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: |
| Sumario: | 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. |
|---|