License agreement signed to commercialize intelligent hearing aid

April 01, 2001

CHAMPAIGN, Ill. -- For someone with partial hearing loss, picking out a voice in a crowded social gathering can be hard, even with the help of a hearing aid. That's about to change in a revolutionary way.

Scientists at the University of Illinois recently signed an exclusive licensing agreement with Phonak Inc., a leading manufacturer of technologically advanced hearing aids, to commercialize an intelligent hearing aid system. The new hearing-aid technology will be able to spatially separate sounds and process them in a way much like the human brain. A key feature of the new system is its ability to integrate signals from each ear so that a listener can focus on a desired voice while canceling out background noise.

The concept for the intelligent hearing aid was developed by a team of 12 researchers at the university's Beckman Institute for Advanced Science and Technology. Professors from the departments of physiology, electrical and computer engineering, and speech and hearing science contributed to the work.

"Today's state-of-the-art hearing aids can select a voice in a crowd by applying highly directive microphones," said Albert Feng, a UI professor of molecular and integrative physiology and leader of the Beckman team. "However, these devices cannot effectively differentiate between background noise and the desired conversation when the sources are in close proximity, causing confusion in noisy environments." By allowing the wearer to focus on a single conversation without excessive interference, the intelligent hearing aid will represent a significant improvement over conventional systems, Feng said.

The intelligent hearing aid prototype consists of a pair of miniature microphones, a processor, an amplifier and two earpieces. At the heart of the system is what is called a Binaurally based Intelligent Auditory Processor, which filters the sounds and transmits only the desired voice to the amplifier. The processor works by comparing signals from the microphones and detecting subtle differences in their time of arrival - much like the process that occurs in the human brain.

"Normal hearing exploits the fact that we have two ears," said Doug Jones, a UI professor of electrical and computer engineering and a member of the Beckman team. "Our brains utilize both the time of arrival and the intensity of impinging sound waves to perform spatial processing and filtering. This allows us to focus our attention in the direction of the desired sounds and ignore the rest." To perform this process artificially, the researchers developed an efficient algorithm capable of extracting the desired speech signal in the presence of multiple interfering sounds. Using the algorithm, they built a prototype that works in real time and performs very well in noisy environments.

"The algorithm mimics the biological system to perform auditory scene analysis and to reproduce how the brain selects and filters information," Jones said. "By pointing the microphones at the desired source, we can capture the intended signal and filter out all others." Phonak engineers and UI researchers are now working to package the prototype into a miniature, self-contained system. Phonak is headquartered in Stäfa, Switzerland.
-end-


University of Illinois at Urbana-Champaign

Related Algorithm Articles from Brightsurf:

CCNY & partners in quantum algorithm breakthrough
Researchers led by City College of New York physicist Pouyan Ghaemi report the development of a quantum algorithm with the potential to study a class of many-electron quantums system using quantum computers.

Machine learning algorithm could provide Soldiers feedback
A new machine learning algorithm, developed with Army funding, can isolate patterns in brain signals that relate to a specific behavior and then decode it, potentially providing Soldiers with behavioral-based feedback.

New algorithm predicts likelihood of acute kidney injury
In a recent study, a new algorithm outperformed the standard method for predicting which hospitalized patients will develop acute kidney injury.

New algorithm could unleash the power of quantum computers
A new algorithm that fast forwards simulations could bring greater use ability to current and near-term quantum computers, opening the way for applications to run past strict time limits that hamper many quantum calculations.

QUT algorithm could quash Twitter abuse of women
Online abuse targeting women, including threats of harm or sexual violence, has proliferated across all social media platforms but QUT researchers have developed a sophisticated statistical model to identify misogynistic content and help drum it out of the Twittersphere.

New learning algorithm should significantly expand the possible applications of AI
The e-prop learning method developed at Graz University of Technology forms the basis for drastically more energy-efficient hardware implementations of Artificial Intelligence.

Algorithm predicts risk for PTSD after traumatic injury
With high precision, a new algorithm predicts which patients treated for traumatic injuries in the emergency department will later develop posttraumatic stress disorder.

New algorithm uses artificial intelligence to help manage type 1 diabetes
Researchers and physicians at Oregon Health & Science University have designed a method to help people with type 1 diabetes better manage their glucose levels.

A new algorithm predicts the difficulty in fighting fire
The tool completes previous studies with new variables and could improve the ability to respond to forest fires.

New algorithm predicts optimal materials among all possible compounds
Skoltech researchers have offered a solution to the problem of searching for materials with required properties among all possible combinations of chemical elements.

Read More: Algorithm News and Algorithm Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.