[hts-users:04675] Different consonants are sounding similar
- Subject: [hts-users:04675] Different consonants are sounding similar
- From: उत्कर्ष राजपूत <utkars.rajput@xxxxxxxxx>
- Date: Fri, 9 Oct 2020 10:59:33 +0530
- Authentication-results: mailgw.mains.nitech.ac.jp; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="FpoWVqyj"
- Delivered-to: hts-users@xxxxxxxxxxxxxxx
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:from:date:message-id:subject:to; bh=jg/ld6mQbVpTvVDKtewntdcYPQdTbFeMFT6LNzamSas=; b=FpoWVqyjoRCmU+xYquytqyAo2SpXHIxgw5cOMCvGiEyVr0PcN2HhNM2gnMi1P03/1k JyqJwvMJfsVljqatVRiYj2lL6yN+IRHVQbhhSCP6Huj4gSfkXN+JCiubm+Mt20/PL48N GuRMDpXLxlZU+UuTwwt3x/+lYOjrwMtmfQ5KMfS+mikhoxq8bD/9wh4Etc83oW/bzyFJ dgiZ8hGsDCN/gkDcrzx390graKxhbMUPImV7SNSjEfEVWu0/m+XnrjPsSbS2qcM0mV/s HsetZmvLnFMcChkH+oPh4X4aVQyKPdWmrAWjgjBS9as6YkkU2PHjmtnx0m+ZQteS5b5U L/xQ==
I made a voice from 25 minutes of speech. Many consonants which should sound different are sounding same in the synthesis, even though there are lot a of examples (minimum 10 of each consonant, with different vowels) in the training data. For example glottal stop is sounding like dental stop. What parameters need to be changed to get better synthesis?
- Follow-Ups
-
- [hts-users:04676] Re: Different consonants are sounding similar, Sébastien Le Maguer