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.

De Salvio, D., Bianco, M.J., Gerstoft, P., D'Orazio, D., Garai, M. (2023). Blind source separation by long-term monitoring: A variational autoencoder to validate the clustering analysis. THE JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 153(1), 738-750 [10.1121/10.0016887].

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

De Salvio, Domenico
Primo
;
D'Orazio, Dario
Secondo
;
Garai, Massimo
Ultimo
2023

Abstract

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.
2023
De Salvio, D., Bianco, M.J., Gerstoft, P., D'Orazio, D., Garai, M. (2023). Blind source separation by long-term monitoring: A variational autoencoder to validate the clustering analysis. THE JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 153(1), 738-750 [10.1121/10.0016887].
De Salvio, Domenico; Bianco, Michael J; Gerstoft, Peter; D'Orazio, Dario; Garai, Massimo
File in questo prodotto:
File Dimensione Formato  
JASA_Sub_review_blind source_low.pdf

accesso aperto

Descrizione: AAM
Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 2.81 MB
Formato Adobe PDF
2.81 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/914596
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 2
social impact