[hts-users:03117] to speed up CMLLR transform estimation
- Subject: [hts-users:03117] to speed up CMLLR transform estimation
- From: Hui LIANG <tshlmail-hts@xxxxxxxxx>
- Date: Wed, 23 Nov 2011 05:24:56 -0800 (PST)
- Delivered-to: hts-users@xxxxxxxxxxxxxxx
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s1024; t=1322054696; bh=t8AWyRD8BSA6dWJoee7mVOy6W58WpspCytZ/Va9WzUc=; h=X-YMail-OSG:Received:X-Mailer:Message-ID:Date:From:Reply-To:Subject:To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=n7uI3LciTdn2NzquFN3w+usbzeOEjguodZGguxv78X/E/Jjf54nS4tKXVo42SHiR11AtKLGjuiu5RV0rzS/EOruB/QHUa8tFAZq0F+QlMZN2DAIZ7fd0IUfzS2eAovpvECqMMEcDuVwv/NAN2TLYM4gJVgddVGan+0++GAMhFvM=
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:X-Mailer:Message-ID:Date:From:Reply-To:Subject:To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=ur9mXeVUpUa3ZDT1N4z+wm8J5q8thv7T3bFxHnCEtnWrNxJuAUWGLTO8lomtV88xeiU/HsLaEHxzrh3nQBnZ3UoBTwt8Onx4Kr84pzXtmtC6jMxaY2+iIIMK6Anrtj5wZQQnq1yUxsI/255OLWhOkjAXG5xhjx4QkfHUNf47ck8=;
Hello everybody,
I am wondering whether CMLLR transform estimation can be parallelized when the amount of adaptation data of a single speaker is huge ....
Thanks a lot!
Cheers,
Hui