Salta al menu principale di navigazione Salta al contenuto principale Salta al piè di pagina del sito
FrancoAngeli Journals

Articoli Scientifici

V. 48 N. 1 (2024)

Machine learning per la separazione e la misura di sorgenti sonore coesistenti in spazi chiusi

DOI
https://doi.org/10.3280/ria1-2024oa17373
Inviata
28 febbraio 2024
Pubblicato
22-07-2024

Abstract

La crescente potenza di calcolo e capacità di immagazzinamento dati della strumentazione acustica fa sì che si ponga sempre più attenzione verso i monitoraggi a lungo termine. Questa grande quantità di dati spiana la strada all’utilizzo di tecniche di machine learning. L’utilizzo di algoritmi sofisticati, principalmente basati su assunzioni statistiche, permette di ampliare le capacità di analisi dei tecnici acustici di contesti complessi. Il presente lavoro vuole proporre un metodo basato su tecniche di machine learning per separare, identificare e misurare diverse sorgenti sonore coesistenti in scenari reali monitorati tramite un fonometro. Sono presentati quattro casi studio in cui il metodo proposto è stato applicato. Due casi studio riguardano il monitoraggio di lezioni universitarie per separare il parlato dell'insegnante dal chiacchiericcio degli studenti. Questo permette di misurare il grado di attenzione degli studenti durante le lezioni. Altri due casi studio invece riguardano il monitoraggio di due uffici con più postazioni lavorative in cui sono state separate le sorgenti di rumore dal parlato dei lavoratori.

Riferimenti bibliografici (comprensivi di DOI)

