Deep Learning-Based Amplitude Fusion for Speech Dereverberation
Table 3
Description of some important methods derived from masking.
Method
Basic principle
TDR
Time-domain signal reconstruction. This paper uses IAM-based TDR, and also clean speech phase is used to recover the time-domain signal [46ā48].
I_IRM
Indirect mapping of IRM, which was proposed in [23] to learn the IRM target via MSE between the masked and reference clean LMS.
IAM_A
In this method, the DNN estimates a IAM mask that is applied over the corrupted speech amplitude and the loss function is created between masked amplitude and the clean speech amplitude [49, 50].
DCC_A
This method is similar to IAM_A, except that IAM mask is replaced with DCC mask.