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.

5 pages, The code is available at https://github.com/allyoushawn/timit_gas.git

References in corpus (1)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Cited by in corpus (7)

• Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks
• Unsupervised Automatic Speech Recognition: A Review
• Semi-Supervised Speech Recognition via Local Prior Matching
• Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only
• Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection
• Analysis Methods in Neural Language Processing: A Survey
• Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching