SCNet: Sparse Compression Network for Music Source Separation
Deep learning-based methods have made significant achievements in music source
separation. However, obtaining good results while maintaining a low model complexity …
separation. However, obtaining good results while maintaining a low model complexity …
Coarse-to-fine speech separation method in the time-frequency domain
X Yang, C Bao, X Chen - Speech Communication, 2023 - Elsevier
Although time-domain speech separation methods have exhibited the outstanding
performance in anechoic scenarios, their effectiveness is considerably reduced in the …
performance in anechoic scenarios, their effectiveness is considerably reduced in the …