Machine Learning for Audio Signals in Python
Jupyter Notebooks and Videos: Renato Profeta
Prof. Dr. -Ing. Gerald Schuller Applied Media Systems Group
Technische Universität Ilmenau
Content
- Introduction
- Neural Networks as Detectors
- Fully Connected Layer
- Activation Functions
- Optimizers
- Python PyTorch Examples
- Introduction
- Function Approximation
- PyTorch Example: Shallow Network
- Deep Function Approximator
- PyTorch Example: Deep Network
- Introduction
- MNIST Dataset
- PyTorch Model
- Cross Entropy Loss
- PyTorch Example
- Unknown Test Image
- Introduction
- One-Hot Encoding
- PyTorch Example
- Introduction
- A 1-D Signal Detector
- An Audio Predictor
- Introduction
- PyTorch Audio Convolutional Autoencoder
- Effects of Signal Shifts
- Introduction
- Experiment 1 with stride=512
- Experiment 2 with stride=32
- Introduction
- Posterior and Prior Distribution
- Kullback–Leibler Divergence
- Variational Loss
- Lagrange Multiplier
- Variational Autoencoder Experiments
- Introduction
- Infinite Impulse Response (IIR) Filter Structure
- IIR Python Implementation
- IIR Implementation using RNN in PyTorch
- Training the RNN
YouTube Playlist
Requirements
Please check the following files at the 'binder' folder:
- environment.yml
- postBuild
Note
Examples requiring a microphone will not work on remote environments such as Binder and Google Colab.