[hts-users:03172] Re: Should we enable MGE and GV at the same time?
- Subject: [hts-users:03172] Re: Should we enable MGE and GV at the same time?
- From: "Heiga ZEN (Byung Ha CHUN)" <heigazen@xxxxxxxxxx>
- Date: Tue, 21 Feb 2012 18:24:49 +0000
- Authentication-results: mr.google.com; spf=pass (google.com: domain of heigazen@xxxxxxxxxx designates 10.112.23.104 as permitted sender) smtp.mail=heigazen@xxxxxxxxxx; dkim=pass header.i=heigazen@xxxxxxxxxx
- Delivered-to: hts-users@xxxxxxxxxxxxxxx
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :content-type:x-system-of-record; bh=dS8cc3mlYYNWuNfW9xgRDf5OpIecXbWw8PAPR92vNK0=; b=kjbfdZIgduFkaDY8mOIpeHT3jQ+uYPBO06Ee7I6TFwJa/MQEW9PYXL7y/wG6TCIiK1 JWk59j7s2St0x2UjC/z1uHYm3oIyxN/ZYQVy0oezGTQUx2Axu9ty4/IW0IewhqXTQ1gK rDXrApPazR2PmVhA79LRIycki1Ydxb+9gJj2s=
Hi,
2012/2/17 Yuan-Fu Liao <yfliao@xxxxxxxxxxx>:
> Should we combine MGE training (using HMgeTool) and GV parameter generation
> (option in HMGens)? I'm wondering if GV will distort the effect of MGE
> training or not.
For me, using the MGE-trained model with the current implementation of GV in HMGenS sounds wrong, as there is a severe mismatch in their objective functions:
MGE: minimize \sum_n (c_n - ^c_n(q, \lambda))^2 w.r.t. \lambda
GV: maximize \log N(Wc; \mu_q, \Sigma_q) + \alpha \log N(v(c); \mu_gv, \Sigma_gv) w.r.t. c
The MGE-trained model will not give proper N(Wc; \mu_q, \Sigma_q) as its parameters are stimated so as to minimize the Euclidean distance rather than likelihood.
Regards,
Heiga
--
Heiga ZEN (in Japanese)
Byung Ha CHUN (in Korean)
<heigazen@xxxxxxxxxx>
- References
-
- [hts-users:03170] Should we enable MGE and GV at the same time?, Yuan-Fu Liao