4.5 Article

Blind source separation by long-term monitoring: A variational autoencoder to validate the clustering analysis

期刊

JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA
卷 153, 期 1, 页码 738-750

出版社

ACOUSTICAL SOC AMER AMER INST PHYSICS
DOI: 10.1121/10.0016887

关键词

-

向作者/读者索取更多资源

Noise exposure affects people's comfort and well-being in various contexts, such as work or learning environments. To assess sound environments, it is crucial to be able to separate sound sources in real contexts. Long-term monitoring provides abundant data that can be analyzed using machine and deep learning algorithms.
Noise exposure influences the comfort and well-being of people in several contexts, such as work or learning environments. For instance, in offices, different kind of noises can increase or drop the employees' productivity. Thus, the ability of separating sound sources in real contexts plays a key role in assessing sound environments. Long-term monitoring provide large amounts of data that can be analyzed through machine and deep learning algorithms. Based on previous works, an entire working day was recorded through a sound level meter. Both sound pressure levels and the digital audio recording were collected. Then, a dual clustering analysis was carried out to separate the two main sound sources experienced by workers: traffic and speech noises. The first method exploited the occurrences of sound pressure levels via Gaussian mixture model and K-means clustering. The second analysis performed a semi-supervised deep clustering analyzing the latent space of a variational autoencoder. Results show that both approaches were able to separate the sound sources. Spectral matching and the latent space of the variational autoencoder validated the assumptions underlying the proposed clustering methods.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据