We report on community-centered, collaborative research that weaves together HCI, natural language processing, linguistic, and design insights to develop spoken language technologies for unwritten languages. Across three visits to a Banjara farming community in India, we use participatory, technical, and creative methods to engage community members, collect spoken language photo annotations, and develop an information retrieval (IR) system. Drawing on orality theory, we interrogate assumptions and biases of current speech interfaces and create a simple application that leverages our IR system to match fluidly spoken queries with recorded annotations and surface corresponding photos. In-situ evaluations show how our novel approach returns reliable results and inspired the co-creation of media retrieval use-cases that are more appropriate in oral contexts. The very low (< 4h) spoken data requirements makes our approach adaptable to other contexts where languages are unwritten or have no digital language resources available.

In this paper we develop approaches to automatic speech recognition (ASR) development that suit the needs and functions of under-heard language speakers. Our novel contribution to HCI is to show how community-engagement can surface key technical and social issues and opportunities for more effective speech-based systems. We introduce a bespoke toolkit of technologies and showcase how we utilised the toolkit to engage communities of under-heard language speakers; and, through that engagement process, situate key aspects of ASR development in community contexts. The toolkit consists of (1) an information appliance to facilitate spoken-data collection on topics of community interest, (2) a mobile app to create crowdsourced transcripts of collected data, and (3) demonstrator systems to showcase ASR capabilities and to feed back research results to community members. Drawing on the sensibilities we cultivated through this research, we present a series of challenges to the orthodoxy of state-of-the-art approaches to ASR development.

What do pedestrian crossings, ATMs, elevators and ticket machines have in common? These are just a few of the ubiquitous yet essential elements of public-space infrastructure that rely on physical buttons or touchscreens; common interactions that, until recently, were considered perfectly safe to perform. This work investigates how we might integrate touchless technologies into public-space infrastructure in order to minimise physical interaction with shared devices in light of the ongoing COVID-19 pandemic. Drawing on an ethnographic exploration into how public utilities are being used, adapted or avoided, we developed and evaluated a suite of technology probes that can be either retrofitted into, or replace, these services. In-situ community deployments of our probes demonstrate strong uptake and provide insight into how hands-free technologies can be adapted and utilised for the public domain; and, in turn, used to inform the future of walk-up-and use public technologies.

Automatic Speech Recognition (ASR) researchers are turning their attention towards supporting low-resource languages, such as isiXhosa or Marathi, with only limited training resources. We report and reflect on collaborative research across ASR & HCI to situate ASR-enabled technologies to suit the needs and functions of two communities of low-resource language speakers, on the outskirts of Cape Town, South Africa and in Mumbai, India. We build on longstanding community partnerships and draw on linguistics, media studies and HCI scholarship to guide our research. We demonstrate diverse design methods to: remotely engage participants; collect speech data to test ASR models; and ultimately field-test models with users. Reflecting on the research, we identify opportunities, challenges, and use-cases of ASR, in particular to support pervasive use of WhatsApp voice messaging. Finally, we uncover implications for collaborations across ASR & HCI that advance important discussions at CHI surrounding data, ethics, and AI.

Many of us daily encounter shadow and reflected light patterns alongside macro-level changes in ambient light levels. These are caused by elements—opaque objects, glass, mirrors, even clouds—in our environment interfacing with sunlight or artificial indoor lighting. Inspired by these phenomena, we explored ways of creating digitally-supported displays that use light, shade and reflection for output and harness the energy they need to operate from the sun or indoor ambient light. Through a set of design workshops we developed exemplar devices: SolarPix, ShadMo and GlowBoard. We detail their function and implementation, as well as evidencing their technical viability. The designs were informed by material understandings from the Global North and Global South and demonstrated in a cross-cultural workshop run in parallel in India and South Africa where community co-designers reflected on their uses and value given lived experience of their communication practices and unreliable energy networks.

Working with emergent users in two of Mumbai’s slums, we explored the value and uses of photovoltaic (PV) self-powering digital materials. Through a series of co-design workshops, a diary study and responses by artists and craftspeople, we developed the PV-Pix concept for inter-home connections. Each PV-Pix element consists of a deformable energy harvesting material that, when actuated by a person in one home, changes its physical state both there and in a connected home. To explore the concept we considered two forms of PV-Pix: one uses rigid materials and the other flexible ones. We deployed two low-fidelity prototypes, each constructed of a grid of one PV-Pix type, in four slum homes over a four week period to further understand the usability and uses of the materials, eliciting interesting inter-family communication practices. Encouraged by these results we report on a first-step towards working prototypes and demonstrate the technical viability of the approach.