  1. IEC 61672-1:2013 | IEC Webstore, (n.d.). https://webstore.iec.ch/publication/5708 (accessed February 20, 2024).
  2. H. Sato, J.S. Bradley, Evaluation of acoustical conditions for speech communication in working elementary school classrooms, The Journal of the Acoustical Society of America 123 (2008) 2064–2077. https://doi.org/10.1121/1.2839283.
  3. M. Hodgson, R. Rempel, S. Kennedy, Measurement and prediction of typical speech and background-noise levels in university classrooms during lectures, The Journal of the Acoustical Society of America 105 (1999) 226–233. https://doi.org/10.1121/1.424600.
  4. D. De Salvio, D. D’Orazio, Effectiveness of acoustic treatments and PA redesign by means of student activity and speech lev-els, Applied Acoustics 194 (2022) 108783. https://doi.org/10.1016/j.apacoust.2022.108783.
  5. K. Hummel, E. Ryherd, X. Cheng, B. Lowndes, Relating clustered noise data to hospital patient satisfaction, The Journal of the Acoustical Society of America 154 (2023) 1239–1247. https://doi.org/10.1121/10.0020760.
  6. D. De Salvio, D. D’Orazio, M. Garai, Unsupervised analysis of background noise sources in active offices, The Journal of the Acoustical Society of America 149 (2021) 4049–4060. https://doi.org/10.1121/10.0005129.
  7. D. De Salvio, M.J. Bianco, P. Gerstoft, D. D’Orazio, M. Garai, Blind source separation by long-term monitoring: A variation-al autoencoder to validate the clustering analysis, The Journal of the Acoustical Society of America 153 (2023) 738–750. https://doi.org/10.1121/10.0016887.
  8. D. De Salvio, G. Fratoni, D. D’Orazio, M. Garai, Assessing human activity noise in workspaces using machine learning and numerical models, INTER-NOISE and NOISE-CON Congress and Conference Proceedings 265 (2023) 5259–5269. https://doi.org/10.3397/IN_2022_0767.
  9. M. Cingolani, D. De Salvio, D. D’Orazio, M. Garai, Clustering analysis of noise sources in healthcare facilities, Applied Acoustics 214 (2023) 109660. https://doi.org/10.1016/j.apacoust.2023.109660.
  10. Y.-J. Choi, Evaluation of acoustical conditions for speech communication in active university classrooms, Applied Acoustics 159 (2020) 107089. https://doi.org/10.1016/j.apacoust.2019.107089.
  11. M.C. Cutler, M.R. Cook, M.K. Transtrum, K.L. Gee, Data-driven decomposition of crowd noise from indoor sporting events, The Journal of the Acoustical Society of America 155 (2024) 962–970. https://doi.org/10.1121/10.0024724.
  12. D. D’Orazio, D. De Salvio, L. Anderlucci, M. Garai, Measuring the speech level and the student activity in lecture halls: Vis-ual- vs blind-segmentation methods, Applied Acoustics 169 (2020) 107448. https://doi.org/10.1016/j.apacoust.2020.107448.
  13. Y. Hasegawa, E. Ryherd, Clustering acoustical measurement data in pediatric hospital units, The Journal of the Acoustical Society of America 148 (2020) 265–277. https://doi. org/10.1121/10.0001584.
  14. M.J. Bianco, P. Gerstoft, J. Traer, E. Ozanich, M.A. Roch, S. Gannot, C.-A. Deledalle, Machine learning in acoustics: Theory and applications, The Journal of the Acoustical Society of America 146 (2019) 3590–3628. https://doi.org/10.1121/1.5133944.
  15. E. Ozanich, A. Thode, P. Gerstoft, L.A. Freeman, S. Freeman, Deep embedded clustering of coral reef bioacoustics, The Journal of the Acoustical Society of America 149 (2021) 2587–2601. https://doi.org/10.1121/10.0004221.
  16. M.J. Bianco, S. Gannot, E. Fernandez-Grande, P. Gerstoft, Semi-Supervised Source Localization in Reverberant Environments With Deep Generative Modeling, IEEE Access 9 (2021) 84956–84970. https://doi.org/10.1109/ACCESS.2021.3087697.
  17. W.F. Jenkins II, P. Gerstoft, M.J. Bianco, P.D. Bromirski, Unsupervised Deep Clustering of Seismic Data: Monitoring the Ross Ice Shelf, Antarctica, Journal of Geophysical Research: Solid Earth 126 (2021) e2021JB021716. https://doi.org/10.1029/2021JB021716.
  18. J. Neri, R. Badeau, P. Depalle, Unsupervised Blind Source Sep-aration with Variational Auto-Encoders, in: 2021 29th Euro-pean Signal Processing Conference (EUSIPCO), IEEE, Dublin, Ire-land, 2021: pp. 311–315. https://doi.org/10.23919/EUSIPCO54536.2021.9616154.
  19. C.C. Aggarwal, C.K. Reddy, eds., Data Clustering: Algorithms and Applications, 1st edition, Chapman and Hall/CRC, Boca Ra-ton, 2013.
  20. C.M. Bishop, N.M. Nasrabadi, Pattern recognition and machine learning, Springer, 2006. https://link.springer.com/book/9780387310732 (accessed February 20, 2024).
  21. D.H. Wolpert, W.G. Macready, No free lunch theorems for optimization, IEEE Transactions on Evolutionary Computation 1 (1997) 67–82. https://doi.org/10.1109/4235.585893.
  22. G.E.P. Box, D.R. Cox, An Analysis of Transformations, Journal of the Royal Statistical Society: Series B (Methodological) 26 (1964) 211–243. https://doi.org/10.1111/j.2517-6161.1964.tb00553.x.
  23. G.J. McLachlan, S.X. Lee, S.I. Rathnayake, Finite Mixture Models, Annual Review of Statistics and Its Application 6 (2019) 355–378. https://doi.org/10.1146/annurev-statistics-031017-100325.
  24. J. Shao, Mathematical statistics, Springer Science & Business Media, 2003.
  25. X.-L. Meng, D. Van Dyk, The EM Algorithm—an Old Folk-song Sung to a Fast New Tune, Journal of the Royal Statistical Society: Series B (Methodological) 59 (1997) 511–567. https://doi.org/10.1111/1467-9868.00082.
  26. T. Caliński, J. Harabasz, A dendrite method for cluster analysis, Communications in Statistics 3 (1974) 1–27. https://doi.org/10.1080/03610927408827101.
  27. D.L. Davies, D.W. Bouldin, A Cluster Separation Measure, IEEE Trans. Pattern Anal. Mach. Intell. PAMI-1 (1979) 224–227. https://doi.org/10.1109/TPAMI.1979.4766909.
  28. P.J. Rousseeuw, Silhouettes: A graphical aid to the interpretation and validation of cluster analysis, Journal of Computational and Applied Mathematics 20 (1987) 53–65. https://doi.org/10.1016/0377-0427(87)90125-7.
  29. R. Tibshirani, G. Walther, T. Hastie, Estimating the number of clusters in a data set via the gap statistic, Journal of the Royal Statistical Society: Series B (Statistical Methodology) 63 (2001) 411–423. https://doi.org/10.1111/1467-9868.00293.
  30. UNI 11532-2:2020 - UNI Ente Italiano di Normazione, (n.d.). https://store.uni.com/uni-11532-2-2020 (accessed February 28, 2024).
  31. 2023 ASHRAE Handbook—HVAC Applications | ashrae.org, (n.d.). https://www.ashrae.org/technical-resources/ashrae-handbook/2023-ashrae-handbook-hvac-applications (accessed February 28, 2024).
  32. UNI EN 1793-3:1999 - UNI Ente Italiano di Normazione, (n.d.). https://store.uni.com/uni-en-1793-3-1999 (accessed February 28, 2024).
  33. A. Can, L. Leclercq, J. Lelong, D. Botteldooren, Traffic noise spectrum analysis: Dynamic modeling vs. experimental observations, Applied Acoustics 71 (2010) 764–770. https://doi.org/10.1016/j.apacoust.2010.04.002.
  34. UNI EN ISO 3382-3:2022 - UNI Ente Italiano di Normazione, (n.d.). https://store.uni.com/uni-en-iso-3382-3-2022 (accessed February 28, 2024).
  35. J.H. Rindel, C.L. Christensen, A.C. Gade, Dynamic sound source for simulating the Lombard effect in room acoustic modeling software, in: INTER-NOISE and NOISE-CON Congress and Conference Proceedings, Institute of Noise Control Engineering, 2012: pp. 954–966. https://www.odeon.dk/pdf/C118-IN12_Paper%20209_Rindel_Christensen.pdf (accessed Febru-ary 28, 2024).
  36. G. Leembruggen, J. Verhave, S. Feistel, L. Holtzem, P. Mapp, H. Sato, T. Steinbrecher, S. Van Wijngaarden, The effect on sti results of changes to the male test-signal spectrum, Proc. IOA 38 (2016) 78–87.

Metriche

Caricamento metriche ...