Interactive Voice Response Service Research Articles

Interactive Voice Response Service to Improve High School Students Covid-19 Literacy in Burkina Faso: A Usability Study.

Mobile technology is widely used in healthcare. However, designers and developers in many cases have focused on developing solutions that are often tailored to highly literate people. While the advent of the pandemic has called for people to seek and use Covid-19 related information to adapt their behaviors, it is relatively difficult for low literate to get easily access to health information through digital technologies. In this study, we present a Mobile based Interactive Voice Response service designed particularly for low-literate people which provides validated Covid-19 related health information in local African languages. We conducted a field study, among high school students, through a usability study to assess users' perception. The service received an excellent numerical usability score of 78.75.

A Mobile Education and Social Support Group Intervention for Improving Postpartum Health in Northern India: Development and Usability Study.

BackgroundStructural and cultural barriers limit Indian women’s access to adequate postnatal care and support despite their importance for maternal and neonatal health. Targeted postnatal education and support through a mobile health intervention may improve postnatal recovery, neonatal care practices, nutritional status, knowledge and care seeking, and mental health.ObjectiveWe sought to understand the feasibility and acceptability of our first pilot phase, a flexible 6-week postnatal mobile health intervention delivered to 3 groups of women in Punjab, India, and adapt our intervention for our next pilot phase, which will formally assess intervention feasibility, acceptability, and preliminary efficacy.MethodsOur intervention prototype was designed to deliver culturally tailored educational programming via a provider-moderated, voice- and text-based group approach to connect new mothers with a social support group of other new mothers, increase their health-related communication with providers, and refer them to care needed. We targeted deployment using feature phones to include participants from diverse socioeconomic groups. We held moderated group calls weekly, disseminated educational audios, and created SMS text messaging groups. We varied content delivery, group discussion participation, and chat moderation. Three groups of postpartum women from Punjab were recruited for the pilot through community health workers. Sociodemographic data were collected at baseline. Intervention feasibility and acceptability were assessed through weekly participant check-ins (N=29), weekly moderator reports, structured end-line in-depth interviews among a subgroup of participants (15/29, 52%), and back-end technology data.ResultsThe participants were aged 24 to 28 years and 1 to 3 months postpartum. Of the 29 participants, 17 (59%) had their own phones. Half of the participants (14/29, 48%) attended ≥3 of the 6 calls; the main barriers were childcare and household responsibilities and network or phone issues. Most participants were very satisfied with the intervention (16/19, 84%) and found the educational content (20/20, 100%) and group discussions (17/20, 85%) very useful. The participants used the SMS text messaging chat, particularly when facilitator-moderated. Sustaining participation and fostering group interactions was limited by technological and sociocultural challenges.ConclusionsThe intervention was considered generally feasible and acceptable, and protocol adjustments were identified to improve intervention delivery and engagement. To address technological issues, we engaged a cloud-based service provider for group calls and an interactive voice response service provider for educational recordings and developed a smartphone app for the participants. We seek to overcome sociocultural challenges through new strategies for increasing group engagement, including targeting midlevel female community health care providers as moderators. Our second pilot will assess intervention feasibility, acceptability, and preliminary effectiveness at 6 months. Ultimately, we seek to support the health and well-being of postpartum women and their infants in South Asia and beyond through the development of efficient, acceptable, and effective intervention strategies.

