Spectrograms of baleen whale records synthesized from Autoenconder architectures: CAE, VAE and CAE-LSTM
In this paper, different architectures of simple convolutional networks are analyzed to generate synthetic spectrograms corresponding to baleen whales. Simplicity in these models plays an important role in the implementations of these type of networks on embedded systems. In addition, the scarcity o...
Published in: | Elektron |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English Spanish Portuguese |
Published: |
Universidad de Buenos Aires
2022
|
Subjects: | |
Online Access: | https://doi.org/10.37537/rev.elektron.6.2.167.2022 https://doaj.org/article/411901d32928472fb4a4ee344cbbe2d6 |
id |
ftdoajarticles:oai:doaj.org/article:411901d32928472fb4a4ee344cbbe2d6 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:411901d32928472fb4a4ee344cbbe2d6 2023-05-15T15:36:55+02:00 Spectrograms of baleen whale records synthesized from Autoenconder architectures: CAE, VAE and CAE-LSTM María Celeste Cabedio Marco Carnaghi 2022-12-01T00:00:00Z https://doi.org/10.37537/rev.elektron.6.2.167.2022 https://doaj.org/article/411901d32928472fb4a4ee344cbbe2d6 EN ES PT eng spa por Universidad de Buenos Aires http://elektron.fi.uba.ar/index.php/elektron/article/view/167 https://doaj.org/toc/2525-0159 2525-0159 doi:10.37537/rev.elektron.6.2.167.2022 https://doaj.org/article/411901d32928472fb4a4ee344cbbe2d6 Revista Elektrón, Vol 6, Iss 2, Pp 129-134 (2022) autoencoders convolucionales capas recursivas espectrogramas sonidos subcuáticos síntesis Electrical engineering. Electronics. Nuclear engineering TK1-9971 Computer engineering. Computer hardware TK7885-7895 article 2022 ftdoajarticles https://doi.org/10.37537/rev.elektron.6.2.167.2022 2022-12-30T19:34:17Z In this paper, different architectures of simple convolutional networks are analyzed to generate synthetic spectrograms corresponding to baleen whales. Simplicity in these models plays an important role in the implementations of these type of networks on embedded systems. In addition, the scarcity of available data requires the generation of efficient models. With this aim in mind, simple Autoencoder architectures with a low number of as- sociated parameters are presented and trained in this paper. Then, adequate metrics are obtained and the corresponding comparison among the architecture alternatives is made. The obtained results show that the more straightforward architecture is, in turn, the most convenient. Finally, from these models, synthetic spectrograms are generated from few data samples are generated, employing a low complexity architecture and assuming a normal distribution of the latent space vectors from the training data. Article in Journal/Newspaper baleen whale baleen whales Directory of Open Access Journals: DOAJ Articles Vae ENVELOPE(27.945,27.945,70.829,70.829) Elektron 6 2 129 134 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English Spanish Portuguese |
topic |
autoencoders convolucionales capas recursivas espectrogramas sonidos subcuáticos síntesis Electrical engineering. Electronics. Nuclear engineering TK1-9971 Computer engineering. Computer hardware TK7885-7895 |
spellingShingle |
autoencoders convolucionales capas recursivas espectrogramas sonidos subcuáticos síntesis Electrical engineering. Electronics. Nuclear engineering TK1-9971 Computer engineering. Computer hardware TK7885-7895 María Celeste Cabedio Marco Carnaghi Spectrograms of baleen whale records synthesized from Autoenconder architectures: CAE, VAE and CAE-LSTM |
topic_facet |
autoencoders convolucionales capas recursivas espectrogramas sonidos subcuáticos síntesis Electrical engineering. Electronics. Nuclear engineering TK1-9971 Computer engineering. Computer hardware TK7885-7895 |
description |
In this paper, different architectures of simple convolutional networks are analyzed to generate synthetic spectrograms corresponding to baleen whales. Simplicity in these models plays an important role in the implementations of these type of networks on embedded systems. In addition, the scarcity of available data requires the generation of efficient models. With this aim in mind, simple Autoencoder architectures with a low number of as- sociated parameters are presented and trained in this paper. Then, adequate metrics are obtained and the corresponding comparison among the architecture alternatives is made. The obtained results show that the more straightforward architecture is, in turn, the most convenient. Finally, from these models, synthetic spectrograms are generated from few data samples are generated, employing a low complexity architecture and assuming a normal distribution of the latent space vectors from the training data. |
format |
Article in Journal/Newspaper |
author |
María Celeste Cabedio Marco Carnaghi |
author_facet |
María Celeste Cabedio Marco Carnaghi |
author_sort |
María Celeste Cabedio |
title |
Spectrograms of baleen whale records synthesized from Autoenconder architectures: CAE, VAE and CAE-LSTM |
title_short |
Spectrograms of baleen whale records synthesized from Autoenconder architectures: CAE, VAE and CAE-LSTM |
title_full |
Spectrograms of baleen whale records synthesized from Autoenconder architectures: CAE, VAE and CAE-LSTM |
title_fullStr |
Spectrograms of baleen whale records synthesized from Autoenconder architectures: CAE, VAE and CAE-LSTM |
title_full_unstemmed |
Spectrograms of baleen whale records synthesized from Autoenconder architectures: CAE, VAE and CAE-LSTM |
title_sort |
spectrograms of baleen whale records synthesized from autoenconder architectures: cae, vae and cae-lstm |
publisher |
Universidad de Buenos Aires |
publishDate |
2022 |
url |
https://doi.org/10.37537/rev.elektron.6.2.167.2022 https://doaj.org/article/411901d32928472fb4a4ee344cbbe2d6 |
long_lat |
ENVELOPE(27.945,27.945,70.829,70.829) |
geographic |
Vae |
geographic_facet |
Vae |
genre |
baleen whale baleen whales |
genre_facet |
baleen whale baleen whales |
op_source |
Revista Elektrón, Vol 6, Iss 2, Pp 129-134 (2022) |
op_relation |
http://elektron.fi.uba.ar/index.php/elektron/article/view/167 https://doaj.org/toc/2525-0159 2525-0159 doi:10.37537/rev.elektron.6.2.167.2022 https://doaj.org/article/411901d32928472fb4a4ee344cbbe2d6 |
op_doi |
https://doi.org/10.37537/rev.elektron.6.2.167.2022 |
container_title |
Elektron |
container_volume |
6 |
container_issue |
2 |
container_start_page |
129 |
op_container_end_page |
134 |
_version_ |
1766367351886839808 |