search

csun22 / Synthetic-Voice-Detection-Vocoder-Artifacts

This repository is related to our Dataset and Detection code from the paper: AI-Synthesized Voice Detection Using Neural Vocoder Artifacts accepted in CVPR Workshop on Media Forensic 2023.
https://arxiv.org/abs/2304.13085
MIT License
94 stars 10 forks source link

About SampleRate #12

Closed qingfusheng closed 3 months ago

qingfusheng commented 4 months ago

Hello, I would like to ask why the sampling rate is defined as 16000 in the model SincConv, but the sampling rate specified in the training is 24000. Will this sampling rate affect the training process?

SwenHou commented 3 months ago

This is a good question, thanks for raising it. Sampleing rate in SincConv should be 24000, same as in training code.