Audio signal processing is moving towards detecting and/or defining rare/anomalous sounds. The ap- plication of such an anomaly detection problem can be easily extended to audio surveillance systems. Thus, a rare sound event detection method for road traffic monitoring is proposed in this paper, includ- ing detection of hazardous events, i.e., road accidents. The method is based on combining anomaly detection techniques, such as variational autoencoders (VAE) and Interval-valued fuzzy sets. The VAE is used to calculate the reconstruction error of the input audio segment. Based on this reconstruction er- ror, a fuzzy membership function, composed of an optimistic/upper component and a pessimistic/lower component, is calculated. Finally, a probabilistic method for interval comparison is used to calculate the membership score, hence to evaluate the interval-valued fuzzy sets. Finally, classification into anoma- lous/normal events is obtained by defuzzification. Results show that with a careful parameter setting, the proposed method outperforms the state-of-the-art one-class SVM for anomaly detection.
Anomaly detection based on interval-valued fuzzy sets: Application to rare sound event detection / S. Rovetta, Z. Mnasri, F. Masulli, A. Cabri (CEUR WORKSHOP PROCEEDINGS). - In: WILF 2021: International Workshop on Fuzzy Logic and Applications 2021 / [a cura di] A. Ciaramella, C. Mencar, S. Montes, S. Rovetta. - [s.l] : CEUR-WS, 2021. - pp. 1-8 (( Intervento presentato al 13. convegno WILF tenutosi a Vietri sul Mare nel 2021.
Anomaly detection based on interval-valued fuzzy sets: Application to rare sound event detection
A. Cabri
2021
Abstract
Audio signal processing is moving towards detecting and/or defining rare/anomalous sounds. The ap- plication of such an anomaly detection problem can be easily extended to audio surveillance systems. Thus, a rare sound event detection method for road traffic monitoring is proposed in this paper, includ- ing detection of hazardous events, i.e., road accidents. The method is based on combining anomaly detection techniques, such as variational autoencoders (VAE) and Interval-valued fuzzy sets. The VAE is used to calculate the reconstruction error of the input audio segment. Based on this reconstruction er- ror, a fuzzy membership function, composed of an optimistic/upper component and a pessimistic/lower component, is calculated. Finally, a probabilistic method for interval comparison is used to calculate the membership score, hence to evaluate the interval-valued fuzzy sets. Finally, classification into anoma- lous/normal events is obtained by defuzzification. Results show that with a careful parameter setting, the proposed method outperforms the state-of-the-art one-class SVM for anomaly detection.File | Dimensione | Formato | |
---|---|---|---|
paper09.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Dimensione
1.21 MB
Formato
Adobe PDF
|
1.21 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.