Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR.
To solve the problem of inaccurate recognition of types of communication signal modulation, a RNN neural network recognition algorithm combining residual block network with attention mechanism is proposed.
In addition, the proposed method has other preferred properties such as special advantages in dealing with highly imbalanced data, and it pioneers the research on the regularization for dynamic ensemble methods.
The key idea is that, in addition to the conventional attention mechanism, information of layers prior to feature extraction and LSTM are introduced into attention weights calculations.
Ranked #4 on Keyword Spotting on Google Speech Commands (Google Speech Commands V2 20 metric)
Furthermore, to compute quantization results with a given amount of values/clusters, this paper designed an iterative method and a clustering-based method, and both of them are built on sparse least square.