A CRNN with mid-side intensity, spatial coherence, stereo channel swapping, FilterAugment, frequency shifting, and distance normalization improves stereo 3D SELD on STARSS23.
Dataset The STARSS23 dataset consists of real-world, multi-room record- ings with annotations of event activity, spatial trajectories, and dis- tances [23]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Stereo 3D Sound Event Localization and Detection: Perceptual Features, Stereo-specific Data Augmentation, and Distance Normalization
A CRNN with mid-side intensity, spatial coherence, stereo channel swapping, FilterAugment, frequency shifting, and distance normalization improves stereo 3D SELD on STARSS23.