# Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data

arXiv: https://arxiv.org/abs/1602.05875 · HTML: https://mlsanity.com/paper/1602.05875/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2016.

## Built on by (most cited first, 17 of 17)

- [Speaker Normalization for Self-supervised Speech Emotion Recognition](https://mlsanity.com/paper/2202.01252/) (2022)
- [Improved Speech Emotion Recognition using Transfer Learning and Spectrogram Augmentation](https://mlsanity.com/paper/2108.02510/) (2021)
- [Speaker Attentive Speech Emotion Recognition](https://mlsanity.com/paper/2104.07288/) (2021)
- [Benchmarks for Physical Reasoning AI](https://mlsanity.com/paper/2312.10728/) (2023)
- [Multimodal Emotion Recognition using Transfer Learning from Speaker Recognition and BERT-based models](https://mlsanity.com/paper/2202.08974/) (2022)
- [Predictive Maintenance for General Aviation Using Convolutional Transformers](https://mlsanity.com/paper/2110.03757/) (2021)
- [Deep Learning Models for Flood Predictions in South Florida](https://mlsanity.com/paper/2306.15907/) (2023)
- [Stepping Forward on the Last Mile](https://mlsanity.com/paper/2411.04036/) (2024)
- [An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works](https://mlsanity.com/paper/2105.14278/) (2021)
- [Generative Plant Growth Simulation from Sequence-Informed Environmental Conditions](https://mlsanity.com/paper/2405.14796/) (2024)
- [Using Deep Learning Sequence Models to Identify SARS-CoV-2 Divergence](https://mlsanity.com/paper/2111.06593/) (2021)
- [Image Classification using Sequence of Pixels](https://mlsanity.com/paper/2209.11495/) (2022)
- [Speech and Text-Based Emotion Recognizer](https://mlsanity.com/paper/2312.11503/) (2023)
- [Towards Secure AI-driven Industrial Metaverse with NFT Digital Twins](https://mlsanity.com/paper/2412.15716/) (2024)
- [Benefits of Feature Extraction and Temporal Sequence Analysis for Video Frame Prediction: An Evaluation of Hybrid Deep Learning Models](https://mlsanity.com/paper/2508.00898/) (2025)
- [Improvement of Human-Object Interaction Action Recognition Using Scene Information and Multi-Task Learning Approach](https://mlsanity.com/paper/2509.09067/) (2025)
- [Efficient-Husformer: Efficient Multimodal Transformer Hyperparameter Optimization for Stress and Cognitive Loads](https://mlsanity.com/paper/2511.22362/) (2025)

## Abstract (arXiv)

Traditional convolutional layers extract features from patches of data by applying a non-linearity on an affine function of the input. We propose a model that enhances this feature extraction process for the case of sequential data, by feeding patches of the data into a recurrent neural network and using the outputs or hidden states of the recurrent units to compute the extracted features. By doing so, we exploit the fact that a window containing a few frames of the sequential data is a sequence itself and this additional structure might encapsulate valuable information. In addition, we allow for more steps of computation in the feature extraction process, which is potentially beneficial as an affine function followed by a non-linearity can result in too simple features. Using our convolutional recurrent layers we obtain an improvement in performance in two audio classification tasks, compared to traditional convolutional layers. Tensorflow code for the convolutional recurrent layers is publicly available in https://github.com/cruvadom/Convolutional-RNN.