Interactive Voice Response (IVR) Systems as Automatic Speech Recognition (ASR) Comes of Age

1998 ◽  
Vol 42 (4) ◽  
pp. 444-447 ◽  
Author(s):  
Daryle Gardner-Bonneau ◽  
Cristina Delogu ◽  
Chuck Green ◽  
Lydia Volaitis ◽  
Martha Lindeman ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Interactive Voice Response ◽  
Commercial Use ◽  
The Impact ◽  
Potential Customers ◽  
Workplace Speech ◽  
Ivr Systems ◽  
Made In ◽  
Voice Response

While interactive voice response (IVR) systems were rapidly making their way into the workplace, speech scientists were working hard to improve the performance of automatic speech recognition (ASR) systems to foster their acceptance among potential customers. In the last five years, great strides have been made in this regard, and the commercial use ASR is on the rise. The purpose of this panel is to explore the impact that ASR is (or is not) having on the design of IVR systems that were envisioned originally to operate solely via touch-tone input.

Telephone-Based Menus: Evidence that Broader is Better than Deeper

1997 ◽  
Vol 41 (1) ◽  
pp. 315-319 ◽  
Author(s):  
Robert A. Virzi ◽  
John S. Huitema
Keyword(s):  
Interactive Voice Response ◽  
Item Selection ◽  
Menu Item ◽  
Ivr Systems ◽  
Better Than ◽  
Voice Response ◽  
Menu Item Selection

Recent guidelines intended for designers of telephone menus for Interactive Voice Response (IVR) systems advocate keeping menus to four or fewer items. Additional items, the guidelines recommend, should appear on a secondary menu accessible from the first. The current study compared this deep-menu approach to a broad-menu approach wherein all the items appear on a single menu. Item selection times favored the broad-menu approach for both repeated and unique trials, casting some doubt on the validity of this particular guideline.

scholarly journals An analysis of the impact of implementing a new interactive voice response system (IVR) on client experience in the Canadian banking industry

2021 ◽  
Author(s):  
Priscilla Manatsa
Keyword(s):  
Banking Industry ◽  
Interactive Voice Response ◽  
Research Question ◽  
Client Experience ◽  
Use Of Technology ◽  
Net Promoter ◽  
The Impact ◽  
Canadian Banking ◽  
Voice Response

Banks are constantly competing to find new ways to satisfy clients and meet their growing, heterogenous needs. Clients can access round the clock banking services worldwide. One way to access information is through Interactive Voice Response (IVR) systems. This research is an analysis of the process of implementing an IVR system and the impact on client experience using the case study of a Canadian bank. The research question is: “What is the impact of an IVR system upgrade on client experience in the Canadian banking industry?” The Productivity Paradox and the Unified Theory of Acceptance and Use of Technology model (UTAUT) are leveraged and a thematic analysis of the feedback provided from Net Promoter Score (NPS) surveys is done. The results show that although the IVR system can be an attractive automation interface for clients, there are many unanswered concerns about customer satisfaction as demonstrated by NPS feedback.

scholarly journals The Trustworthiness of Voice Assistants in the Context of Healthcare Investigating the Effect of Perceived Expertise on the Trustworthiness of Voice Assistants, Providers, Data Receivers, and Automatic Speech Recognition

2021 ◽  
Vol 3 ◽  
Author(s):  
Carolin Wienrich ◽  
Clemens Reitelbach ◽  
Astrid Carolus
Keyword(s):  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Emerging Market ◽  
Individual Characteristics ◽  
Healthcare Sector ◽  
Sensitive Data ◽  
Future Technology ◽  
Health Related ◽  
Theoretical Line ◽  
The Impact