Agromet Advisory Services for Climate Smart Agriculture

Climate smart agriculture (CSA) is a strategy for guiding the transformation and reorientation of agricultural production in light of the new realities of climate change. CSA manage the climate risks by adapting and building resilience of agricultural and food security system to climate change at multiple levels. CSA involves dissemination of the advance weather information to the farmers through different state of art information technology (SMS, apps and e-mail) are being taken to control and minimize of loss of crop due to pest and diseases incidences. Increase agricultural productivity and incomes; adapt to and build resilience to climate change; and reduce or eliminate greenhouse gas emissions from agriculture are the three pillars of the CSA. Under the Gramin Krishi Mausam Sewa (GKMS) scheme, the Agrometeorological Advisory Service (AAS) of the India Meteorological Department (IMD), Ministry of Earth Sciences (MoES), collects and organises climate/weather, soil, and crop information and combines it with weather forecast to assist farmers in making management decisions. Gramin Krishi Mausam Sewa (GKMS), District Agro-Met Units (DAMUs), and the IMD Mausam Website are examples of CSA projects. They deliver crop-specific alerts to farmers using meteorological parameters and a variety of print, visual, radio, and IT-based media, including short message service (SMS) and Interactive Voice Response Service (IVRS). This CSA will assist farmers in anticipating the occurrence of pests and illnesses, allowing for the scientific and sensible scheduling of preventative actions.

Information and Communication Technologies to Provide Agricultural Advice to Smallholder Farmers: Experimental Evidence from Uganda

Agricultural advisory services generally rely on interpersonal knowledge transfers by agricultural extension agents who visit farmers to provide information. This approach is not always effective and has proved hard to scale sustainably, particularly in highly dispersed smallholder farming systems. Information and communication technologies (ICTs) have been advanced as a promising way to overcome many of the problems associated with conventional agricultural extension. We evaluate the effectiveness of an ICT‐mediated approach to deliver agricultural information in a field experiment conducted among small‐scale maize farmers in eastern Uganda. Three complementary technologies designed to address both informational and behavioral constraints to technical change are considered. First, we investigate the effectiveness of audiovisual messages (video) as a means of delivering information on input use and improved maize management practices to farmers. Second, we quantify the additional impact of complementing video with an interactive voice response (IVR) service. Third, we estimate the incremental effect of time‐sensitive short message services (SMS) messages designed to remind farmers about applying key practices at specific points during the season. We find that households that were shown a short video on how to become better maize farmers were performing significantly better on a knowledge test, more likely to apply recommended practices, and more likely to use fertilizer than households that did not view the video. These same households also reported maize yields about 10.5% higher than those that did not view the video. We find little evidence of an incremental effect of the IVR service or SMS reminders.

QoS Estimation and Prediction of Input Modality in Degraded IP Networks

This paper evaluates the impact of combined transcoding and packet loss degradation on speech as input for the interactive voice response service (IVR) and proposes a method for classification of user input according to speech quality. Careful optimization of a communication system and all of its segments need to be considered, as the quality of the user's experience is becoming a more prominent part of the overall acceptance and desirability of modern service. Within our research, emulation environment was developed and the behavior of IVR analyzed under different packet loss and transcoding conditions. A set of frequently-used vocoders was tested on its performance with an automatic speech recognition module under degraded conditions. Further, quality estimation classifier was proposed, based on the Gaussian mixture models to determine best user's input modality. Various train and test parameters were investigated to provide more detailed insight of input quality estimation for IVR service working under error prone conditions.

Linking farmers to markets in Kenya: The evolving KACE model

The Kenya Agricultural Commodity Exchange Limited (KACE) was incorporated in 1992 but formally launched in 1997 to address the challenges facing farmers in Kenya, especially poor smallholder farmers, in accessing input and output markets. A commercial for-profit model was chosen in order to charge clients modest fees for services rendered and raise revenue to sustain the services in the long term. The KACE model has evolved through various stages over time, with KACE developing, testing and experimenting with various platforms to link smallholder farmers to more remunerative markets. This article describes the various platforms, the challenges that were experienced and how they were addressed at each stage in the evolution. Chronologically, these platforms consisted of a physical trading floor, market information points (MIP), information and communication technology (ICT)-based platforms (short messaging service - SMS, interactive voice response service - IVRS, Internet based website and electronic database and radio), market resource centres (MRC), and a market call centre (MCC). Thus, the challenge experienced by KACE has been to find the right mix or portfolio of appropriate and affordable technology platforms, with complementary human skill and capacity, to efficiently manage the technologies, as well as the revenue flows, towards increased technical and financial sustainability. Despite the challenges, the KACE model continues to evolve and function, with a social entrepreneurial spirit of determination, to provide a solution to the social problem of poor smallholder farmers in Kenya, and God and technology willing, in the rest of Africa. The ICT platforms are being upgraded to improve technical and financial performance and efficiency, and the MRC staff are being trained to improve their capacity to generate and manage revenue efficiently.

