Search papers, labs, and topics across Lattice.
Sogang University
2
0
4
DASH achieves robust speech recognition in noisy environments without compromising clean accuracy, all while adding just 4% to fine-tuning time.
By shifting the learning objective from direct spectral mapping to filter estimation based on inter-frame correlations, IF-CorrNet achieves state-of-the-art monaural speech dereverberation performance, particularly in real-world environments where generalization is critical.