Jayvee Lee

That's also my question.Via reading the origin paper, wavform is shaped into the type of 4s and 8khz. And they prepare 10 hours train-set and 5 hours test-set. That's so...

Yep,the model can deal with three speakers,but you need to change the function 1x1 Conv ,making sure that it ouput three masks. But the performance on more speakers is not...