[hts-users:04592] Description of DNN Predicted output

Subject: [hts-users:04592] Description of DNN Predicted output
From: Aayush Kumar Tyagi <aayush16081@xxxxxxxxxxx>
Date: Wed, 31 Jan 2018 13:53:30 +0530
Authentication-results: mailgw.mains.nitech.ac.jp; dkim=pass (1024-bit key) header.d=iiitd.ac.in header.i=@iiitd.ac.in header.b="GWIX3v0d"
Delivered-to: hts-users@xxxxxxxxxxxxxxx
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=iiitd.ac.in; s=google; h=mime-version:from:date:message-id:subject:to; bh=kWgjhYNymGTPJY1zeo7bNOJjyvMivRB7NDD0KdvC8/o=; b=GWIX3v0dfzLUNnXp+IddLknd4BGF27ivpZgzSsKiyiWaVnvM0pu/ux2g8hpeFxX12J ufBC/ZkPOmKb/0l+yfM5f5vcdkyE1RU2Sf0rcRWMp2euycjU5UMQqGdm9hicUz8GYjpd GKIMK5xCajCwGS4wpv9WMMb3hqKg5PTVkmSls=

Hi,

I am using DNN based speech synthesis(USEDNN=1).

I guess the output of DNN is a combination of spectral and excitation parameters.

The number of output units of DNN is 109.

Can someone help me understand what these 109 points correspond to?Like how many of these are MGC points and which one is log f0.

I am particularly interested in the position of the fundamental frequency in the predicted output.

Please Correct me if I am completely wrong.

Thanks a lot

Aayush Tyagi

Follow-Ups
: [hts-users:04593] Re: Description of DNN Predicted output, Takenori Yoshimura