Instrumentalizing Voice

This article applies Bakhtin’s ideas of “dialogics” and “speech genres” and Bourdieu’s approach to the “linguistic field” in a study of the “instrumentalization” of voice in interactive voice response (IVR) telephony. The article examines two dimensions of voice as it appears in IVR services: technician-led installations and voice branding “on-hold messaging.” It is argued that technician-led installations of IVR are essentially monologic in character. In contrast, voice branding agencies’ IVR reveals a more dialogic form of voice. The article is based on data collected from telephone and face-to-face interviews with staff in both sides of IVR and from an examination of six IVR services of major UK companies. The article assesses the social indexing of recorded voice in IVR by drawing out how particular “speech genre” functions of IVR prompts coincide with accent, gender, and age.

Interactive Voice Response Mashup System for Service Enhancement

Mashup service is common in the realm of web development. Mashup, generally, is a web page that sources two or more data sources to create a new and an improved service. While mashup service is a common phenomenon in the web development scenario, there is no such mashup for services that are based on voice user interface in the Interactive Voice Response (IVR) systems. IVR based telephony services have been popular because they are an easy and a convenient means to inquire, seek information or book services. At the same time frequently used service, like taxi usually has multiple service operators. Though the Same Service is provided by Multiple Operators (SSMO) to the end user, their access points are different and require the user to choose a particular service operator to call. Unlike a web portal or a web mashup, there is no way for the user to comparatively and simultaneously check the offerings from SSMO and choose the best among them. This paper describes a novel approach, based on a recent patent, to create a mashup service by integrating two or more IVR services. Keywords: IVR Mashup, User experience, Telephony channel, service integration.

Enhancing Construction As-Built Documentation Using Interactive Voice Response

This paper utilizes interactive voice response (IVR) technology to enhance progress tracking of projects and as-built documentation. First, possible site events and tracking needs of construction activities have been analyzed based on literature and sample daily progress forms. Accordingly, activity logical-flow diagrams have been developed to guide IVR sessions. Afterward, the IVR technology has been implemented to enhance an existing e-mail-based framework for as-built documentation by integrating a cloud-based IVR service and a customized scheduling application. The IVR features work by either receiving calls from supervisors at any time or by configuring eligible activities to automatically initiate calls to their supervisors. Compared with lengthy e-mails, the IVR sessions are interactive, minimize the questions asked, and allow supervisors to specify site events and any requests for information. Responses are also received instantaneously to update the schedule and visualize the latest as-built information directly on the daily segments of a schedule. The paper contributes to automating site-data collection, designing low-cost voice applications for construction, facilitating bidirectional communication between site personnel and head office, and enhancing project tracking and control.

C1-inhibitor therapy for hereditary angioedema attacks: Prospective patient assessments of health-related quality of life

C1-inhibitor (INH) concentrate, which is recommended as first-line treatment for acute hereditary angioedema (HAE) attacks in many countries, was recently approved in the United States. We sought to solicit patients' feedback about their health-related quality of life (HRQoL) while being treated with C1-INH concentrate for acute HAE attacks under real-world conditions, as well as the personal impact of the availability of C1-INH on lifestyle and mental health domains. Subjects enrolled in an open-label study of C1-INH at 20 U/kg for acute HAE attacks were invited to participate in a prospectively designed survey to solicit "real-time" patient responses that were collected via an interactive voice response service or online with a personal computer. Eighteen subjects submitted 60 quarterly HRQoL and treatment impact survey responses over 29 months. Seventeen of 18 patients responding reported mean short form 12 HRQoL scores that were within a normal range. More than one-half indicated that C1-INH availability made them feel somewhat or much better, and >80% reported having a better outlook on the future and feeling more secure about the danger of life-threatening attacks. These data confirm a high level of HRQoL and a positive impact in lifestyle and emotional domains among patients who were treated for acute attacks of HAE with C1-INH concentrate.

