search

leimao / Voice-Converter-CycleGAN

Voice Converter Using CycleGAN and Non-Parallel Data
https://leimao.github.io/project/Voice-Converter-CycleGAN/
MIT License
526 stars 127 forks source link

mcep #16

Closed assyoucan closed 5 years ago

assyoucan commented 5 years ago

Why does the dimension increase after mcep is output from the network? What is the added dimension?

leimao commented 5 years ago

I am not sure if I understand your question. But I you check the paper, they used 1D-CNN to process the 2D spectrum, the first dimension becomes 1, the second dimension becomes time domain frames and the third dimension becomes the first dimension in the 2D spectrum, if my memory is correct.

leimao commented 5 years ago

No follow-up response. Close the thread.