Fig. 2From: Multi-rate modulation encoding via unsupervised learning for audio event detectionBlock diagram detailing the proposed method. a ModVAE pipeline. Parameters and models indicated with blue boxes are trainable via backpropagation. Models in green boxes are computed as an exponential moving average of the corresponding learned parameters (blue boxes). b AED system pipeline. Outputs of 3 different encoders are concatenated and passed through a BiGRU and a fully connected layer to produce event posteriorsBack to article page