In this paper, we propose a Deep Recurrent Neural Network (DRNN) approach based on Long-Short Term Memory (LSTM) units for the classification of audio signals recorded in construction sites. Five classes of multiple vehicles and tools, normally used in construction sites, have been considered. The input provided to the DRNN consists in the concatenation of several spectral features, like MFCCs, mel-scaled spectrogram, chroma and spectral contrast. The proposed architecture and the feature extraction have been described. Some experimental results, obtained by using real-world recordings, demonstrate the effectiveness of the proposed idea. The final overall accuracy on the test set is up to 97% and overcomes other state-of-the-art approaches.

Deep recurrent neural networks for audio classification in construction sites / Scarpiniti, M.; Comminiello, D.; Uncini, A.; Lee, Y. -C.. - 2021:(2021), pp. 810-814. (Intervento presentato al convegno 28th European Signal Processing Conference, EUSIPCO 2020 tenutosi a Amsterdam) [10.23919/Eusipco47968.2020.9287802].

Deep recurrent neural networks for audio classification in construction sites

Scarpiniti M.;Comminiello D.;Uncini A.;
2021

Abstract

In this paper, we propose a Deep Recurrent Neural Network (DRNN) approach based on Long-Short Term Memory (LSTM) units for the classification of audio signals recorded in construction sites. Five classes of multiple vehicles and tools, normally used in construction sites, have been considered. The input provided to the DRNN consists in the concatenation of several spectral features, like MFCCs, mel-scaled spectrogram, chroma and spectral contrast. The proposed architecture and the feature extraction have been described. Some experimental results, obtained by using real-world recordings, demonstrate the effectiveness of the proposed idea. The final overall accuracy on the test set is up to 97% and overcomes other state-of-the-art approaches.
2021
28th European Signal Processing Conference, EUSIPCO 2020
audio processing; construction sites; deep learning; environmental sound classification; LSTM units; recurrent neural networks (RNNs)
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Deep recurrent neural networks for audio classification in construction sites / Scarpiniti, M.; Comminiello, D.; Uncini, A.; Lee, Y. -C.. - 2021:(2021), pp. 810-814. (Intervento presentato al convegno 28th European Signal Processing Conference, EUSIPCO 2020 tenutosi a Amsterdam) [10.23919/Eusipco47968.2020.9287802].
File allegati a questo prodotto
File Dimensione Formato  
Scarpiniti_Deep_2020.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 216.27 kB
Formato Adobe PDF
216.27 kB Adobe PDF   Contatta l'autore

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/11573/1482332
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 29
  • ???jsp.display-item.citation.isi??? 22
social impact