Do we have a clear reference on ResNET34 settings?

Snowdar / asv-subtools

An Open Source Tools for Speaker Recognition

Apache License 2.0

597 stars 135 forks source link

Do we have a clear reference on ResNET34 settings? #25

Closed underdogliu closed 3 years ago

underdogliu commented 3 years ago

Hi and big kudos to your asv-subtool with both academic and practical contributions!

I found the ResNET34 setting in the toolkit does not have a clear reference. While for other x-vector networks references are quite clear, can I have such for this model please? Maybe from your group?

By saying ResNET34, I am talking about this implemented class.

Snowdar commented 3 years ago

Hi，there are various versions of standard ResNet structure from kaiming He (in CV) and the version of asv-subtools was modified by our own. Maybe you could pay attention to some similar works of speaker recognition, such as "The ins and outs of speaker recognition: lessons from VoxSRC 2020" and "A NOVEL LEARNABLE DICTIONARY ENCODING LAYER FOR END-TO-END LANGUAGE IDENTIFICATION" etc.

underdogliu commented 3 years ago

OK thanks a lot for answering!