Noise Canceling AI Headphones Filter Unwanted Noise
Author: University of Washington
Published: 2023/11/09 - Updated: 2026/01/21
Publication Details: Peer-Reviewed, Product Release, Update
Category Topic: Hearing Devices - Related Publications
Page Content: Synopsis - Introduction - Main - Insights, Updates
Synopsis: This article discusses semantic hearing technology, which is particularly useful for individuals with hearing impairments, seniors, and those with disabilities by offering a novel approach to audio processing. It describes how noise-canceling AI headphones can selectively filter sounds, allowing wearers to choose which sounds they hear by streaming captured audio to a connected smartphone. This technology can significantly improve communication and reduce the challenges faced in noisy environments, making it an invaluable tool for enhancing auditory experiences. The article provides insights into how these devices work, their potential applications, and the benefits they offer, making it an interesting and informative read for anyone interested in assistive technologies or looking to improve their quality of life through better hearing solutions - Disabled World (DW).
- Definition: Noise-cancelling Headphones
Noise-cancelling headphones are a special type/kind of headphones which suppress unwanted ambient sounds. Noise-cancelling headphones can improve listening enough to completely offset the effect of a distracting concurrent activity.
There are two kinds of this noise cancellation: passive and active:
- Active noise cancellation uses more advanced technology to actively counter noise by detecting and analyzing the sound pattern of incoming noise and then generating a mirror "anti-noise" signal to cancel it out. The end result is means you hear a drastically reduced level of noise.
- Passive noise cancellation refers to noise cancellation achieved by the headset's physical features, like the design and type of materials used.
Noise-cancellation headphones have helped children with autism spectrum disorder (ASD) cope with behaviors related to hyper-reactivity and auditory stimuli - (2016 study from the Hong Kong Journal of Occupational Therapy).
Noise-cancellation headphones can also be used as sleeping aids, both passive isolating and active noise-cancellation headphones or earplugs help to achieve a reduction of ambient sounds, which is particularly helpful for people suffering from insomnia or other sleeping disorders.
Introduction
Most anyone who's used noise-canceling headphones knows that hearing the right noise at the right time can be vital. Someone might want to erase car horns when working indoors, but not when walking along busy streets. Yet people can't choose what sounds their headphones cancel.
A team led by researchers at the University of Washington has developed deep-learning algorithms that let users pick which sounds filter through their headphones in real time. The team is calling the system "semantic hearing."
The headphones stream captured audio to a connected smartphone, which cancels all environmental sounds. Either through voice commands or a smartphone app, headphone wearers can select which sounds they want to include from 20 classes, such as sirens, baby cries, speech, vacuum cleaners and bird chirps. Only the selected sounds will be played through the headphones.
Main Content
The team presented its findings Nov. 1 at UIST '23 in San Francisco. In the future, the researchers plan to release a commercial version of the system.
"Understanding what a bird sounds like and extracting it from all other sounds in an environment requires real-time intelligence that today's noise canceling headphones haven't achieved," said senior author Shyam Gollakota, a UW professor in the Paul G. Allen School of Computer Science & Engineering.
"The challenge is that the sounds headphone wearers hear need to sync with their visual senses. You can't be hearing someone's voice two seconds after they talk to you. This means the neural algorithms must process sounds in under a hundredth of a second."
Because of this time crunch, the semantic hearing system must process sounds on a device such as a connected smartphone, instead of on more robust cloud servers. Additionally, because sounds from different directions arrive in people's ears at different times, the system must preserve these delays and other spatial cues so people can still meaningfully perceive sounds in their environment.
Tested in environments such as offices, streets and parks, the system was able to extract sirens, bird chirps, alarms and other target sounds, while removing all other real-world noise. When 22 participants rated the system's audio output for the target sound, they said that on average the quality improved compared to the original recording.
In some cases, the system struggled to distinguish between sounds that share many properties, such as vocal music and human speech. The researchers note that training the models on more real-world data might improve these outcomes.
Co-authors
Additional co-authors on the paper were:
Bandhav Veluri and Malek Itani, both UW doctoral students in the Allen School.
Justin Chan, who completed this research as a doctoral student in the Allen School and is now at Carnegie Mellon University.
Takuya Yoshioka, director of research at AssemblyAI.
Insights, Analysis, and Developments
Editorial Note: The implications of semantic hearing extend beyond accessibility into questions about how we fundamentally interact with our soundscapes. For decades, noise-canceling technology has operated on a binary principle - suppress or allow - leaving users with limited control over their acoustic environment. The University of Washington team's breakthrough moves us toward a more nuanced relationship with sound, one that recognizes context and intention. While current limitations exist - the system's difficulty distinguishing between speech and vocal music suggests challenges ahead - the underlying principle is transformative for people with hearing impairments, sensory processing differences, and age-related hearing loss.What makes this advancement particularly significant is its emphasis on real-time processing and spatial awareness; by preserving the natural delays and directional cues that help us locate sound sources, semantic hearing doesn't just filter noise, it maintains our embodied connection to the environment. As these systems mature and training datasets expand, the gap between what sounds we can isolate and what sounds we want to isolate will continue to narrow. The commercialization of this technology will likely represent a watershed moment for assistive audio devices - Disabled World (DW).
Attribution/Source(s): This peer reviewed publication was selected for publishing by the editors of Disabled World (DW) due to its relevance to the disability community. Originally authored by University of Washington and published on 2023/11/09, this content may have been edited for style, clarity, or brevity.