PHAST-Net learns an application-general mapping from a CLAWT constellation to ideal cross-term-suppressed T-F representations using attention and a physics-informed reprojection loss.
Reassignment and synchrosqueez- ing for general time–frequency filter banks, subsampling and processing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PHAST-Net: Attention-Guided, Physics-Informed Network for Unified Estimation of Ideal Time-Frequency Representations
PHAST-Net learns an application-general mapping from a CLAWT constellation to ideal cross-term-suppressed T-F representations using attention and a physics-informed reprojection loss.