Blizzard2013_Segmentation
Blizzard2013_Segmentation copied to clipboard
The splitting of the data
Hi, I just wonder whether the splitting you implemented is from one of the paper in the reference?
Hello, no it is not.
Another question is that, is there any dev and test set, which I cat get access? Or I have to split the dev from the train myself?
No, you have to split it on your own.
I tried to use the alignment tool, and I realised each audio length is about 15-25s. Is it possible to modify the script to align shorter length(<10s)?