# Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition

arXiv: https://arxiv.org/abs/1609.08789 · HTML: https://mlsanity.com/paper/1609.08789/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2016.

## Built on by (most cited first, 4 of 4)

- [Continuous Speech for Improved Learning Pathological Voice Disorders](https://mlsanity.com/paper/2202.10777/) (2022)
- [DeepGraviLens: a Multi-Modal Architecture for Classifying Gravitational Lensing Data](https://mlsanity.com/paper/2205.00701/) (2022)
- [2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos](https://mlsanity.com/paper/2409.07588/) (2024)
- [Multiway Multislice PHATE: Visualizing Hidden Dynamics of RNNs through Training](https://mlsanity.com/paper/2406.01969/) (2024)

## Abstract (arXiv)

Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU). However, the dynamic properties behind the remarkable performance remain unclear in many applications, e.g., automatic speech recognition (ASR). This paper employs visualization techniques to study the behavior of LSTM and GRU when performing speech recognition tasks. Our experiments show some interesting patterns in the gated memory, and some of them have inspired simple yet effective modifications on the network structure. We report two of such modifications: (1) lazy cell update in LSTM, and (2) shortcut connections for residual learning. Both modifications lead to more comprehensible and powerful networks.