Emmanuel Hardy
YOU?
Author Swipe
View article: Comparison metrics and power trade-offs for BCI motor decoding circuit design
Comparison metrics and power trade-offs for BCI motor decoding circuit design Open
Brain signal decoders are increasingly being used in early clinical trials for rehabilitation and assistive applications such as motor control and speech decoding. As many Brain-Computer Interfaces (BCIs) need to be deployed in battery-pow…
View article: 17.8 0.4V 988nW Time-Domain Audio Feature Extraction for Keyword Spotting Using Injection-Locked Oscillators
17.8 0.4V 988nW Time-Domain Audio Feature Extraction for Keyword Spotting Using Injection-Locked Oscillators Open
International audience
View article: Hand Gesture Recognition Using Thin Plate Radiation and Gated-Recurrent-Unit, Based on Ultrasound Doppler
Hand Gesture Recognition Using Thin Plate Radiation and Gated-Recurrent-Unit, Based on Ultrasound Doppler Open
International audience
View article: Leveraging Sparsity with Spiking Recurrent Neural Networks for Energy-Efficient Keyword Spotting
Leveraging Sparsity with Spiking Recurrent Neural Networks for Energy-Efficient Keyword Spotting Open
International audience
View article: Spike-based Beamforming using pMUT Arrays for Ultra-Low Power Gesture Recognition
Spike-based Beamforming using pMUT Arrays for Ultra-Low Power Gesture Recognition Open
International audience
View article: Neuromorphic object localization using resistive memories and ultrasonic transducers
Neuromorphic object localization using resistive memories and ultrasonic transducers Open
Real-world sensory-processing applications require compact, low-latency, and low-power computing systems. Enabled by their in-memory event-driven computing abilities, hybrid memristive-Complementary Metal-Oxide Semiconductor neuromorphic a…
View article: Neuromorphic object localization using resistivememories and ultrasonic transducers
Neuromorphic object localization using resistivememories and ultrasonic transducers Open
Real-world sensory-processing applications require compact, low-latency, and low-power computing systems. Enabled by their in-memory event-driven computing abilities, hybrid memristive-CMOS neuromorphic architectures provide an ideal hardw…
View article: An Ultra-low Power RNN Classifier for Always-On Voice Wake-Up Detection Robust to Real-World Scenarios
An Ultra-low Power RNN Classifier for Always-On Voice Wake-Up Detection Robust to Real-World Scenarios Open
We present in this paper an ultra-low power (ULP) Recurrent Neural Network (RNN) based classifier for an always-on voice Wake-Up Sensor (WUS) with performances suitable for real-world applications. The purpose of our sensor is to bring dow…
View article: An Ultra-low Power RNN Classifier for Always-On Voice Wake-Up Detection\n Robust to Real-World Scenarios
An Ultra-low Power RNN Classifier for Always-On Voice Wake-Up Detection\n Robust to Real-World Scenarios Open
We present in this paper an ultra-low power (ULP) Recurrent Neural Network\n(RNN) based classifier for an always-on voice Wake-Up Sensor (WUS) with\nperformances suitable for real-world applications. The purpose of our sensor is\nto bring …