PDF

A Resource-Efficient CNN-Based EEG Auditory Attention Decoding ASIC

Qier Ma, Richard George

2024eneegcnnasicauditorylow-power

Abstract

Language:

Following a target speaker in a noisy environment, commonly known as the cocktail party problem, remains particularly challenging for cochlear implant (CI) users. This study aims to address this issue by presenting a resource-efficient ASIC designed for real-time EEG-based auditory attention decoding. The methodology involves integrating a quantized CNN inference engine with a Pearson-correlation classifier, and employing streaming execution, on-chip buffering, and memory-efficient dataflow to optimize resource use without sacrificing performance. The architectures have been implemented in GF22FDX 22-nm CMOS technology, with a total die size of 2.09 mm2, where the CNN inference engine occupies just 0.076 mm2. Operating at a core voltage of 0.55 V, the design achieves a remarkably low power consumption of 0.4941 mW and a latency of 7.34 ms. Results indicate that this ASIC provides an energy-efficient platform for EEG-based auditory attention decoding, contributing significant advancements for hearing-assistance applications, especially for CI users who struggle in multi-speaker environments.

Download

Cite This Work

@article{f2b97a2e-e236-4748-9fdf-809e9e7d8cd4,
  title={A Resource-Efficient CNN-Based EEG Auditory Attention Decoding ASIC},
  author={Qier Ma and Richard George},
  year={2024},
  language={en}
}
TY  - JOUR
TI  - A Resource-Efficient CNN-Based EEG Auditory Attention Decoding ASIC
AU  - Qier Ma
AU  - Richard George
PY  - 2024
LA  - en
ER  -

Similar Items

Optimization of Integrated Steel Plant R

This paper addresses the challenge of assessing the feasibility of wind power plant projects at sites with insufficient or no local historic wind data

2025enPDF

Design for Recovery of Precious and Base

2026enPDF

Electrochemical techniques for a cleaner

Important advances in electrochemical engineering technology over the last three decades have fostered the development of a lternative methods to alle

2026enPDF

Environmental and Human Health Risks Ass

2026enPDF

The Recovery of Precious and Base Metals

Increasing volumes of waste printed circuit boards from obsolete electronic equipment posed escalating environmental risks and resource losses due to

2026enPDF

Treatment of manufacturing scrap TV boar

The leachability tests for manufacturing scrap TV boards (STVB) have indicated the release of metals beyond the limit levels with potential problems f

2026enPDF