0
0
April 29, 2025
For millions of people with hearing loss, navigating lively social settings-such as bustling restaurants or crowded parties-can be a daunting challenge. Traditional hearing aids often struggle to filter out background noise, making it difficult to focus on a single conversation amid the din. Now, a team of researchers from Boston University (BU) may have found a breakthrough solution.
Tackling the “Cocktail Party Problem”
The so-called “cocktail party problem” has long plagued hearing aid users: the inability to distinguish a single voice from a sea of overlapping chatter. BU researchers, led by Associate Professor Kamal Sen, have developed a new brain-inspired algorithm, dubbed BOSSA (biologically oriented sound segregation algorithm), that promises to dramatically improve hearing aid performance in noisy environments.
In laboratory tests, BOSSA improved word recognition accuracy by 40 percentage points compared to current industry-standard hearing aid algorithms. “We were extremely surprised and excited by the magnitude of the improvement in performance-it’s pretty rare to find such big improvements,” said Sen.
How the Algorithm Works
Inspired by the brain’s own mechanisms for processing sound, BOSSA mimics the way inhibitory neurons help suppress unwanted noise. The algorithm uses spatial cues-such as the volume and timing of sounds-to isolate and enhance a target speaker’s words, while dampening background interference.
“It’s basically a computational model that mimics what the brain does, and actually segregates sound sources based on sound input,” explained Sen.
Real-World Impact and Future Applications
The potential impact is significant: nearly 50 million Americans live with hearing loss, and the World Health Organization estimates that by 2050, 2.5 billion people globally will be affected. “These environments are very common in daily life and they tend to be really important to people-think about dinner table conversations, social gatherings, workplace meetings,” noted co-author Virginia Best, a research associate professor at BU.
The research team tested the algorithm with young adults with sensorineural hearing loss. Participants were asked to pick out specific speakers in simulated noisy environments using the new algorithm, the current standard, and no algorithm. The results were clear: BOSSA provided robust gains in speech intelligibility where existing technology failed.
Looking Ahead: Beyond Hearing Loss
The researchers are already working on an upgraded version of BOSSA that incorporates eye-tracking, allowing users to direct their listening attention more precisely. Sen also sees broader applications for the underlying science, potentially benefiting individuals with ADHD or autism who struggle with attention in multi-source environments.
With tech giants like Apple entering the hearing aid market, the BU team believes their innovation is timely. Sen has patented BOSSA and is seeking industry partners to bring the technology to consumers.
Reference
The full study, “A brain-inspired algorithm improves ‘cocktail party’ listening for individuals with hearing loss,” by Alexander D. Boyd et al., is published in Communications Engineering (2025). DOI: 10.1038/s44172-025-00414-5
Disclaimer:
This article is based on findings published in a peer-reviewed scientific journal and summarized from a report on Medical Xpress. The described algorithm is currently in the research phase and not yet commercially available. Individuals interested in new hearing aid technologies should consult with healthcare professionals for advice tailored to their specific needs.
Citations:
