MATEC Web Conf.
Volume 161, 201813th International Scientific-Technical Conference on Electromechanics and Robotics “Zavalishin’s Readings” - 2018
|Number of page(s)||6|
|Section||Robotics and Automation|
|Published online||18 April 2018|
A comparison of multi-style DNN-based TTS approaches using small datasets
Faculty of Technical Sciences, University of Novi Sad, 21000 Novi Sad, Serbia
2 AlfaNum Speech Technologies, 21000 Novi Sad, Serbia
* Corresponding author: firstname.lastname@example.org
Studies have shown that people already perceive the interaction with computers, robots and media in the same way as they perceive social communication with other people. For that reason it is critical for a high-quality text-to-speech system (TTS) to sound as human-like as possible. However, a major obstacle in creating expressive TTS voices is that the amount of style-specific speech needed for training such a system is often not sufficient. This paper presents a comparison between different approaches to multi-style TTS, with focus on cases when only a small dataset per style is available. The described approaches have been originally proposed for efficient modelling of multiple speakers with a limited amount of data per speaker. Among the suggested approaches the approach based on style codes has emerged as the best, regardless of the target speech style.
© The Authors, published by EDP Sciences, 2018
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (http://creativecommons.org/licenses/by/4.0/).
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.