Question about the loss funvtion

[xiaoyiming]

The cost function is defined as follows,in your codes:
def audio_discriminate_loss2(gamma=0.1,beta = 20.1,num_speaker=2):
def loss_func(S_true,S_pred,gamma=gamma,beta=beta,num_speaker=num_speaker):
sum_mtr = K.zeros_like(S_true[:,:,:,:,0])
for i in range(num_speaker):
sum_mtr += K.square(S_true[:,:,:,:,i]-S_pred[:,:,:,:,i])
for j in range(num_speaker):
if i != j:
sum_mtr -= gamma(K.square(S_true[:,:,:,:,i]-S_pred[:,:,:,:,j]))
for i in range(num_speaker):
for j in range(i+1,num_speaker):
#sum_mtr -= betaK.square(S_pred[:,:,:,i]-S_pred[:,:,:,j])
#sum_mtr += betaK.square(S_true[:,:,:,:,i]-S_true[:,:,:,:,j])
pass
#sum = K.sum(K.maximum(K.flatten(sum_mtr),0))
loss = K.mean(K.flatten(sum_mtr))
return loss
return loss_func
However, I do not understand the meaning of this parts:
for j in range(num_speaker):
if i != j:
sum_mtr -= gamma*(K.square(S_true[:,:,:,:,i]-S_pred[:,:,:,:,j]))
I guess you want to use the permutation invariant (PIT) loss, but the definition of PIT is not like that. what is the meaning of this part?

[bill9800]

You can see the detail in C.Training Objectives on page 4-5.
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation, P. Hunag et al,arXiv:1502.04149v4 [cs.SD] 1 Oct 2015

[xiaoyiming]

Thanks for replay!! I will chick it .