ZIM Cooperation Project

Expressive Articulatory SYnthesis for audiobooks

Duration: 22 Months

Kickoff: September 2018

Currently, text-to-speech synthesis sounds rather artificial, especially in emotional contexts, and merely offers limited emotionally expressive variations. As part of the Central Innovation Program for Small and Medium-sized Enterprises (SMEs) (German: Zentrales Innovationsprogramm Mittelstand - ZIM), Aristech worked on the EASY - Expressive Articular SYnthesis for audio books - project together with the Technical University of Dresden. The goal was to narrate audio books with TTS voices which convey emotions realistically.

Aristech was responsible for an automatic semantic text analysis including emotion extraction, and responsible for backing the audio book with music and sound effects during this project.

The Technical University of Dreseden was responsible for rendering the text with different voices and speech styles.

Collaboration partner:

Sponsored by:

Published on 8/31/2018

Cookie settings