meta-SR
meta-SR copied to clipboard
Pytorch implementation of Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs (Interspeech, 2020)
 can you help me
Thanks for open-sourcing implementation. I am trying use you code, however even after 5 epochs the accuracy is not imporving. The acc_e is 20% and acc_g is 0% from the...
@seongmin-kye Hello, The full connection layer in the model is not defined at initialization time: https://github.com/seongmin-kye/meta-SR/blob/b4c1ea1728e33f7bbf7015c38f508f24594f3f88/model/resnet_256.py#L157 In [Youngmoon Jung's repo](https://github.com/jymsuper/SpeakerRecognition_tutorial), I noticed that in similar model code, he defined `self.fc`,...
For the "Unseen speaker identification," that means the speaker in the test set isn't seen in the training set? Thank you. @seongmin-kye