Spectrograms of baleen whale records synthesized from Autoenconder architectures: CAE, VAE and CAE-LSTM

• Published in: Elektron
• Main Authors: María Celeste Cabedio, Marco Carnaghi
• Format: Article in Journal/Newspaper
• Language: English; Spanish; Portuguese
• Published: Universidad de Buenos Aires 2022
• Subjects: autoencoders convolucionales; capas recursivas; espectrogramas; sonidos subcuáticos; síntesis; Electrical engineering. Electronics. Nuclear engineering; TK1-9971; Computer engineering. Computer hardware; TK7885-7895; Vae; baleen whale; baleen whales
• Online Access: https://doi.org/10.37537/rev.elektron.6.2.167.2022; https://doaj.org/article/411901d32928472fb4a4ee344cbbe2d6

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.