There is widespread concern over the ways speech assistant providers currently use humans to listen to users' queries without their knowledge. We report two iterations of the TalkBack smart speaker, which transparently combines machine and human assistance. In the first, we created a prototype to investigate whether people would choose to forward their questions to a human answerer if the machine was unable to help. Longitudinal deployment revealed that most users would do so when given the explicit choice. In the second iteration we extended the prototype to draw upon spoken answers from previous deployments, combining machine efficiency with human richness. Deployment of this second iteration shows that this corpus can help provide relevant, human-created instant responses. We distil lessons learned for those developing conversational agents or other AI-infused systems about how to appropriately enlist human-in-the-loop information services to benefit users, task workers and system performance.

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.

“Designed in California” is a brand statement used by high-tech manufacturers to denote provenance and cachet of digital innovation and modernity. In this paper, we explore philosophically alternate design perspectives to those this statement embodies, reporting and reflecting on a long-term multi-sited project that seeks to diversify future-making by engaging communities of “emergent” users in “developing” regions. We argue that digital technologies are typically created with a design lens firmly focused on “first world” populations, assuming a base set of cultural norms, resource availabilities, and technological experience levels that do not strongly align with those of emergent users. We discuss and argue for inclusive technology design methods, present our approach, and detail indicative results and case studies as an example of the potential of these perspectives in uncovering radical innovations. Distilling findings and lessons learned, we present a methodology—itinerative design—that pivots between emergent user communities across multiple regions, driving digital innovation through the periphery of mainstream design’s current remit.

We present APPropriate -- a novel mobile design to allow users to temporarily annex any Android device for their own use. APPropriate is a small, cheap storage pod, designed to be easily carried in a pocket or hidden within clothing. Its purpose is simple: to hold a copy of the local content an owner has on their mobile, liberating them from carrying a phone, or allowing them to use another device that provides advantages over their own. Picking up another device when carrying APPropriate transfers all pertinent content to the borrowed device (using local no-cost WiFi from the APPropriate device), transforming it to give the impression that they are using their own phone. While APPropriate is useful for a wide range of contexts, the design was envisaged through a co-design process with resource-constrained emergent users in three countries. Lab studies and a subsequent deployment on participants' own devices identified key benefits of the approach in these contexts, including for security, resource sharing, and privacy.

This paper gives an interwoven account of the theoretical and practical work we undertook in pursuit of designing co-located interactions. We show how we sensitized ourselves to theory from diverse intellectual disciplines, to develop an analytical lens to better think about co-located interactions. By critiquing current systems and their conceptual foundations, and further interrelating theories particularly in regard to performative aspects of identity and communication, we develop a more nuanced way of thinking about co-located interactions. Drawing on our sensitivities, we show how we generated and are exploring, through the process of design, a set of co-located interactions that are situated within our social ecologies, and contend that our upfront theoretical work enabled us to identify and explore this space in the first place. This highlights the importance of problem framing, especially for projects adopting design methodologies.

We reflect on activities to design a mobile application to enable rural people in South Africa's Eastern Cape to record and share their stories, which have implications for 'cross-cultural design,' and the wider use of stories in design. We based our initial concept for generating stories with audio and photos on cell-phones on a scenario informed by abstracting from digital storytelling projects globally and our personal experience. But insights from ethnography, and technology experiments involving storytelling, in a rural village led us to query our grounding assumptions and usability criteria. So, we implemented a method using cell-phones to localise storytelling, involve rural users and probe ways to incorporate visual and audio media. Products from this method helped us to generate design ideas for our current prototype which offers great flexibility. Thus we present a new way to depict stories digitally and a process for improving such software.

We describe and reflect on a method we used to evaluate usability and give insights on situated use of a mobile digital storytelling prototype. We report on rich data we gained by implementing this method and argue that we were able to learn more about our prototype, users, their needs, and their context, than we would have through other evaluation methods. We look at the usability problems we uncovered and discuss how our flexibility in field-testing allowed us to observe unanticipated usage, from which we were able to motivate future design directions. Finally, we reflect on the importance of spending time in-situ during all stages of design, especially when designing across cultures.