2017
INTERSPEECH
INTERSPEECH 2017
Gate Activation Signal Analysis for Gated Recurrent Neural Networks and its Correlation with Phoneme Boundaries
Abstract
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.
π
Interdisciplinary Bridge
β Artificial Intelligence and Deep Learning
π
Trend Setter
β Interpretability
π§
Keyword Pioneer
β neural network interpretability
π
Cross-Pollinator
β Artificial Intelligence, Deep Learning, Machine Learning, Speech & Audio