Back to Case Studies
Wearables
AudioMind
AI Smart Earbuds based on BES2600
True wireless earbuds that automatically adjust ANC and EQ based on detected environment and user activity.
ANC Depth
45 dB
Latency
80ms (Game)
AudioMind
Client
A premium audio brand developing true wireless earbuds with adaptive noise cancellation that automatically adjusts to the user's environment.
Challenge
Running simultaneous ANC DSP, environmental classification, and BLE audio streaming on a single BES SoC without introducing audio artifacts during mode transitions.
Product Concept & Architecture
The BES2600YP dual-core SoC handles ANC processing, audio codec, and BLE 5.3. Three feed-forward and two feedback MEMS microphones enable hybrid ANC. A Knowles balanced armature + dynamic hybrid driver delivers full-range audio.
Engineering Solution
One core runs the hybrid ANC filter continuously (FF/FB adaptive filters updated at 48kHz). The second core performs environmental classification using a TinyML CNN on 1-second audio windows from the feed-forward mics. Classified environments trigger smooth ANC/EQ transitions using 200ms cross-fade ramps.
Result
45dB maximum ANC depth, 92% environment classification accuracy. Zero audible artifacts during mode transitions.
Deep Tech FAQ
What makes the AI Smart Earbuds based on BES2600 unique?+
The AI Smart Earbuds based on BES2600 leverages custom hardware and edge AI to deliver industry-leading performance and efficiency.
What are the core technical benefits?+
Key benefits include low power consumption, real-time processing, robust connectivity, and a compact form factor tailored for deployment.
Can this architecture be adapted for other use cases?+
Absolutely. The underlying methodology is modular and can be retargeted for various applications with minimal redesign.
Project Profile
Services Delivered
Hardware DesignEmbedded Software
Core Technologies
BLETinyMLRTOS
Silicon & Vendors
BestechnicKnowles
Need similar outcomes?
Let's discuss how ChipTalk can deliver results for your next project.
Tell us about your project.
Fast Response — Initial feedback within 48 hours
Full R&D Lifecycle — From feasibility to mass production
Extensive Experience — 500+ projects across 15 verticals
Rapid MVP Validation — Prototype in as fast as 12 weeks
Portfolio
