Bird sounds classification by large scale acoustic features and extreme learning machine

Kun Qian; Zixing Zhang; Fabien Ringeval; Bjorn Schuller

doi:10.1109/GlobalSIP.2015.7418412

Bird sounds classification by large scale acoustic features and extreme learning machine

Kun Qian, Zixing Zhang, Fabien Ringeval, Bjorn Schuller

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

26 Citations (Scopus)

Abstract

Automatically classifying bird species by their sound signals is of crucial relevance for the research of ornithologists and ecologists. In this study, we present a novel framework for bird sounds classification from audio recordings. Firstly, the p-centre is used to detect the 'syllables' of bird songs, which are the units for the recognition task; then, we use our openSMILE toolkit to extract large scales of acoustic features from chunked units of analysis (the 'syllables'). ReliefF helps to reduce the dimension of the feature space. Lastly, an Extreme Learning Machine (ELM) serves for decision making. Results demonstrate that our system can achieve an excellent and robust performance scalable to different numbers of species (mean unweighted average recall of 93.82%, 89.56%, 85.30%, and 83.12% corresponding to 20, 30, 40, and 50 species of birds, respectively).

Original language	English
Title of host publication	2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1317-1321
Number of pages	5
ISBN (Electronic)	9781479975914
DOIs	https://doi.org/10.1109/GlobalSIP.2015.7418412
Publication status	Published - 23 Feb 2016
Externally published	Yes
Event	IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 - Orlando, United States Duration: 13 Dec 2015 → 16 Dec 2015

Publication series

Name	2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015

Conference

Conference	IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015
Country/Territory	United States
City	Orlando
Period	13/12/15 → 16/12/15

Keywords

Bird Sounds
Extreme Learning Machine
ReliefF
openSMILE
p-centre

Access to Document

10.1109/GlobalSIP.2015.7418412

Cite this

Qian, K., Zhang, Z., Ringeval, F., & Schuller, B. (2016). Bird sounds classification by large scale acoustic features and extreme learning machine. In 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 (pp. 1317-1321). Article 7418412 (2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobalSIP.2015.7418412

Qian, Kun ; Zhang, Zixing ; Ringeval, Fabien et al. / Bird sounds classification by large scale acoustic features and extreme learning machine. 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1317-1321 (2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015).

@inproceedings{a92527d02a4d4c8f890398682f5908fe,

title = "Bird sounds classification by large scale acoustic features and extreme learning machine",

abstract = "Automatically classifying bird species by their sound signals is of crucial relevance for the research of ornithologists and ecologists. In this study, we present a novel framework for bird sounds classification from audio recordings. Firstly, the p-centre is used to detect the 'syllables' of bird songs, which are the units for the recognition task; then, we use our openSMILE toolkit to extract large scales of acoustic features from chunked units of analysis (the 'syllables'). ReliefF helps to reduce the dimension of the feature space. Lastly, an Extreme Learning Machine (ELM) serves for decision making. Results demonstrate that our system can achieve an excellent and robust performance scalable to different numbers of species (mean unweighted average recall of 93.82%, 89.56%, 85.30%, and 83.12% corresponding to 20, 30, 40, and 50 species of birds, respectively).",

keywords = "Bird Sounds, Extreme Learning Machine, ReliefF, openSMILE, p-centre",

author = "Kun Qian and Zixing Zhang and Fabien Ringeval and Bjorn Schuller",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 ; Conference date: 13-12-2015 Through 16-12-2015",

year = "2016",

month = feb,

day = "23",

doi = "10.1109/GlobalSIP.2015.7418412",

language = "English",

series = "2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015",

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

pages = "1317--1321",

booktitle = "2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015",

address = "United States",

}

Qian, K, Zhang, Z, Ringeval, F & Schuller, B 2016, Bird sounds classification by large scale acoustic features and extreme learning machine. in 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015., 7418412, 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015, Institute of Electrical and Electronics Engineers Inc., pp. 1317-1321, IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015, Orlando, United States, 13/12/15. https://doi.org/10.1109/GlobalSIP.2015.7418412

Bird sounds classification by large scale acoustic features and extreme learning machine. / Qian, Kun; Zhang, Zixing; Ringeval, Fabien et al.
2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1317-1321 7418412 (2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015).

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

TY - GEN

T1 - Bird sounds classification by large scale acoustic features and extreme learning machine

AU - Qian, Kun

AU - Zhang, Zixing

AU - Ringeval, Fabien

AU - Schuller, Bjorn

PY - 2016/2/23

Y1 - 2016/2/23

N2 - Automatically classifying bird species by their sound signals is of crucial relevance for the research of ornithologists and ecologists. In this study, we present a novel framework for bird sounds classification from audio recordings. Firstly, the p-centre is used to detect the 'syllables' of bird songs, which are the units for the recognition task; then, we use our openSMILE toolkit to extract large scales of acoustic features from chunked units of analysis (the 'syllables'). ReliefF helps to reduce the dimension of the feature space. Lastly, an Extreme Learning Machine (ELM) serves for decision making. Results demonstrate that our system can achieve an excellent and robust performance scalable to different numbers of species (mean unweighted average recall of 93.82%, 89.56%, 85.30%, and 83.12% corresponding to 20, 30, 40, and 50 species of birds, respectively).

AB - Automatically classifying bird species by their sound signals is of crucial relevance for the research of ornithologists and ecologists. In this study, we present a novel framework for bird sounds classification from audio recordings. Firstly, the p-centre is used to detect the 'syllables' of bird songs, which are the units for the recognition task; then, we use our openSMILE toolkit to extract large scales of acoustic features from chunked units of analysis (the 'syllables'). ReliefF helps to reduce the dimension of the feature space. Lastly, an Extreme Learning Machine (ELM) serves for decision making. Results demonstrate that our system can achieve an excellent and robust performance scalable to different numbers of species (mean unweighted average recall of 93.82%, 89.56%, 85.30%, and 83.12% corresponding to 20, 30, 40, and 50 species of birds, respectively).

KW - Bird Sounds

KW - Extreme Learning Machine

KW - ReliefF

KW - openSMILE

KW - p-centre

UR - http://www.scopus.com/inward/record.url?scp=84964734785&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2015.7418412

DO - 10.1109/GlobalSIP.2015.7418412

M3 - Conference contribution

AN - SCOPUS:84964734785

T3 - 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015

SP - 1317

EP - 1321

BT - 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015

Y2 - 13 December 2015 through 16 December 2015

ER -

Qian K, Zhang Z, Ringeval F, Schuller B. Bird sounds classification by large scale acoustic features and extreme learning machine. In 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1317-1321. 7418412. (2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015). doi: 10.1109/GlobalSIP.2015.7418412

Bird sounds classification by large scale acoustic features and extreme learning machine

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this