New Brain-Inspired Algorithm Significantly Enhances Hearing Aid Performance in Noisy Environments

Navigating conversations in noisy places can be particularly challenging for individuals with hearing loss, a condition affecting nearly 50 million Americans and expected to impact 2.5 billion people globally by 2050. This difficulty, known as the "cocktail party problem," arises when hearing aids fail to effectively filter out background noise, making it hard to focus on specific voices. However, a new brain-inspired algorithm developed at Boston University (BU) could change that. Kamal Sen, an associate professor of biomedical engineering at the BU College of Engineering, and co-authors Virginia Best and Alexander D. Boyd, tested and validated this innovative algorithm, called BOSSA (Biologically Oriented Sound Segregation Algorithm), which aims to enhance the performance of hearing aids in noisy environments. BOSSA mimics the brain's natural ability to suppress unwanted sounds and focus on desired ones, using spatial cues like volume and timing to tune in and out of speakers. In their study, published in Communications Engineering, the researchers compared BOSSA with the industry-standard noise-reduction algorithms used in current hearing aids. The existing algorithms often fail to improve performance and sometimes make it worse, as anecdotal evidence and the team's data suggest. Conversely, BOSSA significantly boosted word recognition accuracy by 40 percentage points, a substantial and rare improvement in the field. Best, a research associate professor of speech, language, and hearing sciences at BU's Sargent College, emphasizes the importance of addressing the cocktail party problem: "People with hearing loss often struggle to communicate in noisy environments, such as dinner table conversations, social gatherings, and workplace meetings. Solutions that can enhance communication in these settings could have a significant impact on their quality of life." To test the algorithm, the team conducted behavioral studies with young adults who had sensorineural hearing loss, a common form usually caused by genetic factors or childhood diseases. Participants wore headphones that simulated multiple speakers in different locations, and their ability to distinguish specific voices was evaluated with and without the aid of BOSSA. Boyd, a Ph.D. candidate in biomedical engineering, collected much of the data and was the lead author on the study. The study's results were compelling: "The biologically inspired algorithm led to robust intelligibility gains under conditions in which a standard beamforming approach failed," the researchers reported. This indicates that BOSSA could be a game changer for people with hearing loss, offering a significant improvement in their ability to engage in social interactions and professional settings. Sen, who has a background in physics and neuroscience, has patented the algorithm and is seeking commercial partners to bring it to market. He believes that the current climate, with major tech companies like Apple entering the hearing aid sector, highlights the urgency for traditional hearing aid manufacturers to innovate. "If hearing aid companies don't start innovating fast, they're going to get wiped out, because Apple and other startups are entering the market," Sen warns. The researchers are not stopping at hearing loss. They are exploring the potential of BOSSA for other conditions related to attention difficulties, such as ADHD and autism. Sen explains that the neural circuits underlying BOSSA are fundamental to the brain's attention mechanisms. "It ultimately has to do with where you want to focus, and that's what the circuit was really built for. We're hoping to extend this to other populations who struggle in multi-stimulus environments," he says. The early tests of an upgraded version of BOSSA that includes eye-tracking technology show promise. This enhancement could allow users to better direct their listening attention, further improving the algorithm's effectiveness. Industry insiders and experts in the field have hailed BOSSA as a significant breakthrough. Its unique approach to sound segregation not only outperforms existing technologies but also opens up new possibilities for treating various attention disorders. The potential for widespread impact, combined with the algorithm's robust performance, positions BOSSA as a promising innovation in the rapidly evolving landscape of hearing technology. Boston University, known for its interdisciplinary research and cutting-edge technology, houses several centers dedicated to advancing understanding and treatment of hearing and neurological conditions. The Natural Sounds & Neural Coding Laboratory, where Sen conducts his research, focuses on decoding the brain's auditory pathways. The collaboration between Sen's team and clinical researchers like Best underscores the university's commitment to translating scientific discoveries into practical applications that improve human health and quality of life.