What's in an accent? The impact of accented synthetic speech on lexical choice in human-machine dialogue

TL;DR

This study investigates how accented synthetic speech influences lexical choices in human-machine dialogue, showing that accent affects perceptions of partner knowledge and subsequent language use, with implications for dialogue system design.

Contribution

It demonstrates that synthesis design, specifically accent, impacts lexical choices and partner perception in dialogue, highlighting the importance of accent in shaping interaction dynamics.

Findings

People prefer American English terms with US accented speech.

Accent influences perceived partner knowledge in dialogue.

Synthesis design affects lexical choice and partner modeling.

Abstract

The assumptions we make about a dialogue partner's knowledge and communicative ability (i.e. our partner models) can influence our language choices. Although similar processes may operate in human-machine dialogue, the role of design in shaping these models, and their subsequent effects on interaction are not clearly understood. Focusing on synthesis design, we conduct a referential communication experiment to identify the impact of accented speech on lexical choice. In particular, we focus on whether accented speech may encourage the use of lexical alternatives that are relevant to a partner's accent, and how this is may vary when in dialogue with a human or machine. We find that people are more likely to use American English terms when speaking with a US accented partner than an Irish accented partner in both human and machine conditions. This lends support to the proposal that synthesis design can influence partner perception of lexical knowledge, which in turn guide user's lexical choices. We discuss the findings with relation to the nature and dynamics of partner models in human machine dialogue.