Bidirectional Recurrent Neural Networks

Bidirectional GRU

A Bidirectional GRU, or BiGRU, is a sequence processing model that consists of two GRUs. one taking the input in a forward direction, and the other in a backwards direction. It is a bidirectional recurrent neural network with only the input and forget gates.

Image Source: Rana R (2016). Gated Recurrent Unit (GRU) for Emotion Classification from Noisy Speech.


Paper Code Results Date Stars


Task Papers Share
Speech Synthesis 41 25.79%
Text-To-Speech Synthesis 15 9.43%
Sentence 9 5.66%
General Classification 6 3.77%
Voice Cloning 5 3.14%
Classification 5 3.14%
Voice Conversion 4 2.52%
Speech Recognition 4 2.52%
Sentiment Analysis 3 1.89%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign