Sound classification using summary statistics and N-path filtering

Conference paper (2019)

Authors

Daniel Villamizar NXP Semiconductors, Stanford University

Daniele Battaglino Texas Instruments

D.G. Muratore NXP Semiconductors, Stanford University, Mougins

Reza Hoshyar NXP Semiconductors, Stanford University

Boris Murmann Stanford University, NXP Semiconductors

Affiliation

External organisation

N-path filter Acoustic environment recognition Acoustic textures Baby cry detection Internet of Everything Passive mixer Speaker identification

To reference this document use:

http://resolver.tudelft.nl/uuid:cfb61e59-d0a8-4c1c-a807-94e3248ebb9e

More Info

expand_more

Published Date

2019

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Affiliation

External organisation

Abstract

Always-on sound classification is a desirable but power-intensive function for a variety of emerging Internet of Everything applications. This work explores the accuracy-complexity tradeoff by using summary statistics for classifying semi-stationary sounds. Compared to contemporary solutions including deep learning, this approach requires one to three orders of magnitude fewer parameters and can therefore be trained over ten times faster. We propose a mixed-signal design using N-path filters for feature extraction to further improve energy efficiency without incurring a large accuracy penalty for a binary classification task (less than 2.5% area reduction under receiver operating characteristic curve).