Gate Activation Signal Analysis for Gated Recurrent Neural Networks and Its Correlation with Phoneme Boundaries
arXiv:1703.07588v242 citations
AI Analysis
This addresses phoneme segmentation for speech processing, but it is incremental as it applies an existing method to new data.
The paper analyzed gate activation signals in gated recurrent neural networks and found their temporal structure highly correlated with phoneme boundaries, achieving better results in phoneme segmentation experiments compared to standard approaches.
In this paper we analyze the gate activation signals inside the gated recurrent neural networks, and find the temporal structure of such signals is highly correlated with the phoneme boundaries. This correlation is further verified by a set of experiments for phoneme segmentation, in which better results compared to standard approaches were obtained.