StreetWise

Abstract

This paper explores the use of conversational speech question and answer systems in the challenging context of public spaces in slums. A major part of this work is a comparison of the source and speed of the given responses; that is, either machine-powered and instant or human-powered and delayed. We examine these dimensions via a two-stage, multi-sited deployment. We report on a pilot deployment that helped refine the system, and a second deployment involving the installation of nine of each type of system within a large Mumbai slum for a 40-day period, resulting in over 12,000 queries. We present the findings from a detailed analysis and comparison of the two question-answer corpora; discuss how these insights might help improve machine-powered smart speakers; and, highlight the potential benefits of multi-sited public speech installations within slum environments. CCS CONCEPTS• Information systems → Speech / audio search; • Humancentered computing → Field studies; Interaction paradigms; Sound-based input / output; Interaction techniques.

A Question of Access: Exploring the Perceived Benefits and Barriers of Intelligent Voice Assistants for Improving Access to Consumer Health Resources Among Low-Income Older Adults

“…Therefore, we must also explore designs that can support health information tasks using sporadic internet connections or through mobile connections in the future to address access gaps. For example, some are exploring IVA design approaches in resource-constrained environments (Pearson et al, 2019). We may also consider IVAs that allow for asynchronous voice interactions to allow users to manage internet access more easily.…”

Diversifying Future-Making Through Itinerative Design

“…It should be noted that the other scenarios also stimulated prototypes and deployments (not reported here) with evidence of their value to users and communities. For example, the Audioliser led us to consider the use of speech systems in public settings [33,36]; and, a Google Physical Web trial emerged from the Shopping Beacon scenario [34]. Figure 8 shows the further stages in the continued development, evaluation, refinement and deployment of the Safety Pod scenario.…”

“…In other cycles of the intinerative design process, the work has also led to a phone connectivity toolkit 1 being integrated into an Indic language keyboard application that is actively used by 800,000 people; and, to a series of high-profile research articles (e.g., [20,31,33,37,38]). Such outcomes suggest to us that the process and the perspectives it brings can and do generate ideas that are novel, fresh and useful.…”

An Honest Conversation: Transparently Combining Machine and Human Speech Assistance in Public Spaces

“…While concerns have been widely voiced, then, with regard to such practices in private spaces, in this article we build on our previous work that has shown that direct, overtly humanpowered responses to questions posed to smart speakers in public settings can be of value [26]. Our earlier work explored the installation of voice assistant-type devices across Dharavi, a very large informal settlement in Mumbai, India.…”

“…Here, we investigate whether merging machine and human responses in a single speech appliance can provide benefits in the same setting. We extended the open-source toolkit described in [26] to create a combined machine+human system that we call TalkBack, and deployed ten instances of this in areas of Dharavi for a 25day period. Unique to the TalkBack system is that forwarding questions to humans is an explicit, user-driven choice.…”