ghua-ac / end-to-end-synthetic-speech-detection Goto Github PK

Hi ghuawhu ,

Thanks for providing the pre-trained model but I have tested your model for FoR dataset by aptly lab and it is not working at all!

EER = 44 % for eval dataset
Accuracy = 48.64 %
could you please tell me what is the reason behind this and model is working fine for the asvspoof2019 dataset but when I tested for the new or unseen dataset, it is not working as expected?

Also , please provide me your email id for further contact.

Thanks,
Utkarsh

https://github.com/ghuawhu/end-to-end-synthetic-speech-detection/blob/fdd024db1da4ef0f1983366a35fe3d013688b822/data.py#L20

I use two pcs; they have different specs but use the exact same python libraries.

In one of the two pcs, the reading by soundfile library sf.read makes the floating issue for some audio files, ending up with extremely large number over a component of a sample.

I recommend using torchaudio.load instead of sf.read'; this fixes the issue.

Is this project still being kept up?

whenever I used to apply a pre-trained model on my own real voice, it shows the following error:

RuntimeError: mat1 dim 1 must match mat2 dim 0

Do you what is the reason for this error?

Note: it works well for other data apart from my real recorded voice.