This is the pytorch code of TCN-DenseUNet used in our paper:

Z.-Q. Wang*, P. Wang*, and D.L. Wang, "Complex Spectral Mapping for Single- and Multi-Channel Speech Enhancement and Robust ASR", in IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE/ACM T-ASLP), vol. 28, pp. 1778-1787, May 2020. [* denotes equal contribution]