This paper introduces a model of environmental acoustic scenes which adopts a morphological approach by ab-stracting temporal structures of acoustic scenes. To demonstrate its potential, this model is employed to evaluate the performance of a large set of acoustic events detection systems. This model allows us to explicitly control key morphological aspects of the acoustic scene and isolate their impact on the performance of the system under evaluation. Thus, more information can be gained on the behavior of evaluated systems, providing guidance for further improvements. The proposed model is validated using submitted systems from the IEEE DCASE Challenge; results indicate that the proposed scheme is able to successfully build datasets useful for evaluating some aspects the performance of event detection systems, more particularly their robustness to new listening conditions and the increasing level of background sounds.
Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling
Institute of Acoustics, CAS（中国科学院声学研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Xinjiang Technical Institute of Physics and Chemistry, CAS（中国科学院新疆理化技术研究所）
DynFOA: Generating First-Order Ambisonics with Conditional Diffusion for Dynamic and Acoustically Complex 360-Degree Videos
School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing, China（计算机与人工智能学院，北京技术与商业大学）；School of Computer Science, The University of Sydney, Sydney, NSW, Australia（计算机科学学院，悉尼大学）；School of Software, Shandong University, Jinan, China（软件学院，山东大学）
Acoustic Scene Classification Using Bilinear Pooling on Time-liked and Frequency-liked Convolution Neural Network
Xylem Inc（赛莱默公司）；Newcastle University（纽卡斯尔大学）
当前处理声学场景分类（ASC）任务的方法可以描述为两个步骤，将音频波形预处理成对数梅尔频谱图，然后将其用作卷积神经网络（CNN）的输入表示。这种范式转变发生在DCASE 2016之后，该框架模型在（ESC-50）数据集上实现了ASC任务的最新结果，并实现了64.5%的准确度，比基线模型提高了20.5%，DCASE 2016数据集的准确度为90.0%（开发）和86.2%（评估），分别比基线系统提高了6.4%和9%。本文探讨了利用谐波和谐波源分离（HPSS）将音频分离为谐波音频和谐波音频的方法，该方法在音乐信息检索（MIR）领域得到了广泛的应用。虽然已经在ASC任务中使用HPSS作为CNN模型的输入表示方面做了工作，但是本文进一步研究了通过策展2个CNN来利用分离的谐波分量和谐波分量的可能性，所述2个CNN试图以其自然形式理解谐波音频和谐波音频，一个专门用于在时间偏置域中提取深度特征，另一个专门用于在频率偏置域中提取深度特征，分别然后，从这2个CNN中提取的深度特征将使用双线性池进行组合。因此，提出了一种时频双流CNN结构的声学场景分类方法。该模型正在DCASE 2019子任务1a数据集上进行评估，并在开发数据集Kaggle Leadership Private and Public Board上平均得分为65%。