Robust Design and Control of Call Centers with Flexible Interactive Voice Response Systems

We consider the robust design and control of call center systems with flexible interactive voice response (IVR) systems. In a typical call center equipped with an IVR system, customers are handled first by the IVR system, which is a computerized system that often enables customers to self-serve. Those customers whose service cannot be handled by the IVR system are sent to the second stage to be served by agents. To address the design of a call center with a flexible IVR system, we consider a call center whose IVR system can operate in two different service delivery modes that have statistically different outcomes. We formulate a stochastic program to determine the number of agents needed in the second stage as well as the proportion of customers that should be selected for each IVR service mode under different demand levels with the objective of minimizing the total staffing and abandonment costs. We also propose dynamic control policies to achieve the optimal proportions without the knowledge of the exact arrival rate. We show that the staffing levels found by the stochastic program combined with the proposed routing policies are asymptotically optimal in large systems. We present extensive numerical and simulation results to illustrate the effectiveness of the proposed solutions.

Predictors of utilization of an IVR self-monitoring program by problem drinkers with recent natural resolutions

BackgroundAs part of a randomized controlled trial, problem drinkers who recently initiated natural recovery on their own were offered access to an interactive voice response (IVR) self-monitoring (SM) system as a sobriety maintenance tool during early recovery when relapse risk is high. Because observed IVR utilization was variable, predictors of utilization were evaluated to inform knowledge of populations likely to access and use IVR services. MethodsParticipants were 87 untreated community-dwelling adults who recently initiated sobriety following longstanding high-risk drinking practices and alcohol-related problems (M=16.58 years, SD=10.95). Baseline interviews assessed pre-resolution drinking practices and problems, and behavioral economic (BE) measures of reward preferences (delay discounting, pre-resolution monetary allocation). Participants had IVR access for 24 weeks to report daily drinking and to hear weekly recovery-focused messages. ResultsIVR use ranged from 0 to 100%. Frequent (n=28), infrequent (n=42), and non-caller (n=17) groups were identified. Non-callers tended to be younger and to report heavier pre-resolution drinking. Frequent callers (≥70% of IVR days) tended to be older, male non-smokers with higher/stable socio-economic status and lower delay discounting compared to infrequent callers. Premature drop-out typically occurred fairly abruptly and was related to extended binge drinking. ConclusionsCharacteristics common in the untreated problem drinker population were associated with higher IVR utilization. This large under-served population segment can be targeted for lower intensity alcohol interventions using an IVR platform.

Robust Design and Control of Call Centers with Flexible IVR Systems

We consider the robust design and control of call center systems with flexible interactive voice response (IVR) systems. In a typical call center equipped with an IVR system, customers are handled first by the IVR system, which is a computerized system that often enables customers to self-serve. Those customers whose service cannot be handled by the IVR system are sent to the second stage to be served by agents. In order to address the design of a call center with a flexible IVR system, we consider a call center whose IVR system can operate in two different service delivery modes that have statistically different outcomes. We formulate a stochastic program to determine the number of agents needed in the second stage as well as the proportion of customers that should be selected for each IVR service mode under different demand levels with the objective of minimizing the total staffing and abandonment costs. We also propose dynamic control policies to achieve the optimal proportions without the knowledge of the exact arrival rate. We show that the staffing levels found by the stochastic program combined with the proposed routing policies are asymptotically optimal in large systems. We present extensive numerical and simulation results to illustrate the effectiveness of the proposed solutions.

