Enhanced Multiple Sound Event Detection and Classification Using Physical Signal Properties in Recurrent Spiking Neural Networks

Sound event detection and classification present significant challenges, particularly in noisy environments with multiple overlapping sources. This paper introduces an innovative architecture for multiple sound event detection and classification utilizing recurrent spiking neural networks (SNNs). Ou...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Zahra Roozbehi, Ajit Narayanan, Mahsa Mohaghegh, Samaneh-Alsadat Saeedinia
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	IEEE 2025-01-01
Σειρά:	IEEE Access
Θέματα:	Sound classification spiking neural network Tempotron audio signal power detection multiple sound sources
Διαθέσιμο Online:	https://ieeexplore.ieee.org/document/10973233/
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!