Litcius/Paper detail

An 800 nW Switched-Capacitor Feature Extraction Filterbank for Sound Classification

Daniel Augusto Villamizar, Dante G. Muratore, Jim Wieser, Boris Murmann

2021IEEE Transactions on Circuits and Systems I Regular Papers29 citationsDOI

Abstract

This paper presents a 32-channel analog filterbank for front-end signal processing in sound classification systems. It employs a passive N-path switched capacitor topology to achieve high power efficiency and reconfigurability. The circuit's unwanted harmonic mixing products are absorbed by the machine learning model during training. To enable a systematic pre-silicon study of this effect, we develop a computationally efficient circuit model that can process large machine learning datasets on practical time scales. Measured results using a 130 nm CMOS prototype IC indicate competitive classification accuracy on datasets for baby cry detection (93.7% AUC) and voice commands (92.4% average precision), while lowering the feature extraction energy compared to digital realizations by approximately 2× and 10×, respectively. The 1.44 mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> chip consumes 800 nW, which corresponds to the lowest normalized power per simultaneously sampled channel in recent literature.

Topics & Concepts

ReconfigurabilitySwitched capacitorComputer scienceFeature extractionCapacitorFilter bankSignal processingChannel (broadcasting)Electronic engineeringDigital signal processingTopology (electrical circuits)Artificial intelligencePattern recognition (psychology)Electrical engineeringComputer hardwareEngineeringTelecommunicationsVoltageSpeech and Audio ProcessingMusic and Audio ProcessingSpeech Recognition and Synthesis
An 800 nW Switched-Capacitor Feature Extraction Filterbank for Sound Classification | Litcius