Sound Events Recognition and Retrieval Using Multi-Convolutional-Channel Sparse Coding Convolutional Neural Networks

Chien Yao Wang; Tzu Chiang Tai; Jia Ching Wang; Andri Santoso; Seksan Mathulaprangsan; Chin Chin Chiang; Chung Hsien Wu

doi:10.1109/TASLP.2020.2964959

Sound Events Recognition and Retrieval Using Multi-Convolutional-Channel Sparse Coding Convolutional Neural Networks

Chien Yao Wang, Tzu Chiang Tai, Jia Ching Wang, Andri Santoso, Seksan Mathulaprangsan, Chin Chin Chiang, Chung Hsien Wu

Department of Computer Science and Information Engineering

Research output: Contribution to journal › Article › peer-review

15 Citations (Scopus)

Abstract

This article proposes two novel deep convolutional neural networks (CNN), which are called the sparse coding convolutional neural network (SC-CNN) and the multi-convolutional-channel SC-CNN (MSC-CNN), to address the sound event recognition and retrieval problem. Unlike the general framework of a CNN, in which the feature learning process is performed hierarchically, the proposed framework models the whole memorization process in the human brain, including encoding, storage, and recollection. In particular, the MSC-CNN is designed to recognize multiple sound events that occur simultaneously. The experimental results indicate that the proposed SC-CNN and MSC-CNN outperforms the state-of-the-art systems in sound event recognition and retrieval.

Original language	English
Article number	8952659
Pages (from-to)	1875-1887
Number of pages	13
Journal	IEEE/ACM Transactions on Audio Speech and Language Processing
Volume	28
DOIs	https://doi.org/10.1109/TASLP.2020.2964959
Publication status	Published - 2020

All Science Journal Classification (ASJC) codes

Computer Science (miscellaneous)
Acoustics and Ultrasonics
Computational Mathematics
Electrical and Electronic Engineering

Access to Document

10.1109/TASLP.2020.2964959

Cite this

@article{b59ea94e77b94118869bf2ee01ca3705,

title = "Sound Events Recognition and Retrieval Using Multi-Convolutional-Channel Sparse Coding Convolutional Neural Networks",

abstract = "This article proposes two novel deep convolutional neural networks (CNN), which are called the sparse coding convolutional neural network (SC-CNN) and the multi-convolutional-channel SC-CNN (MSC-CNN), to address the sound event recognition and retrieval problem. Unlike the general framework of a CNN, in which the feature learning process is performed hierarchically, the proposed framework models the whole memorization process in the human brain, including encoding, storage, and recollection. In particular, the MSC-CNN is designed to recognize multiple sound events that occur simultaneously. The experimental results indicate that the proposed SC-CNN and MSC-CNN outperforms the state-of-the-art systems in sound event recognition and retrieval.",

author = "Wang, {Chien Yao} and Tai, {Tzu Chiang} and Wang, {Jia Ching} and Andri Santoso and Seksan Mathulaprangsan and Chiang, {Chin Chin} and Wu, {Chung Hsien}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2020",

doi = "10.1109/TASLP.2020.2964959",

language = "English",

volume = "28",

pages = "1875--1887",

journal = "IEEE/ACM Transactions on Audio Speech and Language Processing",

issn = "2329-9290",

publisher = "IEEE Advancing Technology for Humanity",

}

TY - JOUR

T1 - Sound Events Recognition and Retrieval Using Multi-Convolutional-Channel Sparse Coding Convolutional Neural Networks

AU - Wang, Chien Yao

AU - Tai, Tzu Chiang

AU - Wang, Jia Ching

AU - Santoso, Andri

AU - Mathulaprangsan, Seksan

AU - Chiang, Chin Chin

AU - Wu, Chung Hsien

PY - 2020

Y1 - 2020

N2 - This article proposes two novel deep convolutional neural networks (CNN), which are called the sparse coding convolutional neural network (SC-CNN) and the multi-convolutional-channel SC-CNN (MSC-CNN), to address the sound event recognition and retrieval problem. Unlike the general framework of a CNN, in which the feature learning process is performed hierarchically, the proposed framework models the whole memorization process in the human brain, including encoding, storage, and recollection. In particular, the MSC-CNN is designed to recognize multiple sound events that occur simultaneously. The experimental results indicate that the proposed SC-CNN and MSC-CNN outperforms the state-of-the-art systems in sound event recognition and retrieval.

AB - This article proposes two novel deep convolutional neural networks (CNN), which are called the sparse coding convolutional neural network (SC-CNN) and the multi-convolutional-channel SC-CNN (MSC-CNN), to address the sound event recognition and retrieval problem. Unlike the general framework of a CNN, in which the feature learning process is performed hierarchically, the proposed framework models the whole memorization process in the human brain, including encoding, storage, and recollection. In particular, the MSC-CNN is designed to recognize multiple sound events that occur simultaneously. The experimental results indicate that the proposed SC-CNN and MSC-CNN outperforms the state-of-the-art systems in sound event recognition and retrieval.

UR - http://www.scopus.com/inward/record.url?scp=85087459713&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85087459713&partnerID=8YFLogxK

U2 - 10.1109/TASLP.2020.2964959

DO - 10.1109/TASLP.2020.2964959

M3 - Article

AN - SCOPUS:85087459713

SN - 2329-9290

VL - 28

SP - 1875

EP - 1887

JO - IEEE/ACM Transactions on Audio Speech and Language Processing

JF - IEEE/ACM Transactions on Audio Speech and Language Processing

M1 - 8952659

ER -

Sound Events Recognition and Retrieval Using Multi-Convolutional-Channel Sparse Coding Convolutional Neural Networks

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this