A Preliminary Study of a Cloud-Computing Model for Chronic Illness Self-Care Support in an Underdeveloped Country

Although interactive voice response (IVR) calls can be an effective tool for chronic disease management, many regions of the world lack the infrastructure to provide these services. This study evaluated the feasibility and potential impact of an IVR program using a cloud-computing model to improve diabetes management in Honduras. A single-group, pre-post study was conducted between June and August 2010. The telecommunications infrastructure was maintained on a U.S. server, and calls were directed to patients' cell phones using VoIP. Eighty-five diabetes patients in Honduras received weekly IVR disease management calls for 6 weeks, with automated follow-up e-mails to clinicians, and voicemail reports to family caregivers. Patients completed interviews at enrollment and a 6-week follow-up. Other measures included patients' glycemic control (HbA1c) and data from the IVR calling system. A total of 53% of participants completed at least half of their IVR calls and 23% of participants completed 80% or more. Higher baseline blood pressures, greater diabetes burden, greater distance from the clinic, and better medication adherence were related to higher call completion rates. Nearly all participants (98%) reported that because of the program, they improved in aspects of diabetes management such as glycemic control (56%) or foot care (89%). Mean HbA1c's decreased from 10.0% at baseline to 8.9% at follow-up (p<0.01). Most participants (92%) said that if the service were available in their clinic they would use it again. Cloud computing is a feasible strategy for providing IVR services globally. IVR self-care support may improve self-care and glycemic control for patients in underdeveloped countries.

Home Blood Glucose Prediction: Validation, Safety, and Efficacy Testing in Clinical Diabetes

Patients with diabetes do daily self-monitoring of blood glucose (SMBG). For such patients, we devised an engine that predicts not only the expected blood glucose level at the next meal but also the pending risks of hypoglycemia. The purpose of this study was to validate the predictions and provide evidence of the safety and efficacy of using predicted data in dosing decision support for routine patient care. The prediction engine is a computer program that accesses a central database into which daily records of self-monitored blood glucose data are captured by direct access either across the WWW or by an interactive voice response service on-line 24/7. Validation was done by comparison of predicted values to the subsequently observed data using a Clarke Error Grid. Safety focused on body weight and the frequency of hypoglycemia. Efficacy was judged according to glycated hemoglobin and daily insulin dosages. The experimental design contrasted patients in the tight control (TC) group who had been recently converted to intensified (basal-bolus) therapy with patients in the poor control (PC) group on conventional therapy and who were referred to begin intensified therapy. Both groups accessed the remote database to report their daily SMBG. Predicted glucose values were used in dosing decision support for the PC but not the TC group. Over the 6-month study period a total of 30,129 blood glucose levels were reported by the 54 study patients, and some 24,953 blood glucose predictions were made. Of these, 83% were in the clinically acceptable zones of the Clarke Error Grid. When these data were used for dosing decision support in the PC group, glycated hemoglobin levels fell significantly from 9.7 +/- 1.7% to 7.9 +/- 1.2%, and hypoglycemia dropped fourfold. Total daily insulin doses declined 22%, while body weight remained constant. In the parallel TC group (n = 24), glycated hemoglobin also fell, but only slightly from 7.6 +/- 0.9% to 7.2 +/- 1.1%, while daily insulin doses, rates of hypoglycemia and body weight remained constant. A novel engine is capable of generating meaningful predictions of blood glucose levels. Use of these validated predictions in decision support for managing medication doses proved safe and efficacious.

