当前位置: X-MOL 学术arXiv.cs.SD › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Training Sound Event Detection On A Heterogeneous Dataset
arXiv - CS - Sound Pub Date : 2020-07-08 , DOI: arxiv-2007.03931
Nicolas Turpault (MULTISPEECH), Romain Serizel (MULTISPEECH)

Training a sound event detection algorithm on a heterogeneous dataset including both recorded and synthetic soundscapes that can have various labeling granularity is a non-trivial task that can lead to systems requiring several technical choices. These technical choices are often passed from one system to another without being questioned. We propose to perform a detailed analysis of DCASE 2020 task 4 sound event detection baseline with regards to several aspects such as the type of data used for training, the parameters of the mean-teacher or the transformations applied while generating the synthetic soundscapes. Some of the parameters that are usually used as default are shown to be sub-optimal.

中文翻译:

在异构数据集上训练声音事件检测

在异构数据集上训练声音事件检测算法,包括可以具有各种标记粒度的录制和合成音景,这是一项非常重要的任务,可能导致系统需要多种技术选择。这些技术选择通常从一个系统传递到另一个系统而不会受到质疑。我们建议从几个方面对 DCASE 2020 任务 4 声音事件检测基线进行详细分析,例如用于训练的数据类型、平均教师的参数或在生成合成音景时应用的变换。通常用作默认值的一些参数显示为次优。
更新日期:2020-07-09
down
wechat
bug