[hts-users:03121] Re: Parameters of Festival cmu_us_slt_arctic_hts voice
- Subject: [hts-users:03121] Re: Parameters of Festival cmu_us_slt_arctic_hts voice
- From: Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>
- Date: Sun, 4 Dec 2011 21:21:13 +0900
- Cc: uratec <uratec@xxxxxxxxxxxx>
- Delivered-to: hts-users@xxxxxxxxxxxxxxx
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; 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; bh=hDSBmG2EHe9A1jrSfyB7dvcQFO/VsSmh44i98xZk1rw=; b=NqQN3hny7fzTW+AqlnoXTJ7HmwLaeJsvVhsqtv4+fE2r6wdRVuaNd0c7vGVUprWFyD wnfnzZaPk26WNfVsXDAwifRiVImhnt0bIrhVqJ9V98sLAylGxOpxF9vqXP5NFXWOwXLg Do8wDu3sLJHwL/tdRreVc2ZZR5SRbVaRfJato=
Hi,
The SLT voice in Festival 2.1 was trained by using the standard
programs and data files.
But, the analysis/training parameters are very different from the
standard demo scripts.
Regards,
Keiichiro Oura
2011/12/4 Mark Huckvale <m.huckvale@xxxxxxxxx>:
> Dear List
>
> I have built an HTS voice from the SLT ARCTIC audio files as per the
> demonstration recipe, but the voice doesn't sound as good as the SLT voice
> that comes with Festival 2.1. It sounds more "buzzy" and has some harsh
> fricatives.
>
> Is a different recipe required to get the superior voice, or is that quality
> not attainable using the standard programs and demo data files?
>
> Thanks
>
> Mark
> --
> Mark Huckvale
> UCL Speech, Hearing & Phonetic Sciences
> www.phon.ucl.ac.uk/home/mark
>
>
- Follow-Ups
-
- [hts-users:03122] Re: Parameters of Festival cmu_us_slt_arctic_hts voice, Mark Huckvale
- References
-
- [hts-users:03120] Parameters of Festival cmu_us_slt_arctic_hts voice, Mark Huckvale