Next Article in Journal
The Requirement of Genetic Diagnostic Technologies for Environmental Surveillance of Antimicrobial Resistance
Next Article in Special Issue
Attention-Based Joint Training of Noise Suppression and Sound Event Detection for Noise-Robust Classification
Previous Article in Journal
Investigating the Usability of a Head-Mounted Display Augmented Reality Device in Elementary School Children
Previous Article in Special Issue
Automatic Detection of Chewing and Swallowing
 
 
Article

An Incremental Class-Learning Approach with Acoustic Novelty Detection for Acoustic Event Recognition

by 1 and 1,2,*
1
Computer Engineering Department, Faculty of Computer and Informatics Engineering, Istanbul Technical University, Istanbul 34469, Turkey
2
Artificial Intelligence and Data Science Application and Research Center, Istanbul Technical University, Istanbul 34469, Turkey
*
Author to whom correspondence should be addressed.
Academic Editor: Hong-Kook Kim
Sensors 2021, 21(19), 6622; https://doi.org/10.3390/s21196622
Received: 25 August 2021 / Revised: 29 September 2021 / Accepted: 30 September 2021 / Published: 5 October 2021
(This article belongs to the Special Issue Acoustic Event Detection and Sensing)
Acoustic scene analysis (ASA) relies on the dynamic sensing and understanding of stationary and non-stationary sounds from various events, background noises and human actions with objects. However, the spatio-temporal nature of the sound signals may not be stationary, and novel events may exist that eventually deteriorate the performance of the analysis. In this study, a self-learning-based ASA for acoustic event recognition (AER) is presented to detect and incrementally learn novel acoustic events by tackling catastrophic forgetting. The proposed ASA framework comprises six elements: (1) raw acoustic signal pre-processing, (2) low-level and deep audio feature extraction, (3) acoustic novelty detection (AND), (4) acoustic signal augmentations, (5) incremental class-learning (ICL) (of the audio features of the novel events) and (6) AER. The self-learning on different types of audio features extracted from the acoustic signals of various events occurs without human supervision. For the extraction of deep audio representations, in addition to visual geometry group (VGG) and residual neural network (ResNet), time-delay neural network (TDNN) and TDNN based long short-term memory (TDNN–LSTM) networks are pre-trained using a large-scale audio dataset, Google AudioSet. The performances of ICL with AND using Mel-spectrograms, and deep features with TDNNs, VGG, and ResNet from the Mel-spectrograms are validated on benchmark audio datasets such as ESC-10, ESC-50, UrbanSound8K (US8K), and an audio dataset collected by the authors in a real domestic environment. View Full-Text
Keywords: acoustic scene analysis; acoustic event recognition; acoustic novelty detection; audio signal augmentation; incremental class-learning acoustic scene analysis; acoustic event recognition; acoustic novelty detection; audio signal augmentation; incremental class-learning
Show Figures

Figure 1

MDPI and ACS Style

Bayram, B.; İnce, G. An Incremental Class-Learning Approach with Acoustic Novelty Detection for Acoustic Event Recognition. Sensors 2021, 21, 6622. https://doi.org/10.3390/s21196622

AMA Style

Bayram B, İnce G. An Incremental Class-Learning Approach with Acoustic Novelty Detection for Acoustic Event Recognition. Sensors. 2021; 21(19):6622. https://doi.org/10.3390/s21196622

Chicago/Turabian Style

Bayram, Barış, and Gökhan İnce. 2021. "An Incremental Class-Learning Approach with Acoustic Novelty Detection for Acoustic Event Recognition" Sensors 21, no. 19: 6622. https://doi.org/10.3390/s21196622

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop