Parallel capsule neural networks for sound event detection

Kai Wen Liang; Yu Hao Tseng; Pao Chi Chang

doi:10.1109/APSIPAASC47483.2019.9023176

Parallel capsule neural networks for sound event detection

Kai Wen Liang, Yu Hao Tseng, Pao Chi Chang

Department of Communication Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

In this work, we propose a sound event detection system based on a parallel capsule neural network. The system takes advantage of the capability of capsule neural networks in the detection of overlapping objects. It further develops a parallel architecture and uses the kernel design of different shapes and sizes to effectively utilize the feature information to increase the detection accuracy. The experimental results show that the performance of the proposed system is as low as 52.34% measured by the error rate, which is even lower than the rank 1 system in DCASE2017 challenge.

Original language	English
Title of host publication	2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1933-1936
Number of pages	4
ISBN (Electronic)	9781728132488
DOIs	https://doi.org/10.1109/APSIPAASC47483.2019.9023176
State	Published - Nov 2019
Event	2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019 - Lanzhou, China Duration: 18 Nov 2019 → 21 Nov 2019

Publication series

Name	2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019

Conference

Conference	2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
Country/Territory	China
City	Lanzhou
Period	18/11/19 → 21/11/19

Keywords

Capsule Neural Network
Computational Auditory Scene Analysis
Deep Learning
Sound Event Detection

Access to Document

10.1109/APSIPAASC47483.2019.9023176

Deep Intelligence Based Spoken Language Processing( II )
Wang, J.-C. (PI)
1/01/19 → 31/12/19
Project: Research
自駕車之深度學習智能感知與情境理解系統技術－自駕車之深度學習智能感知與情境理解系統技術-子計畫四
Chang, P.-C. (PI)
1/12/18 → 31/07/19
Project: Research

Cite this

Liang, K. W., Tseng, Y. H., & Chang, P. C. (2019). Parallel capsule neural networks for sound event detection. In 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019 (pp. 1933-1936). Article 9023176 (2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPAASC47483.2019.9023176

Liang, Kai Wen ; Tseng, Yu Hao ; Chang, Pao Chi. / Parallel capsule neural networks for sound event detection. 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1933-1936 (2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019).

@inproceedings{673643e695fe41d38c1af3d5c7b5aacf,

title = "Parallel capsule neural networks for sound event detection",

abstract = "In this work, we propose a sound event detection system based on a parallel capsule neural network. The system takes advantage of the capability of capsule neural networks in the detection of overlapping objects. It further develops a parallel architecture and uses the kernel design of different shapes and sizes to effectively utilize the feature information to increase the detection accuracy. The experimental results show that the performance of the proposed system is as low as 52.34% measured by the error rate, which is even lower than the rank 1 system in DCASE2017 challenge.",

keywords = "Capsule Neural Network, Computational Auditory Scene Analysis, Deep Learning, Sound Event Detection",

author = "Liang, {Kai Wen} and Tseng, {Yu Hao} and Chang, {Pao Chi}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019 ; Conference date: 18-11-2019 Through 21-11-2019",

year = "2019",

month = nov,

doi = "10.1109/APSIPAASC47483.2019.9023176",

language = "???core.languages.en_GB???",

series = "2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1933--1936",

booktitle = "2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019",

}

Liang, KW, Tseng, YH & Chang, PC 2019, Parallel capsule neural networks for sound event detection. in 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019., 9023176, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019, Institute of Electrical and Electronics Engineers Inc., pp. 1933-1936, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019, Lanzhou, China, 18/11/19. https://doi.org/10.1109/APSIPAASC47483.2019.9023176

Parallel capsule neural networks for sound event detection. / Liang, Kai Wen; Tseng, Yu Hao; Chang, Pao Chi.
2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1933-1936 9023176 (2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Parallel capsule neural networks for sound event detection

AU - Liang, Kai Wen

AU - Tseng, Yu Hao

AU - Chang, Pao Chi

PY - 2019/11

Y1 - 2019/11

N2 - In this work, we propose a sound event detection system based on a parallel capsule neural network. The system takes advantage of the capability of capsule neural networks in the detection of overlapping objects. It further develops a parallel architecture and uses the kernel design of different shapes and sizes to effectively utilize the feature information to increase the detection accuracy. The experimental results show that the performance of the proposed system is as low as 52.34% measured by the error rate, which is even lower than the rank 1 system in DCASE2017 challenge.

AB - In this work, we propose a sound event detection system based on a parallel capsule neural network. The system takes advantage of the capability of capsule neural networks in the detection of overlapping objects. It further develops a parallel architecture and uses the kernel design of different shapes and sizes to effectively utilize the feature information to increase the detection accuracy. The experimental results show that the performance of the proposed system is as low as 52.34% measured by the error rate, which is even lower than the rank 1 system in DCASE2017 challenge.

KW - Capsule Neural Network

KW - Computational Auditory Scene Analysis

KW - Deep Learning

KW - Sound Event Detection

UR - http://www.scopus.com/inward/record.url?scp=85082386879&partnerID=8YFLogxK

U2 - 10.1109/APSIPAASC47483.2019.9023176

DO - 10.1109/APSIPAASC47483.2019.9023176

M3 - 會議論文篇章

AN - SCOPUS:85082386879

T3 - 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019

SP - 1933

EP - 1936

BT - 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019

Y2 - 18 November 2019 through 21 November 2019

ER -

Liang KW, Tseng YH, Chang PC. Parallel capsule neural networks for sound event detection. In 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1933-1936. 9023176. (2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019). doi: 10.1109/APSIPAASC47483.2019.9023176

Parallel capsule neural networks for sound event detection

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

Deep Intelligence Based Spoken Language Processing( II )

自駕車之深度學習智能感知與情境理解系統技術－自駕車之深度學習智 能感知與情境理解系統技術-子計畫四

Cite this

自駕車之深度學習智能感知與情境理解系統技術－自駕車之深度學習智能感知與情境理解系統技術-子計畫四