5.1.1. Objective Results

The purpose of these experiments is to show the effectiveness of the progressive generator. Table 2 presents the performance of the proposed generator when we minimized only the *<sup>L</sup>*1(*Gn*) in Equation (11). In order to better understand the influence of the progressive structure on the PESQ score, we conducted an ablation study with different *p* in ∑*n*≥*p <sup>L</sup>*1(*Gn*). As illustrated in Table 2, compared to the auto-encoder CNN (AECNN) [26] that is the conventional U-net generator minimizing the *L*1 loss only, the PESQ score of the progressive generator improved from 2.5873 to 2.6516. Furthermore, for the smaller *p*, we go<sup>t</sup> a better PESQ score, and the best PESQ score was achieved when *p* was the lowest, i.e., 1*k*. For enhancing high-resolution speech, we verified that it is very useful to progressively generate intermediate enhanced speech while maintaining the estimated information obtained at lower sampling rate. We used the best generator *p* = 1*k* in Table 2 for the subsequent experiments.


**Table 2.** Comparison of results between different architectures of the progressive generator. The best model is shown in bold type.
