cinematographer, a polar adventurer and a robotics researcher plan to fly around Earth’s poles aboard a SpaceX Crew Dragon capsule by the end of the year, becoming the first humans to observe the ice caps and extreme polar environments from orbit, SpaceX announced Monday.

The historic flight, launched from the Kennedy Space Center in Florida, will be commanded by Chun Wang, a wealthy bitcoin pioneer who founded f2pool and stakefish, “which are among the largest Bitcoin mining pools and Ethereum staking providers,” the crew’s website says.

081224-fram2-crew.jpg
The Fram2 crew, seen during a visit to SpaceX’s Hawthorn, Calif., manufacturing facility. Left to right: Eric Philips, Jannicke Mikkelse, commander Chun Wang and Rabea Rogge.

Advertisement

SpaceX


“Wang aims to use the mission to highlight the crew’s explorational spirit, bring a sense of wonder and curiosity to the larger public and highlight how technology can help push the boundaries of exploration of Earth and through the mission’s research,” SpaceX said on its website.

Wang’s crewmates are Norwegian cinematographer Jannicke Mikkelsen, Australian adventurer Eric Philips and Rabea Rogge, a German robotics researcher. All four have an interest in extreme polar environments and plan to carry out related research and photography from orbit.

The mission, known as “Fram2” in honor of a Norwegian ship used to explore both the Arctic and Antarctic regions, will last three to five days and fly at altitudes between about 265 and 280 miles.

Advertisement

“This looks like a cool & well thought out mission. I wish the @framonauts the best on this epic exploration adventure!” tweeted Jared Isaacman, the billionaire philanthropist who charted the first private SpaceX mission — Inspiration4 — and who plans to blast off on a second flight — Polaris Dawn — later this month.

The flights “showcase what commercial missions can achieve thanks to @SpaceX’s reusability and NASA’s vision with the commercial crew program,” Isaacman said. “All just small steps towards unlocking the last great frontier.”

Like the Inspiration4 mission before them, Wang and his crewmates will fly in a Crew Dragon equipped with a transparent cupola giving them a picture-window view of Earth below and deep space beyond.

No astronauts or cosmonauts have ever viewed Earth from the vantage point of a polar orbit, one tilted, or inclined, 90 degrees to the equator. Such orbits are favored by spy satellites, weather stations and commercial photo-reconnaissance satellites because they fly over the entire planet as it rotates beneath them.

The high-inclination record for piloted flight was set in the early 1960s by Soviet Vostok spacecraft launched into orbits inclined 65 degrees. The U.S. record was set by a space shuttle mission launched in 1990 that carried out a classified military mission in an orbit tilted 62 degrees with respect to the equator.

The International Space Station never flies beyond 51.6 degrees north and south latitude. NASA planned to launch a space shuttle on a classified military mission around the poles in 1986, but the flight was canceled in the wake of the Challenger disaster.

Advertisement

“The North and South Poles are invisible to astronauts on the International Space Station, as well as to all previous human spaceflight missions except for the Apollo lunar missions but only from far away,” the Fram2 website says. “This new flight trajectory will unlock new possibilities for human spaceflight.”

SpaceX has launched 13 piloted missions carrying 50 astronauts, cosmonauts and private citizens to orbit in nine NASA flights to the space station, three commercial visits to the lab and the Inspiration4 mission chartered by Isaacman.

Isaacman and three crewmates plan to blast off Aug. 26 on another fully commercial flight, this one featuring the first civilian spacewalks. NASA plans to launch its next Crew Dragon flight to the space station around Sept. 24.

Advertisement





Source link

Advertisement
Continue Reading

Technology

Finally, a screen that goes anywhere

Published

on

Finally, a screen that goes anywhere

Today we’re launching a totally new, totally different app. Meet Orion.

Orion is a small, fun app that helps you use your iPad as an external HDMI display for any camera, video game console, or even VHS. Just plug in one of the bajillion inexpensive adapters, and Orion handles the rest.

But wait — we’re a camera company. Why an HDMI monitor?

We built this to scratch a few itches. First, in professional cinematography, it’s common to connect an external screen to your camera to get a better view of the action. Orion not only gives you a bigger screen, but you can even share screenshots with your crew with a couple of taps.

