Adaptive DCTNet for audio signal classification

Yin Xian; Yunchen Pu; Zhe Gan; Liang Lu; Andrew Thompson

doi:10.1109/icassp.2017.7952907

Adaptive DCTNet for audio signal classification

Yin Xian, Yunchen Pu, Zhe Gan, Liang Lu, Andrew Thompson

School of Continuing Education

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

4 Citations (Scopus)

Abstract

In this paper, we investigate DCTNet for audio signal classification. Its output feature is related to Cohen's class of time-frequency distributions. We introduce the use of adaptive DCTNet (A-DCTNet) for audio signals feature extraction. The A-DCTNet applies the idea of constant-Q transform, with its center frequencies of filterbanks geometrically spaced. The A-DCTNet is adaptive to different acoustic scales, and it can better capture low frequency acoustic information that is sensitive to human audio perception than features such as Mel-frequency spectral coefficients (MFSC). We use features extracted by the A-DCTNet as input for classifiers. Experimental results show that the A-DCTNet and Recurrent Neural Networks (RNN) achieve state-of-the-art performance in bird song classification rate, and improve artist identification accuracy in music data. They demonstrate A-DCTNet's applicability to signal processing problems.

Original language	English
Title of host publication	2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	IEEE
Pages	3999-4003
Number of pages	5
ISBN (Electronic)	9781509041176, 9781509041169
ISBN (Print)	9781509041183
DOIs	https://doi.org/10.1109/icassp.2017.7952907
Publication status	Published - Mar 2017
Event	2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017 - New Orleans, LA, United States Duration: 5 Mar 2017 → 9 Mar 2017 https://ieeexplore.ieee.org/xpl/conhome/7943262/proceeding

Publication series

Name	International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
ISSN (Electronic)	2379-190X

Conference

Conference	2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017
Country/Territory	United States
City	New Orleans, LA
Period	5/03/17 → 9/03/17
Internet address	https://ieeexplore.ieee.org/xpl/conhome/7943262/proceeding

User-Defined Keywords

Adaptive DCTNet
audio signals
time-frequency analysis
RNN
feature extraction

Access to Document

10.1109/icassp.2017.7952907

Cite this

@inproceedings{152c45f67e854e6fab7a678a8d0e7db0,

title = "Adaptive DCTNet for audio signal classification",

abstract = "In this paper, we investigate DCTNet for audio signal classification. Its output feature is related to Cohen's class of time-frequency distributions. We introduce the use of adaptive DCTNet (A-DCTNet) for audio signals feature extraction. The A-DCTNet applies the idea of constant-Q transform, with its center frequencies of filterbanks geometrically spaced. The A-DCTNet is adaptive to different acoustic scales, and it can better capture low frequency acoustic information that is sensitive to human audio perception than features such as Mel-frequency spectral coefficients (MFSC). We use features extracted by the A-DCTNet as input for classifiers. Experimental results show that the A-DCTNet and Recurrent Neural Networks (RNN) achieve state-of-the-art performance in bird song classification rate, and improve artist identification accuracy in music data. They demonstrate A-DCTNet's applicability to signal processing problems.",

keywords = "Adaptive DCTNet, audio signals, time-frequency analysis, RNN, feature extraction",

author = "Yin Xian and Yunchen Pu and Zhe Gan and Liang Lu and Andrew Thompson",

year = "2017",

month = mar,

doi = "10.1109/icassp.2017.7952907",

language = "English",

isbn = "9781509041183",

series = "International Conference on Acoustics, Speech, and Signal Processing (ICASSP) ",

publisher = "IEEE",

pages = "3999--4003",

booktitle = "2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

address = "United States",

note = "2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017 ; Conference date: 05-03-2017 Through 09-03-2017",

url = "https://ieeexplore.ieee.org/xpl/conhome/7943262/proceeding",

}

Xian, Y, Pu, Y, Gan, Z, Lu, L & Thompson, A 2017, Adaptive DCTNet for audio signal classification. in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). International Conference on Acoustics, Speech, and Signal Processing (ICASSP) , IEEE, pp. 3999-4003, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017, New Orleans, LA, United States, 5/03/17. https://doi.org/10.1109/icassp.2017.7952907

Adaptive DCTNet for audio signal classification. / Xian, Yin; Pu, Yunchen; Gan, Zhe et al.
2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2017. p. 3999-4003 (International Conference on Acoustics, Speech, and Signal Processing (ICASSP) ).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Adaptive DCTNet for audio signal classification

AU - Xian, Yin

AU - Pu, Yunchen

AU - Gan, Zhe

AU - Lu, Liang

AU - Thompson, Andrew

PY - 2017/3

Y1 - 2017/3

N2 - In this paper, we investigate DCTNet for audio signal classification. Its output feature is related to Cohen's class of time-frequency distributions. We introduce the use of adaptive DCTNet (A-DCTNet) for audio signals feature extraction. The A-DCTNet applies the idea of constant-Q transform, with its center frequencies of filterbanks geometrically spaced. The A-DCTNet is adaptive to different acoustic scales, and it can better capture low frequency acoustic information that is sensitive to human audio perception than features such as Mel-frequency spectral coefficients (MFSC). We use features extracted by the A-DCTNet as input for classifiers. Experimental results show that the A-DCTNet and Recurrent Neural Networks (RNN) achieve state-of-the-art performance in bird song classification rate, and improve artist identification accuracy in music data. They demonstrate A-DCTNet's applicability to signal processing problems.

AB - In this paper, we investigate DCTNet for audio signal classification. Its output feature is related to Cohen's class of time-frequency distributions. We introduce the use of adaptive DCTNet (A-DCTNet) for audio signals feature extraction. The A-DCTNet applies the idea of constant-Q transform, with its center frequencies of filterbanks geometrically spaced. The A-DCTNet is adaptive to different acoustic scales, and it can better capture low frequency acoustic information that is sensitive to human audio perception than features such as Mel-frequency spectral coefficients (MFSC). We use features extracted by the A-DCTNet as input for classifiers. Experimental results show that the A-DCTNet and Recurrent Neural Networks (RNN) achieve state-of-the-art performance in bird song classification rate, and improve artist identification accuracy in music data. They demonstrate A-DCTNet's applicability to signal processing problems.

KW - Adaptive DCTNet

KW - audio signals

KW - time-frequency analysis

KW - RNN

KW - feature extraction

U2 - 10.1109/icassp.2017.7952907

DO - 10.1109/icassp.2017.7952907

M3 - Conference proceeding

SN - 9781509041183

T3 - International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

SP - 3999

EP - 4003

BT - 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

T2 - 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017

Y2 - 5 March 2017 through 9 March 2017

ER -

Adaptive DCTNet for audio signal classification

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Fingerprint

Cite this