A few question on training schemes

[hyli666]

Hi, Jason

Thank you very much for sharing the codes. I really like your paper, it's quite flexible and efficient to optimize some un-differentiable measures using your proposed scheme. Regarding to the detailed training procedures, I have several questions below:

(1) Did you train enhancement model (G), using PESQ measure (D) directly? I mean, did you add some additional loss, like MSE, or only used PESQ measure alone, in training stage?
(2) when training D, I found you trained it using so-called "previous list". It seems optional, I would like to know whether this stage is crucial for getting a better result?
(3) In the released codes, G and D are trained alternately for num_sampling=100 steps in one epoch. And batch_size used is equal to 1. I am wondering whether these hyper-parameters are same with your recipe, to get the Table.2 results?

Sorry to ask so many questions. Thank you again and wish you good works in future!

[JasonSWFu]

Hi,

1. For the training enhancement model (G), we only use PESQ measure (D) directly.

2. It can provide a better result, but it's not very crucial.

3. Yes. However, as mentioned in the paper, the input features and activation functions used in table 2 are different from those provided here.

[hyli666]

Thanks, it really helps me a lot.