SCRIPT: Speech Synthesis for Spoken Content Production

Status: active
How can we support the research of hybrid text-to-speech synthesis technologies in low-resource languages?
feature-image

SCRIPT is a 3-year research and innovation project looking to develop synthetic voices for low-resourced languages. The BBC is a SCRIPT project partner and will be providing use cases to the University of Edinburgh’s Centre for Speech Technology Research (CSTR), where the project began in January 2017.

The idea for SCRIPT originated at a language technology #newsHACK that we hosted in collaboration with BBC Connected Studio. Our aim in partnering with the CSTR is to support the research of hybrid text-to-speech synthesis technologies in low-resource languages.

The CSTR is researching the possible integration of two methods of producing synthetic voices: unit selection and deep neural network, or parametric text-to-speech. This will combine the broadcast-quality, ‘natural’-sounding voice recordings produced through unit selection, driven by deep neutral network technology to enable parametric changes to tone, pitch and speed.


Next Priorities

  1. Collate language data in low-resource languages to build language models.