[hts-users:02712] Re: trajectory HMM
- Subject: [hts-users:02712] Re: trajectory HMM
- From: Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>
- Date: Mon, 21 Feb 2011 20:01:53 +0900
- Cc: uratec <uratec@xxxxxxxxxxxxxxx>
- Delivered-to: hts-users@xxxxxxxxxxxxxxx
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=4o6X5T+6PzxjT80BRKB5uWs7PykI7yACU8VrqWSkw8k=; b=vSC9G5+Qn1J3tV6pto+VkaV+/hqvB8f8bE+kHQNIHf0M0PU2eZG/WTpsovdlcE5Drg pCPl8jRe9M4aO6kzNlzkgHV8bO6umTk463p9Q+7hHXnYHhfEsVDimqSeAyUMLLNof2Zv JgcsKjZ9NipwvuZ8h2mzevs9bjPOKMtqZjrLQ=
- Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; b=NT4vSyyzWD5UTdk/HFVlpCEgbkIdaVEk7BLIIIT/CxOSxBa09S/PWN1l+APumiAQoA dmMbNFTIV+xCEqQlOF3fEP9+Mnxd17WWmQ5rcPEJP6AOLho9w7MlM1J1rzAe0984Y7Tk PM4Ib1qHdAjaPomoC5i1tBpY87igjYzA5ckyg=
Hi,
Trajectory HMM is not implemented in release version.
2011/2/21 Sébastien Le Maguer <Sebastien.Le_maguer@xxxxxxxx>:
> Hello,
>
> I am reading the papers about the trajectory and I have a question. It is
> discussed about a viterbi training but in the training script the
> reestimation stages are using HERest which, I suppose, is a baum-welch
> reestimation. So I wonder in which files the implementation of the
> Trajectory HMM are in HTS?
>
> Thanks for the answer
>
> Sébastien
- Follow-Ups
-
- [hts-users:02713] Re: trajectory HMM, Sébastien Le Maguer
- References
-
- [hts-users:02711] trajectory HMM, Sébastien Le Maguer