MCD Script File Formats

[Brooklyn S]

I noticed the script to calculate MCD between the reference and synthesized utterances (https://github.com/MattShannon/mcd) requires that we extract .mgc, .bap, and .lp0 files from our synthesized utterances (.wav files) and that our reference utterances be in .mgc format as well. I’m not entirely sure how to do this – is Festival able to do this, or will I need to figure something else out? Any advice is greatly appreciated!

[Korin Richmond]

No, Edinburgh Speech Tools/Festival can’t produce those files.

Those are files derived from STRAIGHT analysis as part of the standard HTS (HMM-based synthesis) build recipe, as Matt Shannon notes elsewhere:

https://github.com/MattShannon/HTS-demo_CMU-ARCTIC-SLT-STRAIGHT-AR-decision-tree/issues/2

Looking at the data processing in, for example

https://github.com/MattShannon/HTS-demo_CMU-ARCTIC-SLT-STRAIGHT-AR-decision-tree/blob/master/data/Makefile.in

You’ll see the matlab version of STRAIGHT is used, followed by several subsequent steps using SPTK tools, perl scripts etc…

[Author]

Posts