Integrated Speech and Gesture Synthesis

TL;DR

This paper introduces a unified neural model for simultaneous speech and gesture synthesis, improving naturalness and efficiency over traditional pipeline approaches by integrating both modalities into a single system.

Contribution

The authors propose a novel integrated speech and gesture synthesis model based on modified neural speech-synthesis engines, demonstrating comparable quality with faster synthesis and fewer parameters.

Findings

Participants rated the integrated model as comparable to state-of-the-art pipeline systems.

The integrated model achieved faster synthesis times.

The model used significantly fewer parameters than traditional pipelines.

Abstract

Text-to-speech and co-speech gesture synthesis have until now been treated as separate areas by two different research communities, and applications merely stack the two technologies using a simple system-level pipeline. This can lead to modeling inefficiencies and may introduce inconsistencies that limit the achievable naturalness. We propose to instead synthesize the two modalities in a single model, a new problem we call integrated speech and gesture synthesis (ISG). We also propose a set of models modified from state-of-the-art neural speech-synthesis engines to achieve this goal. We evaluate the models in three carefully-designed user studies, two of which evaluate the synthesized speech and gesture in isolation, plus a combined study that evaluates the models like they will be used in real-world applications -- speech and gesture presented together. The results show that participants rate one of the proposed integrated synthesis models as being as good as the state-of-the-art pipeline system we compare against, in all three tests. The model is able to achieve this with faster synthesis time and greatly reduced parameter count compared to the pipeline system, illustrating some of the potential benefits of treating speech and gesture synthesis together as a single, unified problem. Videos and code are available on our project page at https://swatsw.github.io/isg_icmi21/