Analysing interactive voice services

IVR (Interactive Voice Response) services are increasingly prevalent in automated telephone enquiry systems. VoiceXML (Voice eXtensible Markup Language) has become one of the leading languages for IVR. The nature of IVR services is introduced, along with an explanation of how they are represented in VoiceXML. However a VoiceXML description is at a low level, so it is difficult to gain an overview of the service that is offered. There is also no rigorous way to check the integrity of an IVR application. C ress (Chisel Representation Employing Systematic Specification) is a graphical notation for describing services in an abstract, language-independent manner. For this paper, IVR services are described with C ress, and translated into L otos (Language Of Temporal Ordering Specification) for automated analysis. Because of the infinite state space, it is not practicable to formally verify the generated specifications. Instead, the focus is on more practical solutions. The properties of a specification are checked by including observer processes to monitor undesirable situations like repeatedly prompting the user for input. M ustard (Multiple-Use Scenario Test And Refusal Description) is introduced as a language for defining scenario-based tests of services. The approach is illustrated with sample tests of IVR services. It is seen how M ustard helps to build confidence in an IVR application. The paper also introduces a feature concept for IVR, and discusses feature interaction in this context. General categories of IVR feature interaction are presented. It is shown how C ress and M ustard combine to help discover interactions among IVR features.

Integrated web and telephone service creation

We describe a system for creating, maintaining, and analyzing interactive services that require access from multiple devices. The system augments the infrastructure of the World Wide Web with Mawl, an application-oriented language for specifying form-based services in a device-independent manner, and TelePortal, a software/hardware platform that enables telephone access to Web content via standard interactive voice response (IVR) platforms. Service creators link service logic and presentation with templates written in an extension of the HyperText Markup Language (HTML). HTML is extended with marks for dynamic content (Meta-HTML) and with marks specific to a user interface or access device. Documents to be interpreted by TelePortal are written in the Phone Markup Language (PML). Together, Mawl and TelePortal provide a new way to create integrated services, as well as IVR services. The ability to develop such services in a single environment appears to be unique.

A Next Generation Multimedia Call Center for Internet Commerce: IMC

Human assistance, as well as automated service, is necessary for providing more convenient services to customers on the Internet-based commerce system. Call centers have been typically human-based service systems. However, the services of existing public switched telephone network-based call centers are not enough to meet the needs of customers on the Internet. Most of them have been designed without considering the interaction involved in shopping on the Internet. In our research, we design a call center named IMC (Internet-based multimedia call center) that can be integrated with an Internet shopping mall. It contains 2 parts: an Internet multimedia dialogue system and a human agent assisting system. The Internet multimedia dialogue system is an Internet and multimedia version of the interactive voice response service of computer telephony integration-based call centers because it provides access to the multimedia Web page along with the recorded voice explanation through the Internet. The human agent assisting system aims to select the most appropriate human agents in the call center and support them in providing high-quality individualized information for each customer. IMC is a real-time, human-embedded system that can provide high-quality services cost-effectively for Internet commerce.

The Design and Evaluation of Dialogues for Interactive Voice Response Services

Good dialogue design is an essential component in the delivery of new interactive telephone services. It wins a competitive edge by improving the usability of services and reducing the risks of customer dissatisfaction. This paper outlines the steps taken to obtain consistent and effective dialogues across the company through the use of the Dialogues Style Guide, dialogue engineering courses and focus groups. Aspects of dialogue design will be illustrated with examples, trials and services developed within BT. Important results from dialogue studies under BT‘s Strategic University Research Initiative at the Centre for Communication Interface Research (CCIR) at the University of Edinburgh are reported, together with a description of current activities. The achievements of the industry-funded Dialogues 2000 initiative is outlined in its pursuit of dialogue consistency. Currently this organisation has a membership of over 217 companies involved with interactive voice response systems.

Operational and experimental French telecommunication services using CNET speech recognition and text-to-speech synthesis

This paper presents a brief overview of current uses, in 1994–1995, for CNET speech recognition and text-to-speech technologies in Interactive Voice Response Services (IVR) in France. It describes several operational and experimental services, and analyzes field evaluations of some of them. Finally, this paper summarizes recent developments in the CNET speech recognition and text-to-speech technology.