We also built this for… pure fun. When traveling with a Nintendo Switch, it’s a delight to play games on a bigger screen, especially alongside friends.

Source link

Advertisement
Continue Reading

Science & Environment

Giant “flying” Joro spiders love big cities. A new study found their ability to chill out in stressful situations may be why

Published

on

Giant "flying" Joro spiders love big cities. A new study found their ability to chill out in stressful situations may be why


The saga of the large invasive Joro spiders that parachute through the air isn’t over. A new study found that the critters with 4-inch-long legs are truly built differently, with hearts that are able to withstand the loud and bustling noises of big cities

University of Georgia researcher Andy Davis made the discovery while conducting cardiac stress tests on Joro spiders and their cousin, the golden silk spider. The research, published in Physiological Entomology on Monday, found that the species know how to chill out and stay calm when put in heart rate-raising situations. 

The Joro spider, also known as Trichonephila clavata, “is known for making webs not only in natural green spaces but also in cities and towns, often on buildings and human dwellings,” the study says. “The stress reactions of Trichonephila spiders could be characterized as ‘even-tempered,’ which may factor into their ability to live in habitats with frequent disturbances.”

Advertisement

Davis and his team evaluated the physiological reactions of Joro spiders and golden silk spiders and compared them to those of another pair of similarly-sized species that are related to each other, garden spiders and banded garden spiders. 

Researchers recorded baseline heart rates of the arachnids while they were resting and inactive, and then recorded their heart rates after restraining them under electronic sensors for 10 minutes.

Spider Takeover
The Joro spider seen in Johns Creek, Georgia, on Oct. 24, 2021.

Alex Sanz / AP

Advertisement


“When subjected to the novel restraint stress, heart rates of all spider species became elevated, which is an expected reaction that other spider researchers have noted,” the study says. “However, there were differences among species in the magnitude of this elevation, and of how the responses progressed during the 10 min period.”

The garden spiders, both of which belong to the Argiope genus, showed “distinct periods of fluctuations during the restraint” and were even found to struggle against the restraints, researchers said. Joro spiders and their golden silk cousins, on the other hand, were “less variable and more even.” They were also observed entering a state of thanatosis for more than an hour after stressors, meaning they essentially froze up during that time. 

The tests “are beginning to paint a picture of how the invasive Joro spider and its cousin, the golden silk spider, have a unique way of tolerating novel stressors, which may be the reason for their ability to occupy anthropogenic landscapes,” researchers said, noting that other spider species in their family line could share this trait, although that would need further investigation.

Joro spiders have been making headlines for years as they continue to spread up the East Coast. Originally from Asia, the spiders are believed to have been first introduced to north Georgia around 2010. They have since been found across nearly a dozen other states. In December, Davis told The New York Times that New York is “right in the middle of where they like to be.” It’s been predicted that they could pop up in the New York tri-state area this summer, although no reports of such have been made.

Advertisement
A Joro spider
A Joro spider

Dave Coyle/Clemson University


“They seem to be OK with living in a city,” he told the paper, adding that they’ve been seen hanging out on street lamps and telephone poles, where “regular spiders wouldn’t be caught dead in.” 

The latest findings may not definitively prove that the spiders’ relaxed demeanor is the reason for “their affinity for urban settings,” the study says, adding that more research is needed. It does, however, bolster Davis’ research from February, which also found that Joro spiders don’t necessarily mind the increased noise and vibrations that come with city living. 

Advertisement

“These Joro webs are everywhere in the fall, including right next to busy roads, and the spiders seem to be able to make a living there. For some reason, these spiders seem urban tolerant,” Davis said of his earlier research. 

UGA student and co-author of that study, Alexa Schultz, agreed, saying, “It looks like Joro spiders are not going to shy away from building a web under a stoplight or an area where you wouldn’t imagine a spider to be.” 

But don’t worry — while the spiders are venomous, they don’t pose a danger to humans, although they may elevate your heart rate more than you elevate theirs.  

Advertisement

Advertisement



Source link

Continue Reading

Trending

Copyright © 2017 Zox News Theme. Theme by MVP Themes, powered by WordPress.