Power Cepstrum Calculation with Convolutional Neural Networks : Cálculo del power cepstrum con redes neuronales convolucionales
A model of neural network with convolutional layers that calculates the power cepstrum of the input signal is proposed. To achieve it, the network calculates the discrete-time short-term Fourier transform internally, obtaining the spectrogram of the signal as an intermediate step. Although the propo...
Guardado en:
Autores principales: | , |
---|---|
Formato: | Articulo |
Lenguaje: | Inglés |
Publicado: |
2019
|
Materias: | |
Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/87765 |
Aporte de: |
id |
I19-R120-10915-87765 |
---|---|
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 Cepstrum Discrete Fourier transform Spectrogram Deep learning Convolutional neural network Transformada discreta de Fourier Espectrograma Aprendizaje profundo Red neuronal convolucional |
spellingShingle |
Ciencias Informáticas Cepstrum Discrete Fourier transform Spectrogram Deep learning Convolutional neural network Transformada discreta de Fourier Espectrograma Aprendizaje profundo Red neuronal convolucional García, Mario Alejandro Destéfanis, Eduardo Atilio Power Cepstrum Calculation with Convolutional Neural Networks : Cálculo del power cepstrum con redes neuronales convolucionales |
topic_facet |
Ciencias Informáticas Cepstrum Discrete Fourier transform Spectrogram Deep learning Convolutional neural network Transformada discreta de Fourier Espectrograma Aprendizaje profundo Red neuronal convolucional |
description |
A model of neural network with convolutional layers that calculates the power cepstrum of the input signal is proposed. To achieve it, the network calculates the discrete-time short-term Fourier transform internally, obtaining the spectrogram of the signal as an intermediate step. Although the proposed neural networks weights can be calculated in a direct way, it is necessary to determine if they can be obtained through training with the gradient descent method. In order to analyse the training behaviour, tests are made on the proposed model, as well as on two variants (power spectrum and autocovariance). Results show that the calculation model of power cepstrum cannot be trained, but the analysed variants in fact can. |
format |
Articulo Articulo |
author |
García, Mario Alejandro Destéfanis, Eduardo Atilio |
author_facet |
García, Mario Alejandro Destéfanis, Eduardo Atilio |
author_sort |
García, Mario Alejandro |
title |
Power Cepstrum Calculation with Convolutional Neural Networks : Cálculo del power cepstrum con redes neuronales convolucionales |
title_short |
Power Cepstrum Calculation with Convolutional Neural Networks : Cálculo del power cepstrum con redes neuronales convolucionales |
title_full |
Power Cepstrum Calculation with Convolutional Neural Networks : Cálculo del power cepstrum con redes neuronales convolucionales |
title_fullStr |
Power Cepstrum Calculation with Convolutional Neural Networks : Cálculo del power cepstrum con redes neuronales convolucionales |
title_full_unstemmed |
Power Cepstrum Calculation with Convolutional Neural Networks : Cálculo del power cepstrum con redes neuronales convolucionales |
title_sort |
power cepstrum calculation with convolutional neural networks : cálculo del power cepstrum con redes neuronales convolucionales |
publishDate |
2019 |
url |
http://sedici.unlp.edu.ar/handle/10915/87765 |
work_keys_str_mv |
AT garciamarioalejandro powercepstrumcalculationwithconvolutionalneuralnetworkscalculodelpowercepstrumconredesneuronalesconvolucionales AT destefaniseduardoatilio powercepstrumcalculationwithconvolutionalneuralnetworkscalculodelpowercepstrumconredesneuronalesconvolucionales |
bdutipo_str |
Repositorios |
_version_ |
1764820489374531585 |