[hts-users:03370] Re: question about GV Based parameter generation
- Subject: [hts-users:03370] Re: question about GV Based parameter generation
- From: Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>
- Date: Tue, 26 Jun 2012 13:20:15 +0900
- Cc: uratec <uratec@xxxxxxxxxxxx>
- Delivered-to: hts-users@xxxxxxxxxxxxxxx
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=1CsTJbVik4rycrQ9VZEh/89RFDRQAdeIet2bcoOjWxU=; b=PIHcav6/vbTaS9sSH5nplm7i1v/QuoTndmKSGtLeAelH4MtmIsEVbbAA2BIYfe5M8k oc281LNKunmQpOAzC1kvZT1iIbInR7n/WTJl+HpK4TV2nsLwyirNSk7+jYl2cmakdIIh y+7RXDAddzgXhAfjab2FA+kFitt2lywyohf5xaO29OoYp0P6OqwtCZLPhChs4ImeBOII pz+c3lHqEPnW9aG8nWXKQz5NtNVXIgVsKaItebmumpNXHf/aRFc4XkVSnr5YMHzGekdM C0ZsZC/WpKf9AWgpuDbdIoToBJcyTmMHnMFvjA6pD3GOkeoxSnwNN1H7bDJku5hik4YC dmnQ==
Hi,
The algorithm is not changed.
Only model tying structure is changed.
Keiichiro Oura, Yi-Jian Wu, and Keiichi Tokuda,
Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2009,
Blizzard Challenge 2009, 2009-09.
Regards,
Keiichiro Oura
2012/6/26 soheil khorram <soheil_khorram@xxxxxxxxx>:
> Dear all,
>
> I have read the paper titled "A Speech Parameter Generation Algorithm
> Considering Global Variance for HMM-Based Speech Synthesis" and I am
> confused about the GV distribution. According to the paper, the GV
> distribution for each parameter is a single Gaussian, but in the HTS demo a
> decision tree is trained for this parameter.
> I want to know, when a context dependent distribution is used for GV, what
> part of the algorithm will be changed.
> I will be appreciated if there is a useful reference for it.
> Thanks in advance.
>
> Khorram
- Follow-Ups
-
- [hts-users:03371] Re: question about GV Based parameter generation, soheil khorram
- References
-
- [hts-users:03369] question about GV Based parameter generation, soheil khorram