ICTworks

Interactive Voice Response (IVR) systems have demonstrated that they provide an opportunity for a low-literate audience to express themselves and interact with information technology systems. However, to achieve such goals in a development setting requires a low-cost system that allows participation of multiple stakeholders in the design process.

In RASP-IVR: A Low Cost Interactive Voice Response System, we describe a low-cost IVR hardware system called RASP-IVR that runs on a Raspberry PI and a local GSM modem. RASP-IVR is an open source appropriate system engineered to nurture community driven solutions. We have open-sourced our system and are working with a Rwandan community-based organization to test our system in the field.

The RASP-IVR Solution

The “RASP-IVR” name was chosen because it was built on the Raspberry Pi, a low-cost, Linux-based, single board computer. The OS is based on RASPBX with a few customizations and libraries to better support IVR interactions.

The system consists of a Raspberry Pi model 3 and a GSM mobile telephone modem. The GSM modem interfaces with an Asterisk server. The Asterisk server can be managed using FreePBX web interface to create and customize the IVR tree or voice over IP (VoIP) parameters. We have added scripts using open source libraries to extend RASPBX to support Voice messages, SMS, and local SIP transfers.

The Asterisk server can connect the GSM call to the local or global VoIP network based on the requirements. The VoIP calls can be routed to various extension based on the clients touch tone input or answered through SIP clients like Yate, Zoiper among others using a desktop or a mobile device through a local SIP account.

Additionally, the VoIP call can be transferred to external services like Twilio to use their cloud-based services e.g. Speech to text engine or cloud storage if needed. However, RASP-IVR is self-sufficient for participatory design or for small-scale deployments.

RASP-IVR is a very low-cost system and it consumes very little power. Our system can be set up for $50, i.e. $35 for a Raspberry PI and $15 for the GSM Modem. The system’s capability can be enhanced by connecting two or more modems allowing for more concurrent calls and call routing.

The Benefits of RASP-IVR

RASP-IVR opens the possibility of creating custom applications that can support contextually relevant challenges using its voice and text messaging platforms. The RASP-IVR enables features such as automatic redirecting of calls, user selected content, recording voice content from callers, text message-based interaction, data collection, and personalized content based on caller ID.

However, we are reflective that IVR based systems like all technology needs to be designed to magnify existing human development efforts. While there are caveats discussed further below, advantages of IVR-based systems include the following.

• A purely voice-based system appeals to low-literate users as compared to text-message or web-based applications.
• IVR systems are accessed through the already familiar process of calling on widely available mobile phones.
• The mobile phone access can be more private and less stigmatizing than physical visits to sensitive services such as mental health counseling or family planning.
• Caller ID allows the IVR system to call back dropped calls and to connect activity from the same phone across different calls.
• Lastly, the voice signal itself contains useful information about the speaker including estimates of age, weight, gender, stress, and other health factors.

Use Cases for RASP-IVR

We have been working with a few partners in the health sector in Rwanda. Our partners have existing face-to-face operations and we hope to build systems to extend the coverage and the reach of their services. IVR can reach clients who cannot travel to existing centers providing extensions, albeit limited, of their existing services.

Interestingly, one NGO partner periodically travels to outlying villages and views the IVR as a tool for driving visitors to these outreach activities.

The IVR can reduce the workload of staff through automated services that cover outside of normal hours or collect and analyze user data. One partner will use this feature to automate reporting to donor sponsors.

Another partner views the IVR as part of a larger transition from paper to electronic health records (EHR). The IVR could be integrated with the EHR system and a web application where the IVR collects caller data which prompts the web application to pull up the client EHR before speaking with a counselor. The call is followed up with a text message to the client and another message to the field office closest to the client.

Challenges of Using IVR in Development

Against these benefits, there are, however, some caveats. The IVR system is language specific and prompts need to be recorded in the different languages and dialects of the user population. While the phone interface is familiar, IVR systems are inhibited by the social and cultural norms of developing communities.

Users more familiar with face-to-face interaction may not be receptive to automated interactions and data queries. Indeed, one partner anticipates that they will get the best response after their clients are shown how to use the IVR system during face-to-face meetings.

We also found that access to phones themselves are a limitation for low-resource users. Phones are not always charged due to cost and availability of electricity. Many times phones are shared so that the same phone might be used by different users and a given user might use different phones. Follow up messages and calls may not reach the intended person.

Further, the use of a shared phone can prompt interest and suspicion about who is being called. Finally, the IVR systems raise a number of privacy concerns from how collected data is stored, transmitted, and reported to how one user is prevented from accessing another’s data.

From the developer side, the current system requires programming expertise which may not be readily available for a CBO. We found that not all modem dongles worked with the system and it was trial and error to find a model that worked correctly.

In some cases, it was a hardware issue where the dongle would not communicate with the Raspberry Pi. In others, it was a network issue: One service provider did not transfer the touch tone signals in mobile-to-mobile calls (including calls to the GSM dongle).

The system, at present, can handle one call at a time and is not appropriate for high-calling volume deployments. For our partners who anticipate modest volumes the RASP-IVR is appropriate. If volume were to grow, they could justify a transfer to one of the more scalable solutions.

Adapted from RASP-IVR: A Low Cost Interactive Voice Response System, by Vikram Kamath Cannanure and Timothy X Brown of Carnegie Mellon University