Browse by author
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.
In this paper, we propose to address the issue of the lack of strongly labeled data by using pseudo strongly labeled data that is approximated using Convolutive Nonnegative Matrix Factorization (CNMF). Using this pseudo strongly labeled data, we then train a new architecture combining Convolutional Neural Network (CNN) with Macaron Net (MN), which we term it as Convolutional Macaron Net (CMN). As opposed to the Mean-Teacher approach which trains two similar models synchronously, we propose to train two different CMNs synchronously where one of the models will provide the frame-level prediction while the other will provide the clip level prediction. Based on our proposed framework, our system outperforms the baseline system of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 Challenge Task 4 by a margin of over 10%. By comparing with the first place of the challenge which utilize a combination of CNN and Conformer, our system also marginally wins it by 0.3%.
Author(s): Chan TK, Chin CS
Publication type: Article
Publication status: Published
Journal: arXiv
Year: 2020
Volume: 2009.09632
Pages: 1-5
Print publication date: 21/09/2020
Online publication date: 21/09/2020
Acceptance date: 21/09/2020
Publisher: Cornell University
URL: https://arxiv.org/abs/2009.09632
