Facultad Regional Córdoba

Permanent URI for this communityhttp://48.217.138.120/handle/20.500.12272/94

Browse

Has files: YesSubject: search.filters.subject.Deep learning

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Trainable windowing coefficients in DNN for raw audio classification
    (Cloud computing, big data y emerging topics, 2020) García , Mario Alejandro; Destefanis, Eduardo; Rosset, Ana Lorena
    An artificial neural network for audio classification is pro posed. This includes the windowing operation of raw audio and the calculation of the power spectrogram. A windowing layer is initialized with a hann window and its weights are adapted during training. The non-trainable weights of spectrogram calculation are initialized with the discrete Fourier transform coefficients. The tests are performed on the Speech Commands dataset. Results show that adapting the windowing coefficients produces a moderate accuracy improvement. It is concluded that the gradient of the error function can be propagated through the neural calculation of the power spectrum. It is also concluded that the training of the windowing layer improves the model’s ability to general iz
  • Thumbnail Image
    Item
    Power Cepstrum Calculation with Convolutional Neural Networks.
    (Journal of Computer Science y Technology., 2019) García, Mario Alejandro; Destefanis , Eduardo
    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 interme diate step. Although the proposed neural networks weights can be calculated in a direct way, it is nec essary 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.