SAN FRANCISCO - August 6, 2025 - attention labs, a NeurIPS award-winning team of neuroscientists and machine-learning engineers, committed to helping machines hear like humans, today announced the debut of Selective Auditory Attention (SAA), an AI technology that gives devices human-like hearing and allows for acoustic clarity issues.
SAA uses artificial intelligence (AI) to overcome a major problem affecting auditory AI, because it needs to understand human conversations, and to date has been unable to differentiate between multiple voices and other sounds. SAA works on different media devices such as headsets, TVs, smart glasses, tablets, and robots.
According to David J. Kim, CEO and cofounder of attention labs, “We first cracked the persistent ‘howling’ interference problem in 2022, for 40 video‑conferencing platforms that required pristine sound for natural hybrid meetings. Our selective auditory attention engine runs locally on devices, delivering crystal‑clear audio with millisecond latency and zero cloud dependency that averages 97% accuracy. Voices keep their snappy interaction timing, even with crosstalk.”
SAA mimics a psycho-acoustic phenomenon known as the cocktail party effect, based on our human brain, which can tune into a specific voice in a noisy environment.
If a room is full of multiple voices, humans can pick out one of them, even though all the sounds have equal volume. Until the advent of SAA, machines lacked this ability, so it was nearly impossible to single out the important voice in a conversation.
SAA features a real‑time auditory perception layer that is technology’s premier solution for people to be understood in loud, real-world settings. Common devices can now respond more quickly and reliably. The user will experience clear, exemplary sound, compared to previous murky sound experiences, where even turning up the volume does not help the listener understand what is being said.
Kim explained, “Voice AI mishears in group conversations. This is the challenge we set out to address. The result was SAA’s real‑time attention‑driven conversation intelligence. Our on-device engine identifies and routes relevant voices. AI identifies and finesses high‑fidelity audio‑visual data, capturing the spatial and conversational nuances of group conversations because scenes constantly shift with acoustics and behavior.”
He added, “Our engine models a selective, attention engine in real time across devices, enabling dynamic, inclusive interactions. The technology supports 2 to 8 microphones with flexible setups for built‑in mics, headsets, and peripherals.”
Speech is locally separated, data is kept private, response times are reduced, and accuracy is maintained as the AI can recognize and enhance the sound among diverse accents or overlapping talk. Applying AI to the sound helps understand context
SAA is private by design. Its sensitive audio processing stays on‑device so raw voices and soundscapes never leave the hardware.
The on‑device audio engine runs entirely on existing hardware, isolating relevant voices. The sound adapts as conversations shift, and works offline across XR, wearables, robots, and vehicles.
SAA instantly finds, focuses, and separates the voices that matter “directly on your device,” said Kim. “Plug it into any LLM and get real‑time context‑aware responses.”
The technology uses an embedded engine running on fast, ultra‑low power, with sub‑100 ms latency and an ultra‑low power draw on‑device for maximum privacy.
Attention labs partners with Meta, Sonos, Nvidia, Intel, Samsung, and Snap along with leading developers and enterprises. Tier‑1 OEMs and platform teams use attention labs for crystal-clear conversations.
For more information, to gain early access, or join the attention labs waitlist, visit https://attentionlabs.ai
Media Contact
Company Name: Attention labs
Contact Person: Media Relations
Email: Send Email
Country: United States
Website: https://attentionlabs.ai
