Event-Driven Continuous-Time Feature Extraction for Ultra Low-Power Audio Keyword Spotting - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Event-Driven Continuous-Time Feature Extraction for Ultra Low-Power Audio Keyword Spotting

Résumé

In the context of autonomous keyword spotting and sound detection, this paper proposes a low power feature extraction unit generating spectrograms that represent a unique signature allowing the classification of audio signals. This system is composed of a continuous-Time digital signal processing feature extractor combined with a convolutional neural network engine. The study evaluates the hardware requirements to implement the feature extraction unit using an advanced CMOS process. Furthermore, a simulation of the complete system using Matlab® reveals that the recognition accuracy remains higher than 90% while offering a power consumption 4000X lower than a conventional discrete time system.
Fichier principal
Vignette du fichier
Event-Driven Continuous-Time Feature Extraction for Ultra Low-Power Audio Keyword Spotting_accepted.pdf (569.65 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03362267 , version 1 (17-12-2021)

Identifiants

Citer

S. Mourrane, Benoit Larras, A. Cathelin, Antoine Frappé. Event-Driven Continuous-Time Feature Extraction for Ultra Low-Power Audio Keyword Spotting. 3rd IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2021, Jun 2021, Washington DC, DC, United States. pp.9458425, ⟨10.1109/AICAS51828.2021.9458425⟩. ⟨hal-03362267⟩
40 Consultations
91 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More