[hts-users:04530] [Advertisement] Deep Learning for Text-to-Speech Synthesis - Interspeech tutorial
- Subject: [hts-users:04530] [Advertisement] Deep Learning for Text-to-Speech Synthesis - Interspeech tutorial
- From: Simon King <Simon.King@xxxxxxxx>
- Date: Thu, 15 Jun 2017 10:10:51 +0100
- Authentication-results: mailgw.mains.nitech.ac.jp; dkim=fail reason="signature verification failed" (1024-bit key) header.d=uoe.onmicrosoft.com header.i=@uoe.onmicrosoft.com header.b=HA4QHzwG
- Authentication-results: sp.nitech.ac.jp; dkim=none (message not signed) header.d=none;sp.nitech.ac.jp; dmarc=none action=none header.from=ed.ac.uk;
- Delivered-to: hts-users@xxxxxxxxxxxxxxx
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=uoe.onmicrosoft.com; s=selector1-ed-ac-uk; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version; bh=gn9+fLJc8yd/iyUk38zwYWnKMdRab1Lu5u2pnAUszWI=; b=HA4QHzwGFUMFYN6v911LomOfXy1pxu+ssjqkCXiTTsGfQpTb5nNW39g+k9dA+jDqrq7FywuBF6ku8VsqANL1gBMGy+Q+tXZQ4lm5pMVtWc9a7wagoLhB2QnVoVNDrMqHpRmmVeSckVvMYFhxziXKdjN6rawZj1rhoKmEOH7/J0c=
- Spamdiagnosticmetadata: NSPM
- Spamdiagnosticoutput: 1:99
Deep Learning for Text-to-Speech Synthesis, using the Merlin toolkit
http://www.interspeech2017.org/program/tutorial-descriptions/
This tutorial will combine the theory and practical application of Deep
Neural Networks (DNNs) for Text-to-Speech (TTS). It will illustrate how
DNNs are rapidly advancing the performance of all areas of TTS,
including waveform generation and text processing, using a variety of
model architectures. We will link the theory to implementation with the
Open Source Merlin toolkit (http://www.cstr.ed.ac.uk/projects/merlin).
--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.