Bird call identification using Dynamic kernel based support vector machines and deep neural networks

Deep Chakraborty, Paawan Mukker, Padmanabhan Rajan, A. D. Dileep

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

In this paper, we apply speech and audio processing techniques to bird vocalizations and for the classification of birds found in the lower Himalayan regions. Mel frequency cepstral coefficients (MFCC) are extracted from each recording. As a result, the recordings are now represented as varying length sets of feature vectors. Dynamic kernel based support vector machines (SVMs) and deep neural networks (DNNs) are popularly used for the classification of such varying length patterns obtained from speech signals. In this work, we propose to use dynamic kernel based SVMs and DNNs for classification of bird calls represented as sets of feature vectors. Results of our studies show that both approaches give comparable performance.

Original languageEnglish
Title of host publicationProceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages280-285
Number of pages6
ISBN (Electronic)9781509061662
DOIs
Publication statusPublished - 31-01-2017
Externally publishedYes
Event15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016 - Anaheim, United States
Duration: 18-12-201620-12-2016

Conference

Conference15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016
CountryUnited States
CityAnaheim
Period18-12-1620-12-16

Fingerprint

Birds
Support vector machines
Processing
Deep neural networks

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Chakraborty, D., Mukker, P., Rajan, P., & Dileep, A. D. (2017). Bird call identification using Dynamic kernel based support vector machines and deep neural networks. In Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016 (pp. 280-285). [7838157] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2016.60
Chakraborty, Deep ; Mukker, Paawan ; Rajan, Padmanabhan ; Dileep, A. D. / Bird call identification using Dynamic kernel based support vector machines and deep neural networks. Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 280-285
@inproceedings{b20e5443bf1049398d22e3607fac514b,
title = "Bird call identification using Dynamic kernel based support vector machines and deep neural networks",
abstract = "In this paper, we apply speech and audio processing techniques to bird vocalizations and for the classification of birds found in the lower Himalayan regions. Mel frequency cepstral coefficients (MFCC) are extracted from each recording. As a result, the recordings are now represented as varying length sets of feature vectors. Dynamic kernel based support vector machines (SVMs) and deep neural networks (DNNs) are popularly used for the classification of such varying length patterns obtained from speech signals. In this work, we propose to use dynamic kernel based SVMs and DNNs for classification of bird calls represented as sets of feature vectors. Results of our studies show that both approaches give comparable performance.",
author = "Deep Chakraborty and Paawan Mukker and Padmanabhan Rajan and Dileep, {A. D.}",
year = "2017",
month = "1",
day = "31",
doi = "10.1109/ICMLA.2016.60",
language = "English",
pages = "280--285",
booktitle = "Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Chakraborty, D, Mukker, P, Rajan, P & Dileep, AD 2017, Bird call identification using Dynamic kernel based support vector machines and deep neural networks. in Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016., 7838157, Institute of Electrical and Electronics Engineers Inc., pp. 280-285, 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016, Anaheim, United States, 18-12-16. https://doi.org/10.1109/ICMLA.2016.60

Bird call identification using Dynamic kernel based support vector machines and deep neural networks. / Chakraborty, Deep; Mukker, Paawan; Rajan, Padmanabhan; Dileep, A. D.

Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 280-285 7838157.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Bird call identification using Dynamic kernel based support vector machines and deep neural networks

AU - Chakraborty, Deep

AU - Mukker, Paawan

AU - Rajan, Padmanabhan

AU - Dileep, A. D.

PY - 2017/1/31

Y1 - 2017/1/31

N2 - In this paper, we apply speech and audio processing techniques to bird vocalizations and for the classification of birds found in the lower Himalayan regions. Mel frequency cepstral coefficients (MFCC) are extracted from each recording. As a result, the recordings are now represented as varying length sets of feature vectors. Dynamic kernel based support vector machines (SVMs) and deep neural networks (DNNs) are popularly used for the classification of such varying length patterns obtained from speech signals. In this work, we propose to use dynamic kernel based SVMs and DNNs for classification of bird calls represented as sets of feature vectors. Results of our studies show that both approaches give comparable performance.

AB - In this paper, we apply speech and audio processing techniques to bird vocalizations and for the classification of birds found in the lower Himalayan regions. Mel frequency cepstral coefficients (MFCC) are extracted from each recording. As a result, the recordings are now represented as varying length sets of feature vectors. Dynamic kernel based support vector machines (SVMs) and deep neural networks (DNNs) are popularly used for the classification of such varying length patterns obtained from speech signals. In this work, we propose to use dynamic kernel based SVMs and DNNs for classification of bird calls represented as sets of feature vectors. Results of our studies show that both approaches give comparable performance.

UR - http://www.scopus.com/inward/record.url?scp=85015382677&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015382677&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2016.60

DO - 10.1109/ICMLA.2016.60

M3 - Conference contribution

SP - 280

EP - 285

BT - Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chakraborty D, Mukker P, Rajan P, Dileep AD. Bird call identification using Dynamic kernel based support vector machines and deep neural networks. In Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 280-285. 7838157 https://doi.org/10.1109/ICMLA.2016.60