To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed. Our two-stage system leverages on an ad-hoc score combination based on two CNN classifiers: (i) the first CNN classifies acoustic inputs into one of three broad classes, and (ii) the second CNN classifies the same inputs into one of ten finer-grained classes. Three different CNN architectures are explored to implement the two-stage classifiers, and a frequency sub-sampling scheme is investigated. Moreover, novel data augmentation schemes for ASC are also investigated. Evaluated on DCASE 2020 Task 1a, our results show that the proposed ASC system attains a state-of-the-art accuracy on the development set, where our best system, a two-stage fusion of CNN ensembles, delivers a 81.9% average accuracy among multi-device test data, and it obtains a significant improvement on unseen devices. Finally, neural saliency analysis with class activation mapping (CAM) gives new insights on the patterns learnt by our models.

Hu, H.u., Yang, C.H., Xia, X., Bai, X., Tang, X., Wang, Y., et al. (2021). A Two-Stage Approach to Device-Robust Acoustic Scene Classification. In 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (pp. 845-849). IEEE [10.1109/ICASSP39728.2021.9414835].

A Two-Stage Approach to Device-Robust Acoustic Scene Classification

Siniscalchi, Sabato Marco;
2021-01-01

Abstract

To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed. Our two-stage system leverages on an ad-hoc score combination based on two CNN classifiers: (i) the first CNN classifies acoustic inputs into one of three broad classes, and (ii) the second CNN classifies the same inputs into one of ten finer-grained classes. Three different CNN architectures are explored to implement the two-stage classifiers, and a frequency sub-sampling scheme is investigated. Moreover, novel data augmentation schemes for ASC are also investigated. Evaluated on DCASE 2020 Task 1a, our results show that the proposed ASC system attains a state-of-the-art accuracy on the development set, where our best system, a two-stage fusion of CNN ensembles, delivers a 81.9% average accuracy among multi-device test data, and it obtains a significant improvement on unseen devices. Finally, neural saliency analysis with class activation mapping (CAM) gives new insights on the patterns learnt by our models.
2021
Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni
978-1-7281-7605-5
Hu, H.u., Yang, C.H., Xia, X., Bai, X., Tang, X., Wang, Y., et al. (2021). A Two-Stage Approach to Device-Robust Acoustic Scene Classification. In 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (pp. 845-849). IEEE [10.1109/ICASSP39728.2021.9414835].
File in questo prodotto:
File Dimensione Formato  
hu2021.pdf

Solo gestori archvio

Tipologia: Versione Editoriale
Dimensione 4.12 MB
Formato Adobe PDF
4.12 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/10447/636669
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 26
  • ???jsp.display-item.citation.isi??? 22
social impact