Speech Interfaces for Equitable Access to Information Technology

Abstract

Speech recognition has often been suggested as a key to universal information access, as the speech modality is a "natural" way to interact, does not require literacy, and relies on existing telephony infrastructure. However, success stories of speech interfaces in developing regions are few and far between. The challenges of literacy, dialectal variation, and the prohibitive expense of creating the necessary linguistic resources are intractable using traditional techniques. We present our findings evaluating a low-cost, scalable speech-driven application designed and deployed in a community center in rural Tamil Nadu, India, to disseminate agricultural information to village farmers. (c) 2007 by The Massachusetts Institute of Technology.

Emergent practices around CGNet Swara, voice forum for citizen journalism in rural India

“…Examples include giving voicemail to homeless individuals in the US [9]; offering ad-hoc group support for NGOs [27]; delivering health information [36]; bringing web content to resource-constrained classroom settings [13]; and exchanging agricultural advice for [32] and by [29] farmers in India.…”

Avaaj Otalo

“…Figure 1 shows Avaaj Otalo in use. Prior research on voice-based user interfaces for the developing world has largely focused on providing access to static information resources [15,21]. A few research efforts have sought to develop voice message forums, both for the developed world [18,24] and for the developing world [4,9].…”

Language Science and Language Technology in Africa: Festschrift for Justus C. Roux

“…Designing effective voice user interfaces (VUIs) is even more challenging when very little is known about users' needs and/or preferences when accessing information via technologies such as IVRs Sharma Grover & Barnard 2011a). Previous research has indicated the potential of telephone-based services for stimulating socio-economic growth through access to information (Sharma Grover & Barnard 2011b), as well as some of the challenges associated with designing VUIs Sharma Grover & Barnard 2011a;Plauché & Nallasamy 2007) for low-literate users, and taking into account dialectal differences and cost, respectively. Yet very few companies in South Africa specialise in multilingual IVR development; the commercial demand for such services seems to be limited; and very little research data is available in this domain.…”