Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-supervised Sound Event Detection

03/11/2021
by   Janek Ebbers, et al.
0

In this paper we present our system for the detection and classification of acoustic scenes and events (DCASE) 2020 Challenge Task 4: Sound event detection and separation in domestic environments. We introduce two new models: the forward-backward convolutional recurrent neural network (FBCRNN) and the tag-conditioned convolutional neural network (CNN). The FBCRNN employs two recurrent neural network (RNN) classifiers sharing the same CNN for preprocessing. With one RNN processing a recording in forward direction and the other in backward direction, the two networks are trained to jointly predict audio tags, i.e., weak labels, at each time step within a recording, given that at each time step they have jointly processed the whole recording. The proposed training encourages the classifiers to tag events as soon as possible. Therefore, after training, the networks can be applied to shorter audio segments of, e.g., 200 ms, allowing sound event detection (SED). Further, we propose a tag-conditioned CNN to complement SED. It is trained to predict strong labels while using (predicted) tags, i.e., weak labels, as additional input. For training pseudo strong labels from a FBCRNN ensemble are used. The presented system scored the fourth and third place in the systems and teams rankings, respectively. Subsequent improvements allow our system to even outperform the challenge baseline and winner systems in average by, respectively, 18.0 code is publicly available at https://github.com/fgnt/pb_sed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/09/2017

Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network

This paper proposes a neural network architecture and training scheme to...
research
09/02/2017

Surrey-cvssp system for DCASE2017 challenge task4

In this technique report, we present a bunch of methods for the task 4 o...
research
12/10/2019

Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization

Sound event detection (SED) is a task to detect sound events in an audio...
research
05/26/2023

Neural modeling of magnetic tape recorders

The sound of magnetic recording media, such as open-reel and cassette ta...
research
02/15/2018

Event Nugget Detection with Forward-Backward Recurrent Neural Networks

Traditional event detection methods heavily rely on manually engineered ...
research
07/30/2020

Weakly-Supervised Cell Tracking via Backward-and-Forward Propagation

We propose a weakly-supervised cell tracking method that can train a con...
research
07/19/2019

Language Modelling for Sound Event Detection with Teacher Forcing and Scheduled Sampling

A sound event detection (SED) method typically takes as an input a seque...

Please sign up or login with your details

Forgot password? Click here to reset