What's in an accent? The impact of accented synthetic speech on lexical choice in human-machine dialogue
This addresses the problem of designing effective synthetic speech for human-machine interaction, showing that accent influences user language choices, though it is incremental in exploring partner models.
The study investigated how accented synthetic speech affects lexical choice in human-machine dialogue, finding that people are more likely to use American English terms with a US-accented partner than an Irish-accented one, both with humans and machines.
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.