Sound classification using summary statistics and N-path filtering

Daniel Villamizar; Daniele Battaglino; Dante G. Muratore; Reza Hoshyar; Boris Murmann

doi:10.1109/ISCAS.2019.8702364

Sound classification using summary statistics and N-path filtering

Daniel Villamizar, Daniele Battaglino, Dante G. Muratore, Reza Hoshyar, Boris Murmann

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

6 Citations (Scopus)

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).

Original language	English
Title of host publication	2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings
Publisher	IEEE
ISBN (Electronic)	9781728103976
DOIs	https://doi.org/10.1109/ISCAS.2019.8702364
Publication status	Published - 2019
Externally published	Yes
Event	2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Sapporo, Japan Duration: 26 May 2019 → 29 May 2019

Publication series

Name	Proceedings - IEEE International Symposium on Circuits and Systems
Volume	2019-May
ISSN (Print)	0271-4310

Conference

Conference	2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019
Country/Territory	Japan
City	Sapporo
Period	26/05/19 → 29/05/19

Keywords

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

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ISCAS.2019.8702364

Cite this

Villamizar, D., Battaglino, D., Muratore, D. G., Hoshyar, R., & Murmann, B. (2019). Sound classification using summary statistics and N-path filtering. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings Article 8702364 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May). IEEE. https://doi.org/10.1109/ISCAS.2019.8702364

@inproceedings{cfb61e59d0a84c1ca80794e3248ebb9e,

title = "Sound classification using summary statistics and N-path filtering",

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).",

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

author = "Daniel Villamizar and Daniele Battaglino and Muratore, {Dante G.} and Reza Hoshyar and Boris Murmann",

year = "2019",

doi = "10.1109/ISCAS.2019.8702364",

language = "English",

series = "Proceedings - IEEE International Symposium on Circuits and Systems",

publisher = "IEEE",

booktitle = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings",

address = "United States",

note = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 ; Conference date: 26-05-2019 Through 29-05-2019",

}

Villamizar, D, Battaglino, D, Muratore, DG, Hoshyar, R & Murmann, B 2019, Sound classification using summary statistics and N-path filtering. in 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings., 8702364, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2019-May, IEEE, 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019, Sapporo, Japan, 26/05/19. https://doi.org/10.1109/ISCAS.2019.8702364

Sound classification using summary statistics and N-path filtering. / Villamizar, Daniel; Battaglino, Daniele; Muratore, Dante G. et al.
2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. IEEE, 2019. 8702364 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Sound classification using summary statistics and N-path filtering

AU - Villamizar, Daniel

AU - Battaglino, Daniele

AU - Muratore, Dante G.

AU - Hoshyar, Reza

AU - Murmann, Boris

PY - 2019

Y1 - 2019

N2 - 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).

AB - 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).

KW - Acoustic environment recognition

KW - Acoustic textures

KW - Baby cry detection

KW - Internet of Everything

KW - N-path filter

KW - Passive mixer

KW - Speaker identification

UR - http://www.scopus.com/inward/record.url?scp=85066809841&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2019.8702364

DO - 10.1109/ISCAS.2019.8702364

M3 - Conference contribution

AN - SCOPUS:85066809841

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings

PB - IEEE

T2 - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019

Y2 - 26 May 2019 through 29 May 2019

ER -

Sound classification using summary statistics and N-path filtering

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this