DDxk/triplet-loss-train-for-speaker-recognition

It is a complete project of voiceprint recognition or speaker recognition.Before, I upload a very classic VGG based model for speaker recognition . The model simply use softmax-loss to train super-parameters. But during testing stage,we found the model is not very reliable。for example, the model can easily distinguish man-man group, and man-woman group, but difficultly in woman-woman. So, we try another method called triplet-group to retrain our model, of course, we use triplet-loss as the loss for back propagation. The I upload our core code, and training curve for the two training stage. Why, I refer to "two training stage"? That need you to understand the triplet-group method. And very very welcome to my mailbox: primtee_nxg@163.com

PythonMIT