Mathematicians Solve the 'Cocktail Party Problem'

August 22, 2006

Officials at the CIA and scientists around the world have pondered the "cocktail party problem" for decades. How could they separate one sound - perhaps a voice - from a group of other recorded sounds, perhaps a multitude of voices at a cocktail party? Now, two researchers at the University of Missouri-Columbia have found a mathematical solution to this problem.

"Theoretically, our solution says you should be able to pick up voices on a squeaky old microphone and then separate them all out so that you can hear what each person is saying in his or her own voice," said Peter Casazza, professor of mathematics in MU's College of Arts and Science. "This is a very old problem, and we have the first mathematical solution to it."

Casazza and Dan Edidin, also a professor of mathematics at MU, worked with Radu Balan of Siemens Corporate Research to solve the problem. Their solution shows that it is possible to separate voices and still retain vocal characteristics. Researchers had previously found a solution for separating and reconstructing voices, but they were only able to reconstruct the words spoken, not the characteristics of the voice itself.

"Our solution is called 'signal reconstruction without noisy phase,'" Edidin said. "In speech recognition technology, a 'signal' could be a recording of 25 people in a room talking at the same time. Our solution shows that we can pull out each voice individually, not just with the words, but with the voice characteristics of each individual. We showed that this 'cocktail party problem' is mathematically solvable."

Although Casazza, Edidin and Balan do not have a computer program that can do this automatically, they hope to find a way to develop one. Currently, their solution runs on a computer, but the process cannot be easily replicated or distributed.

"The computer we use is doing the work without an algorithmic program. It uses a system called a neural net, which is designed for the computer to teach itself. Basically, it works on trial and error," Casazza said. "This isn't consistent and cannot be duplicated easily. We need to find a way to design an implementable algorithm that could do this consistently and quickly."

Casazza said that there are already programs that can separate and reconstruct voices, but they are not completely reliable. For example, such programs have difficulty separating voices with similar pitch characteristics. A program using the researchers' solution would be more exact.

Source: University of Missouri

Explore further: Wearables to boost security of voice-based log-in

Related Stories

Wearables to boost security of voice-based log-in

October 17, 2017

A security-token necklace, ear buds or eyeglasses developed at the University of Michigan could eliminate vulnerabilities in voice authentication—the practice of logging in to a device or service with your voice alone.

Brain-machine interfaces to treat neurological disease

October 18, 2017

Since the 19th century at least, humans have wondered what could be accomplished by linking our brains – smart and flexible but prone to disease and disarray – directly to technology in all its cold, hard precision. Writers ...

Recommended for you

Metacognition training boosts gen chem exam scores

October 20, 2017

It's a lesson in scholastic humility: You waltz into an exam, confident that you've got a good enough grip on the class material to swing an 80 percent or so, maybe a 90 if some of the questions go your way.

Scientists see order in complex patterns of river deltas

October 19, 2017

River deltas, with their intricate networks of waterways, coastal barrier islands, wetlands and estuaries, often appear to have been formed by random processes, but scientists at the University of California, Irvine and other ...

Six degrees of separation: Why it is a small world after all

October 19, 2017

It's a small world after all - and now science has explained why. A study conducted by the University of Leicester and KU Leuven, Belgium, examined how small worlds emerge spontaneously in all kinds of networks, including ...

Ancient DNA offers new view on saber-toothed cats' past

October 19, 2017

Researchers who've analyzed the complete mitochondrial genomes from ancient samples representing two species of saber-toothed cats have a new take on the animals' history over the last 50,000 years. The data suggest that ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.