Progressivity for voice interface design

Abstract

Drawing from Conversation Analysis (CA), we examine how the orientation towards progressivity in talk-keeping things movingmight help us better understand and design for voice interactions. We introduce progressivity by surveying its explication in CA, and then look at how a strong preference for progressivity in conversation works out practically in sequences of voice interaction recorded in people's homes. Following Stivers and Robinson's work on progressivity, we find our data shows: how non-answer responses impede progress; how accounts offered for non-answer responses can lead to recovery; how participants work to receive answers; and how, ultimately, moving the interaction forwards does not necessarily involve a fitted answer, but other kinds of responses as well. We discuss the wider potential of applying progressivity to evaluate and understand voice interactions, and consider what designers of voice experiences might do to design for progressivity. Our contribution is a demonstration of the progressivity principle and its interactional features, which also points towards the need for specific kinds of future developments in speech technology. CCS CONCEPTS • Human-centered computing → Natural language interfaces.

Improving Worker Engagement Through Conversational Microtask Crowdsourcing

“…We estimate the conversational style of workers as follows: 1) For each interaction, we provide one or two options that lead the worker to the next interaction (we call these actual options). These options serve the purpose of ensuring progressivity in the interaction [11,35]. Note that actual options are invisible to workers.…”

Exploring How Older Adults Use a Smart Speaker–Based Voice Assistant in Their First Interactions: Qualitative Study

“…Although existing voice assistants are being called conversational agents, promising to enable human-like conversation with a device, they are in fact not truly conversational in nature. Instead, simple and constrained request-response structures are the norm, rarely including a realistic dialog [ 20 ]. Lastly, research has explored the utility and usability of voice assistants as an assistive technology [ 21 , 22 ].…”

Speech diversity and speech interfaces

“…Significant work in the CUI field has observed user's experiences with interfaces like IPAs, identifying issues such as the need to consider the potential gulf of expectation due to the humanness of such systems versus their actual functionality [8,16,19], the need to learn how to interact effectively [16] as well as how social and multiparty contexts impact the type of interactions we have with IPAs [8,10,24]. This work focuses almost entirely on users without significant accessibility requirements.…”