The CSTR entry to the 2018 Blizzard Challenge

Felipe Espic calderón, Avashna Govender, Manuel Sam Ribeiro, Cassia Valentini Botinhao, Oliver Watts

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Similar to 2016 and 2017 Blizzard Challenge, the task for this year is to train on expressively-read children’s story-books, and to synthesise speech in the same domain. This give us an opportunity to investigate the effectiveness of several techniques we have developed when applied to expressive and prosodically varied audiobook data. This paper describes the text-to-speech system entered by The Centre for Speech Technology Research into the 2018 Blizzard Challenge. The system is a hybrid synthesis system where a halfphone unit selection synthesiser is driven by the output of a neural network based acoustic and duration model. We adopt the same neural network based models used in our last year entry with a different unit selection component. We discuss the performance of our system by reporting the results from formal listening tests provided by the challenge.
Original languageEnglish
Title of host publicationBlizzard Challenge 2018 workshop
Place of PublicationHyderabad, India
Number of pages5
Publication statusPublished - 2018
EventBlizzard Challenge 2018 Workshop - Hyderabad, India
Duration: 8 Sep 20188 Sep 2018


ConferenceBlizzard Challenge 2018 Workshop
Abbreviated titleBlizzard 2018
Internet address

Fingerprint Dive into the research topics of 'The CSTR entry to the 2018 Blizzard Challenge'. Together they form a unique fingerprint.

Cite this