GitHub·Code

gentaiscool/lstm-attention

Attention-based bidirectional LSTM for Classification Task (ICASSP)

116 stars·Updated Sep 2025
attentionattention-mechanismclassificationemotion-recognitionkeraslstmstress-detectiontensorflow
Open on GitHub

Authors

Repository owner

Linked papers

Code

Attention-Based LSTM for Psychological Stress Detection from Spoken Language Using Distant Supervision

icassp · 2018

Why Lacuna links this resource
Repository names this paper

# LSTM with Attention by using Context Vector for Classification task The implementation of <a href="https://arxiv.org/abs/1805.12307">Attention-Based LSTM for Psychological Stress Detection from Spoken Language Using Distant Supervision</a> paper. The idea is to consider the importance of every word from the inputs and use it in the classification. Then the importance scores are normalized through the softmax layer. The weighted sum of the score and hidden states in every time-step is used for

README:focal_exact_title·Open evidence