EmojiVoice: Towards long-term controllable expressivity in robot speech

TL;DR

EmojiVoice is a customizable TTS toolkit enabling social robots to produce long-term, expressive speech with fine-grained control, demonstrated through three diverse case studies showing improved expressivity in storytelling.

Contribution

The paper introduces EmojiVoice, a novel TTS toolkit with emoji-prompting for controllable expressivity in robot speech, suitable for offline deployment and real-time use.

Findings

Emoji prompting enhances long-term speech expressivity in storytelling.

Expressive voice was less preferred in robot assistant scenarios.

Real-time speech generation is feasible with lightweight Matcha-TTS backbone.

Abstract

Humans vary their expressivity when speaking for extended periods to maintain engagement with their listener. Although social robots tend to be deployed with ``expressive'' joyful voices, they lack this long-term variation found in human speech. Foundation model text-to-speech systems are beginning to mimic the expressivity in human speech, but they are difficult to deploy offline on robots. We present EmojiVoice, a free, customizable text-to-speech (TTS) toolkit that allows social roboticists to build temporally variable, expressive speech on social robots. We introduce emoji-prompting to allow fine-grained control of expressivity on a phase level and use the lightweight Matcha-TTS backbone to generate speech in real-time. We explore three case studies: (1) a scripted conversation with a robot assistant, (2) a storytelling robot, and (3) an autonomous speech-to-speech interactive agent. We found that using varied emoji prompting improved the perception and expressivity of speech over a long period in a storytelling task, but expressive voice was not preferred in the assistant use case.