Spectogram Prediction with Neural Networks

A neural network model for spectrogram magnitude prediction is presented. It has one convolutional layer that computes the shorttime Fourier transform. By choosing the magnitude of the spectrum as output and discarding the phase, it is possible to avoid complex number operations. The structure of th...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: García, Mario Alejandro, Destéfanis, Eduardo A.
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2018
Materias:
Ciencias Informáticas
discrete fourier transform
spectrogram
deep learning
convolutional neural network
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/73033
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-73033
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
discrete fourier transform
spectrogram
deep learning
convolutional neural network
spellingShingle Ciencias Informáticas
discrete fourier transform
spectrogram
deep learning
convolutional neural network
García, Mario Alejandro
Destéfanis, Eduardo A.
Spectogram Prediction with Neural Networks
topic_facet Ciencias Informáticas
discrete fourier transform
spectrogram
deep learning
convolutional neural network
description A neural network model for spectrogram magnitude prediction is presented. It has one convolutional layer that computes the shorttime Fourier transform. By choosing the magnitude of the spectrum as output and discarding the phase, it is possible to avoid complex number operations. The structure of the network and coefficients computation for this alternative are presented in detail. The model coefficients can be directly computed or trained with the gradient descent algorithm. In both cases, the results are satisfactory, but the obtained weights are different. An analysis of the differences is made. The main contribution of this article is to show that the proposed model is trainable. Consequently, the coefficients can be adapted to particular problems.
format Objeto de conferencia
Objeto de conferencia
author García, Mario Alejandro
Destéfanis, Eduardo A.
author_facet García, Mario Alejandro
Destéfanis, Eduardo A.
author_sort García, Mario Alejandro
title Spectogram Prediction with Neural Networks
title_short Spectogram Prediction with Neural Networks
title_full Spectogram Prediction with Neural Networks
title_fullStr Spectogram Prediction with Neural Networks
title_full_unstemmed Spectogram Prediction with Neural Networks
title_sort spectogram prediction with neural networks
publishDate 2018
url http://sedici.unlp.edu.ar/handle/10915/73033
work_keys_str_mv AT garciamarioalejandro spectogrampredictionwithneuralnetworks
AT destefaniseduardoa spectogrampredictionwithneuralnetworks
bdutipo_str Repositorios
_version_ 1764820483449028609

Ejemplares similares