Gate Activation Signal Analysis for Gated Recurrent Neural Networks and its Correlation with Phoneme Boundaries

Yu-Hsuan Wang, Cheng-Tao Chung, Hung-Yi Lee


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.


 DOI: 10.21437/Interspeech.2017-877

Cite as: Wang, Y., Chung, C., Lee, H. (2017) Gate Activation Signal Analysis for Gated Recurrent Neural Networks and its Correlation with Phoneme Boundaries. Proc. Interspeech 2017, 3822-3826, DOI: 10.21437/Interspeech.2017-877.


@inproceedings{Wang2017,
  author={Yu-Hsuan Wang and Cheng-Tao Chung and Hung-Yi Lee},
  title={Gate Activation Signal Analysis for Gated Recurrent Neural Networks and its Correlation with Phoneme Boundaries},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={3822--3826},
  doi={10.21437/Interspeech.2017-877},
  url={http://dx.doi.org/10.21437/Interspeech.2017-877}
}