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

March 22, 2017 · Entered Twilight · 🏛 Interspeech

🌅 TWILIGHT: Old Age
Predates the code-sharing era — a pioneer of its time

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, GAS_presentation.pptx, README.md, decode.py, local_rnn, prepare_timit, rnn_autoencoder.py, run.sh, sh_tools, utils

Authors Yu-Hsuan Wang, Cheng-Tao Chung, Hung-yi Lee arXiv ID 1703.07588 Category cs.SD: Sound Cross-listed cs.CL, cs.LG Citations 40 Venue Interspeech Repository https://github.com/allyoushawn/timit_gas.git ⭐ 4 Last Checked 1 month ago
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.
Community shame:
Not yet rated
📄 View on arXiv 🌐 View on ar5iv 📑 PDF 💻 Repository 🎉 Report Code Found
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

📜 Similar Papers

In the same crypt — Sound