Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

实验细节的疑问 #5

Open
Wenhao-Yang opened this issue Dec 29, 2020 · 1 comment
Open

实验细节的疑问 #5

Wenhao-Yang opened this issue Dec 29, 2020 · 1 comment

Comments

@Wenhao-Yang
Copy link

您好:
我想教下您的论文中,实验的实现细节:
1.实验数据:我看很多其他论文都是使用voxceleb2 dev 5994说话人作为训练集(或者voxceleb dev+voxceleb2 dev,1211+5994说话人),您有只在这部分说话人上的实验结果吗?方便透露下嘛?

2.PLDA和Cosine Similarity:您这里实验比较这两个的EER在TDNN中是提取的是倒数第二层(分类器前一层)还是第三层(xvector)的输出啊?因为我在论文中又看到,这两个不同层embedding对不同方法性能有差异,倒数第二层的cosine方法可能会更好一些。

Thanks!🙏

@yuyq96
Copy link
Owner

yuyq96 commented Dec 29, 2020

  1. 有试过只用VoxCeleb2 dev,差距不大。
  2. 是的,倒数第二层配合Cosine更好,倒数第三层配合PLDA更好。但如果我没有记错的话,TDNN直接用倒数第二层配合Cosine还是比不过倒数第三层配合PLDA,不过差距应该没这么明显。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants