论文标题
用于声音事件检测的非阴性基质分解 - 跨务神经网络（NMF-CNN）
Non-Negative Matrix Factorization-Convolutional Neural Network (NMF-CNN) For Sound Event Detection
论文作者
论文摘要
今年DCASE挑战的主要科学问题，任务4-在国内环境中的声音事件检测是，要研究达到最佳性能系统所需的数据类型（强烈标记的合成数据，弱标记的数据，在域数据中没有标记的数据）。在本文中，我们提出了一个深度学习模型，该模型将非负基质分解（NMF）与卷积神经网络（CNN）相结合。这种集成的关键思想是使用NMF为弱标记的数据提供近似强的标签。与基线系统相比，这种集成能够达到更高的基于事件的F1得分（评估数据集：30.39％vs. 23.7％，验证数据集：31％vs. 25.8％）。通过将验证结果与其他参与者进行比较，在今年任务4挑战中，提议的系统在19个团队（包括基线系统）中排名第八。
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.
