Frequency-dependent auto-pooling function for weakly supervised sound event detection

Frequency-dependent auto-pooling function for weakly supervised sound event detection

Abstract Sound event detection (SED), which is typically treated as a supervised problem, aims at detecting types of sound events and corresponding temporal information. It requires to estimate onset and offset annotations for sound events at each frame. Many available sound event datasets only cont...

Full description

Bibliographic Details
Main Authors: Sichen Liu, Feiran Yang, Yin Cao, Jun Yang
Format: Article
Language:English
Published: SpringerOpen 2021-05-01
Series:EURASIP Journal on Audio, Speech, and Music Processing
Subjects:
Sound event detection
Weakly supervised
Auto-pooling function
Depthwise separable convolution
Online Access:https://doi.org/10.1186/s13636-021-00206-7

Internet

https://doi.org/10.1186/s13636-021-00206-7

Similar Items