Deep Learning based Bird Audio Detection
Keywords:
Audio processing, Audio scene analysis, Audio event detection, Bird audio detection, Deep learning, Tensorflow, Audio features.Abstract
Audio event detection (AED) is defined as analyzing a continuous acoustic signal in order to extract the sound events present in the acoustic scene. Sound events are best labels for an auditory scene, because they help in describing and understanding a recognizable event present in the sound. In this work, Bird audio detection is carried out to determine whether birds sound is present in the given environmental audio. The system is designed with machine learning algorithm using Tensorflow. The proposed model learns spectrogram features from audio and predicts the presence of bird sounds with an accuracy of 80.76%.
References
[1] Thomas Pellegrini “Densely Connected CNNs for Bird Audio Detection” 25th European Signal Processing Conference (EUSIPCO), 2017.
[2] R. T. Buxton and I. L. Jones, “Measuring nocturnal seabird activity and status using acoustic recording devices: applications for island restoration,” Journal of Field Ornithology, vol. 83, no. 1, pp. 47–60, 2012.
[3] T. A. Marques, L. Thomas, S. W. Martin, D. K. Mellinger, J. A. Ward, D. J. Moretti, D. Harris, and P. L. Tyack, “Estimating animal population density using passive acoustics,” Biological Reviews, vol. 88, no. 2, pp. 287–309, 2013.
[4] E. C. ak?r, G. Parascandolo, T. Heittola, H. Huttunen, and T. Virtanen, “Convolutional recurrent neural networks for polyphonic sound event detection,” in IEEE/ACM TASLP Special Issue on Sound Scene and Event Analysis, 2017
[5] E. Sprengel, Y. Martin Jaggi, and T. Hofmann, “Audio based bird species identification using deep learning techniques,” Working notes of CLEF, 2016.
[6] G. Huang, Z. Liu, K. Q. Weinberger, and L. van der Maaten, “Densely connected convolutional networks,” arXiv preprint arXiv:1608.06993, 2016.
[7] Sharath Adavanne, Konstantinos Drossos, Emre Cak?r, Tuomas Virtanen “Stacked Convolutional and Recurrent Neural Networks for Bird Audio Detection” 25th European Signal Processing Conference (EUSIPCO), 2017
[8] Emre Cakir, Sharath Adavanne, Giambattista Parascandolo, Konstantinos Drossos and Tuomas Virtanen “Convolutional Recurrent Neural Networks for Bird Audio Detection” 25th European Signal Processing Conference (EUSIPCO), 2017
[9] Qiuqiang Kong, Yong Xu, Mark D. Plumbley “Joint Detection and Classification Convolutional Neural Network on Weakly Labelled Bird Audio Detection” 25th European Signal Processing Conference (EUSIPCO), 2017
[10] Anshul Thakur, R. Jyothi, Padmanabhan Rajan, A.D. Dileep “Rapid Bird Activity Detection Using Probabilistic Sequence Kernels” 25th European Signal Processing Conference (EUSIPCO), 2017
[11] Thomas Grill and Jan Schlüter “Two Convolutional Neural Networks for Bird Detection in Audio Signals” 25th European Signal Processing Conference (EUSIPCO), 2017
[12] Dan Stowell, Mike Wood, Yannis Stylianou and Herve Glotin “Bird Detection In Audio: A Survey and a Challenge” IEEE International Workshop On Machine Learning For Signal Processing, Salerno, Italy, Sept. 13–16, 2016
Downloads
Published
Issue
Section
License
Copyright (c) IJSRSET
This work is licensed under a Creative Commons Attribution 4.0 International License.