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

02/18/2016
by   Gil Keren, et al.
0

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.

READ FULL TEXT
research
03/07/2017

Convolutional Recurrent Neural Networks for Bird Audio Detection

Bird sounds possess distinctive spectral structure which may exhibit sma...
research
05/05/2021

Improved feature extraction for CRNN-based multiple sound source localization

In this work, we propose to extend a state-of-the-art multi-source local...
research
09/29/2022

ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition

The recurrent neural network transducer (RNN-T) is a prominent streaming...
research
03/21/2018

Comparing Fixed and Adaptive Computation Time for Recurrent Neural Networks

Adaptive Computation Time for Recurrent Neural Networks (ACT) is one of ...
research
04/11/2021

GR-RNN: Global-Context Residual Recurrent Neural Networks for Writer Identification

This paper presents an end-to-end neural network system to identify writ...
research
11/13/2019

Vehicle Re-identification: exploring feature fusion using multi-stream convolutional networks

This work addresses the problem of vehicle re-identification through a n...

Please sign up or login with your details

Forgot password? Click here to reset