WTFormer combines wavelet convolution, TF-Conformer, and multi-dimensional attention with a MUSIC spatial-spectrum loss to preserve inter-channel spatial cues during MIMO speech enhancement.
Traditional single-channel methods [1, 2] relied on signal processing and statistical modeling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
WTFormer: A Wavelet Conformer Network for MIMO Speech Enhancement with Spatial Cues Peservation
WTFormer combines wavelet convolution, TF-Conformer, and multi-dimensional attention with a MUSIC spatial-spectrum loss to preserve inter-channel spatial cues during MIMO speech enhancement.