Non-Negative Matrix Factorization-Convolutional Neural Network (NMF-CNN) For Sound Event Detection

01/22/2020
by   Teck Kai Chan, et al.
0

The main scientific question of this year DCASE challenge, Task 4 - Sound Event Detection in Domestic Environments, is to investigate the types of data (strongly labeled synthetic data, weakly labeled data, unlabeled in domain data) required to achieve the best performing system. In this paper, we proposed a deep learning model that integrates Non-Negative Matrix Factorization (NMF) with Convolutional Neural Network (CNN). The key idea of such integration is to use NMF to provide an approximate strong label to the weakly labeled data. Such integration was able to achieve a higher event-based F1-score as compared to the baseline system (Evaluation Dataset: 30.39 23.7 with other participants, the proposed system was ranked 8th among 19 teams (inclusive of the baseline system) in this year Task 4 challenge.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/02/2020

Semi-Supervised NMF-CNN For Sound Event Detection

For the DCASE 2020 Challenge Task 4, this paper pro-posed a combinative ...
research
08/02/2018

DCASE 2018 Challenge Surrey Cross-Task convolutional neural network baseline

The Detection and Classification of Acoustic Scenes and Events (DCASE) c...
research
09/21/2020

Detecting Acoustic Events Using Convolutional Macaron Net

In this paper, we propose to address the issue of the lack of strongly l...
research
10/27/2016

Rapid Posterior Exploration in Bayesian Non-negative Matrix Factorization

Non-negative Matrix Factorization (NMF) is a popular tool for data explo...
research
09/07/2019

A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networks

The paper discusses a pooling mechanism to induce subsampling in graph s...
research
10/03/2022

Process Modeling, Hidden Markov Models, and Non-negative Tensor Factorization with Model Selection

Monitoring of industrial processes is a critical capability in industry ...
research
06/27/2020

Improving Interpretability of CNN Models Using Non-Negative Concept Activation Vectors

Convolutional neural network (CNN) models for computer vision are powerf...

Please sign up or login with your details

Forgot password? Click here to reset