Talking in a noisy place is difficult, especially for people with hearing loss. A team made smart headphones that use artificial intelligence to find the voices in a conversation and reduce other sounds.
The system has two AI models. One tracks who spoke when and the turn-taking rhythm. The other mutes voices that do not follow the conversation pattern and other background noise. It can identify a conversation partner from two to four seconds of audio and runs on common off‑the‑shelf hardware. The team showed the work in Suzhou and released the code as open‑source.
Difficult words
- hearing loss — reduced ability to detect sounds
- artificial intelligence — computer systems that can learn and decide
- model — a computer program that makes predictionsmodels
- turn-taking — the pattern of when people speak in conversation
- background noise — unwanted sounds around that make hearing hard
- open‑source — software with publicly available source code
Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.
Discussion questions
- Do you find it hard to talk in noisy places? Why or why not?
- Would you try smart headphones that reduce background noise? Why?
- How long can you listen to one person in a noisy place before you lose focus?
Related articles
Zenica School of Comics: Art and Education for Children
The Zenica School of Comics began during the 1992–95 war and has taught around 200 young artists. The school still runs, faces changes from tablets and AI, and the regional comics scene survives through festivals and cooperation.
Indonesia tightens rules for digital platforms
Indonesia is increasing regulation of global digital platforms to curb misinformation and protect public safety. Officials inspected a major company's office, require platform registration, and use takedown systems, which has drawn criticism over unclear rules and rights.
People with AMD Judge Car Arrival Times Like Others
A virtual reality study compared adults with age-related macular degeneration (AMD) and adults with normal vision. Both groups judged vehicle arrival times similarly; vision and sound were used together, and a multimodal benefit did not appear.