Event-Driven Continuous-Time Feature Extraction for Ultra Low-Power Audio Keyword Spotting | Mourrane, S.
/5

0 avis

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

Archive ouverte : Communication dans un congrès

Mourrane, S. | Larras, Benoit | Cathelin, A. | Frappé, Antoine

Edité par HAL CCSD ; Institute of Electrical and Electronics Engineers Inc.

International audience. 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.

Consulter en ligne

Suggestions

Du même auteur

Design techniques for very high speed digital delta-sigma modulators aimed at all-digital RE transmitters | Frappé, Antoine

Design techniques for very high speed digital delta-sigma modulators aimed ...

Archive ouverte: Communication dans un congrès

Frappé, Antoine | 2006-12-10

International audience. This paper presents a very high-speed delta-sigma modulator for achieving digital generation of radio-frequency signals. About 68 dB of ACLR (adjacent channel leakage ratio) is obtained on th...

Sampling modulation: An energy efficient novel feature extraction for biosignal processing | Causo, M.

Sampling modulation: An energy efficient novel feature extraction for biosi...

Archive ouverte: Communication dans un congrès

Causo, M. | 2016-10-17

International audience. Extracting useful information from human bio potentials is an essential component of many wearable health applications. Yet the feature extraction itself can be computationally demanding, and...

A 43pJ per Inference CBNN-based Compute-in-sensor Associative Memory in 28nm FDSOI | Larras, Benoit

A 43pJ per Inference CBNN-based Compute-in-sensor Associative Memory in 28n...

Archive ouverte: Communication dans un congrès

Larras, Benoit | 2021-09-13

International audience. Distributed smart sensors are more and more used in applications such as biomedical or domestic monitoring. However, each sensor broadcasts data wirelessly to the others or to an aggregator, ...

Du même sujet

EME-Net: A U-net-based Indoor EMF Exposure Map Reconstruction Method | Mallik, Mohammed

EME-Net: A U-net-based Indoor EMF Exposure Map Reconstruction Method

Archive ouverte: Communication dans un congrès

Mallik, Mohammed | 2022-03-27

International audience. In wireless communication systems, in order to respond to the perception of risks related to electromagnetic field exposure and allocate radio resources, the estimation of the received power ...

10. Incremental learning of convolutional neural networks in bioinformatics | Mousser, Wafa

10. Incremental learning of convolutional neural networks in bioinformatics

Archive ouverte: Type de document indéfini

Mousser, Wafa | 2022

International audience. In recent years, convolutional neural networks (CNNs) have been widely used in various computer visual recognition tasks and then extensively applied for medical images, particularly for comp...

9. Incremental deep learning model for plant leaf diseases detection | Ouadfel, Salima

9. Incremental deep learning model for plant leaf diseases detection

Archive ouverte: Type de document indéfini

Ouadfel, Salima | 2022-09-30

International audience. In recent years, deep learning has revolutionized machine learning and has been used with great success in various engineering fields, such as transportation, agriculture, finance, and market...

Keyword Spotting System using Low-complexity Feature Extraction and Quantized LSTM | Hérissé, Kévin

Keyword Spotting System using Low-complexity Feature Extraction and Quantiz...

Archive ouverte: Communication dans un congrès

Hérissé, Kévin | 2021-11-28

International audience. Long Short-Term Memory (LSTM) neural networks offer state-of-the-art results to compute sequential data and address applications like keyword spotting. Mel Frequency Cepstral Coefficients (MF...

Deep learning based face beauty prediction via dynamic robust losses and ensemble regression | Bougourzi, F.

Deep learning based face beauty prediction via dynamic robust losses and en...

Archive ouverte: Article de revue

Bougourzi, F. | 2022-04

International audience. In the last decade, several studies have shown that facial attractiveness can be learned by machines. In this paper, we address Facial Beauty Prediction from static images. The paper contains...

IDT: an incremental deep tree framework for biological image classification | Mousser, Wafa

IDT: an incremental deep tree framework for biological image classification

Archive ouverte: Article de revue

Mousser, Wafa | 2022-12

International audience. Nowadays, breast and cervical cancers are respectively the first and fourth most common causes of cancer death in females. It is believed that, automated systems based on artificial intellige...

Chargement des enrichissements...