What's in an accent?

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.

What Do We See in Them? Identifying Dimensions of Partner Models for Speech Interfaces Using a Psycholexical Approach

“…These results mirror earlier work showing stronger lexical alignment in interactions with basic systems [99] and later work showing stronger alignment in interactions with avatar based virtual agents versus human dialogue partners [12]. People have also demonstrated a higher likelihood of using American English terms to describe objects when interacting with an American accented speech system compared to an Irish accented speech system [40]. Design cues used to signal and encourage anthropomorphism also infuence changes in language behaviour.…”

“…Although partner models are seen as infuential in HHD and HMD [16,38,40,52], studies in HMD tend to be relatively broad and unspecifc when scoping the concept. Research has identifed that users tend to see systems as at-risk listeners [97] or basic conversational partners [16] when compared to humans.…”

“…Speech agent interaction research has emphasised the importance of user's perceptions toward a system's competence and communicative ability as a dialogue partner (i.e. their partner models), impacting speech choices [16,40] and the types of tasks that users entrust speech agents with [49,88]. However, while the role of partner models is widely acknowledged [16,39,40,88,97], the concept is currently underdefned with regards to its underlying dimensions.…”

Mental Workload and Language Production in Non-Native Speaker IPA Interaction

“…This is similar to the mechanisms for adaptation proposed in psycholinguistics literature, which highlight the tendency for partners to select their language with the perceptions of their audience in mind, termed audience design [6]. A similar effect has recently been shown to operate on lexical choice in speech interface interaction, whereby participants interacting with a US-accented system were significantly more likely to use US lexical terms than when interacting with an Irish-accented system [12].…”

“…Even then, the volume of work on this topic is limited [9], with a focus on comparing language production in interactions between human-machine and human-human interlocutors. Such work finds that users tend to vary significantly in how they interact with systems compared to how they interact with humans [2], although similar mechanisms may influence language production [11,12]. People tend to use fewer topic shifts, use more words, as well as use fewer anaphora and fillers when interacting with computers as opposed to human partners.…”