Comparing recurrent convolutional neural networks for large scale bird species classification

Abstract We present a deep learning approach towards the large-scale prediction and analysis of bird acoustics from 100 different bird species. We use spectrograms constructed on bird audio recordings from the Cornell Bird Challenge (CBC)2020 dataset, which includes recordings of multiple and potent...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gaurav Gupta, Meghana Kshirsagar, Ming Zhong, Shahrzad Gholami, Juan Lavista Ferres
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/b2a960d8cd544517a0d80697245c9575
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b2a960d8cd544517a0d80697245c9575
record_format	dspace
spelling	oai:doaj.org-article:b2a960d8cd544517a0d80697245c95752021-12-02T18:53:14ZComparing recurrent convolutional neural networks for large scale bird species classification10.1038/s41598-021-96446-w2045-2322https://doaj.org/article/b2a960d8cd544517a0d80697245c95752021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-96446-whttps://doaj.org/toc/2045-2322Abstract We present a deep learning approach towards the large-scale prediction and analysis of bird acoustics from 100 different bird species. We use spectrograms constructed on bird audio recordings from the Cornell Bird Challenge (CBC)2020 dataset, which includes recordings of multiple and potentially overlapping bird vocalizations with background noise. Our experiments show that a hybrid modeling approach that involves a Convolutional Neural Network (CNN) for learning the representation for a slice of the spectrogram, and a Recurrent Neural Network (RNN) for the temporal component to combine across time-points leads to the most accurate model on this dataset. We show results on a spectrum of models ranging from stand-alone CNNs to hybrid models of various types obtained by combining CNNs with other CNNs or RNNs of the following types: Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU), and Legendre Memory Units (LMU). The best performing model achieves an average accuracy of 67% over the 100 different bird species, with the highest accuracy of 90% for the bird species, Red crossbill. We further analyze the learned representations visually and find them to be intuitive, where we find that related bird species are clustered close together. We present a novel way to empirically interpret the representations learned by the LMU-based hybrid model which shows how memory channel patterns change over time with the changes seen in the spectrograms.Gaurav GuptaMeghana KshirsagarMing ZhongShahrzad GholamiJuan Lavista FerresNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Gaurav Gupta Meghana Kshirsagar Ming Zhong Shahrzad Gholami Juan Lavista Ferres Comparing recurrent convolutional neural networks for large scale bird species classification
description	Abstract We present a deep learning approach towards the large-scale prediction and analysis of bird acoustics from 100 different bird species. We use spectrograms constructed on bird audio recordings from the Cornell Bird Challenge (CBC)2020 dataset, which includes recordings of multiple and potentially overlapping bird vocalizations with background noise. Our experiments show that a hybrid modeling approach that involves a Convolutional Neural Network (CNN) for learning the representation for a slice of the spectrogram, and a Recurrent Neural Network (RNN) for the temporal component to combine across time-points leads to the most accurate model on this dataset. We show results on a spectrum of models ranging from stand-alone CNNs to hybrid models of various types obtained by combining CNNs with other CNNs or RNNs of the following types: Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU), and Legendre Memory Units (LMU). The best performing model achieves an average accuracy of 67% over the 100 different bird species, with the highest accuracy of 90% for the bird species, Red crossbill. We further analyze the learned representations visually and find them to be intuitive, where we find that related bird species are clustered close together. We present a novel way to empirically interpret the representations learned by the LMU-based hybrid model which shows how memory channel patterns change over time with the changes seen in the spectrograms.
format	article
author	Gaurav Gupta Meghana Kshirsagar Ming Zhong Shahrzad Gholami Juan Lavista Ferres
author_facet	Gaurav Gupta Meghana Kshirsagar Ming Zhong Shahrzad Gholami Juan Lavista Ferres
author_sort	Gaurav Gupta
title	Comparing recurrent convolutional neural networks for large scale bird species classification
title_short	Comparing recurrent convolutional neural networks for large scale bird species classification
title_full	Comparing recurrent convolutional neural networks for large scale bird species classification
title_fullStr	Comparing recurrent convolutional neural networks for large scale bird species classification
title_full_unstemmed	Comparing recurrent convolutional neural networks for large scale bird species classification
title_sort	comparing recurrent convolutional neural networks for large scale bird species classification
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/b2a960d8cd544517a0d80697245c9575
work_keys_str_mv	AT gauravgupta comparingrecurrentconvolutionalneuralnetworksforlargescalebirdspeciesclassification AT meghanakshirsagar comparingrecurrentconvolutionalneuralnetworksforlargescalebirdspeciesclassification AT mingzhong comparingrecurrentconvolutionalneuralnetworksforlargescalebirdspeciesclassification AT shahrzadgholami comparingrecurrentconvolutionalneuralnetworksforlargescalebirdspeciesclassification AT juanlavistaferres comparingrecurrentconvolutionalneuralnetworksforlargescalebirdspeciesclassification
_version_	1718377347533504512

Comparing recurrent convolutional neural networks for large scale bird species classification

Ejemplares similares