Toggle Main Menu Toggle Search

Open Access padlockePrints

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

Lookup NU author(s): Teck CHAN, Professor Cheng Chin


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


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% vs. 23.7%, Validation Dataset: 31% vs. 25.8%). By comparing the validation results with other participants, the proposed system was ranked 8th among 19 teams (inclusive of the baseline system) in this year Task 4 challenge.

Publication metadata

Author(s): Chan TK, Chin CS, Li Y

Publication type: Article

Publication status: Published

Journal: arXiv

Year: 2020

Volume: 2001.07874

Pages: 1-6

Print publication date: 22/01/2020

Online publication date: 22/02/2020

Acceptance date: 22/01/2020

Publisher: Cornell University