AES E-Library

← Back to search

1D Convolutional Layers to Create Frequency-Based Spectral Features for Audio Networks

Time-Frequency transformation and spectral representations of audio signals are commonly used in various machine learning applications. Training networks on frequency features such as the Mel-Spectrogram or Chromagram have been proven more effective and convenient than training on time samples. In practical realizations, these features are created on a different processor and/or pre-computed and stored on disk, requiring additional efforts and making it difficult to experiment with various combinations. In this paper, we provide a PyTorch framework for creating spectral features and time-frequency transformation using the built-in trainable conv1d() layer. This allows computing these on-the-fly as part of a larger network and enabling easier experimentation with various parameters. Our work extends the work in the literature developed for that end: First by adding more of these features; and also by allowing the possibility of either training from initialized kernels or training from random values and converging to the desired solution. The code is written as a template of classes and scripts that users may integrate into their own PyTorch classes for various applications.

 

Author (s):
Affiliation: (See document for exact affiliation information.)
AES Convention: Paper Number:
Publication Date:
Session subject:
Permalink: https://aes2.org/publications/elibrary-page/?id=21940


(1039KB)


Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.

Type:
E-Libary location:
16938
Choose your country of residence from this list:










Skip to content