학술논문
DNN Based Expressive Text-to-Speech with Limited Training Data
Document Type
Conference
Source
2019 27th Telecommunications Forum (TELFOR) Telecommunications Forum (TELFOR), 2019 27th. :1-6 Nov, 2019
Subject
Language
Abstract
Modern text-to-speech synthesis systems should deliver speech which is not just intelligible, but whose style corresponds to the domain in which synthesized speech is used. In this paper three approaches based on deep neural networks aimed at synthesis of expressive speech are presented: style code, model re-training and an architecture using shared hidden layers. Their usability is tested on a speech corpus with a limited amount of expressive speech data. A new architecture for transplanting speech styles is also presented and compared with a referent approach from literature.