As an emerging market for voice assistants (VA), the healthcare sector imposes increasing requirements on the users’ trust in the technological system. To encourage patients to reveal sensitive data requires patients to trust in the technological counterpart. In an experimental laboratory study, participants were presented a VA, which was introduced as either a “specialist” or a “generalist” tool for sexual health. In both conditions, the VA asked the exact same health-related questions. Afterwards, participants assessed the trustworthiness of the tool and further source layers (provider, platform provider, automatic speech recognition in general, data receiver) and reported individual characteristics (disposition to trust and disclose sexual information). Results revealed that perceiving the VA as a specialist resulted in higher trustworthiness of the VA and of the provider, the platform provider and automatic speech recognition in general. Furthermore, the provider’s trustworthiness affected the perceived trustworthiness of the VA. Presenting both a theoretical line of reasoning and empirical data, the study points out the importance of the users’ perspective on the assistant. In sum, this paper argues for further analyses of trustworthiness in voice-based systems and its effects on the usage behavior as well as the impact on responsible design of future technology.

scholarly journals Impact of a mobile phone-based interactive voice response software on tuberculosis treatment outcomes in Uganda (CFL-TB): a protocol for a randomized controlled trial

Trials ◽  
2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Dathan Mirembe Byonanebye ◽  
Hope Mackline ◽  
Christine Sekaggya-Wiltshire ◽  
Agnes N. Kiragga ◽  
Mohammed Lamorde ◽  
...  
Keyword(s):  
Randomized Controlled Trial ◽  
Treatment Outcomes ◽  
Interactive Voice Response ◽  
Controlled Trial ◽  
Treatment Success ◽  
Treatment Completion ◽  
Randomized Controlled ◽  
Tb Treatment ◽  
The Impact ◽  
Voice Response

Abstract Background Throughout the last decade, tuberculosis (TB) treatment success has not surpassed 90%, the global target. The impact of mobile health interventions (MHIs) on TB treatment outcomes is unknown, especially in low- and middle-income countries (LMICs). MHIs, including interactive voice response technology (IVRT), may enhance adherence and retention in the care of patients with tuberculosis and improve TB treatment outcomes. This study seeks to determine the impact of IVRT-based MHI on TB treatment success (treatment completion and cure rates) in patients with TB receiving care at five public health facilities in Uganda. Methods We used a theory-based and human-centered design (HCD) to adapt an already piloted software to design “Call for life-TB” (CFL-TB), an MHI that utilizes IVRT to deliver adherence and appointment reminders and allows remote symptom reporting. This open-label, multicenter, randomized controlled trial (RCT), with nested qualitative and economic evaluation studies, will determine the impact of CFL-TB on TB treatment success in patients with drug-susceptible TB in Uganda. Participants (n = 274) at the five study sites will be randomized (1:1 ratio) to either control (standard of care) or intervention (adherence and appointment reminders, and health tips) arms. Multivariable regression models will be used to compare treatment success, adherence to treatment and clinic appointments, and treatment completion at 6 months post-enrolment. Additionally, we will determine the cost-effectiveness, acceptability, and perceptions of stakeholders. The study received national ethical approval and was conducted in accordance with the international ethical guidelines. Discussion This randomized controlled trial aims to evaluate interactive voice response technology in the context of resource-limited settings with a high burden of TB and high illiteracy rates. The software to be evaluated was developed using HCD and the intervention was based on the IMB model. The software is tailored to the local context and is interoperable with the MHI ecosystem. The HCD approach ensures higher usability of the MHI by integrating human factors in the prototype development. This research will contribute towards the understanding of the implementation and impact of the MHI on TB treatment outcomes and the health system, especially in LMICs. Trial registration ClinicalTrials.govNCT04709159. Registered on January 14, 2021.

scholarly journals Towards an Automatic Speech-Based Diagnostic Test for Alzheimer’s Disease

2021 ◽  
Vol 3 ◽  
Author(s):  
Roozbeh Sadeghian ◽  
J. David Schaffer ◽  
Stephen A. Zahorian
Keyword(s):  
Speech Recognition ◽  
Diagnostic Test ◽  
Automatic Speech Recognition ◽  
Recognition System ◽  
Theory And Practice ◽  
Linguistic Features ◽  
Automatic Speech Recognition System ◽  
Non Invasive ◽  
Considerable Work ◽  
The Impact

Automatic Speech Recognition (ASR) is widely used in many applications and tools. Smartphones, video games, and cars are a few examples where people use ASR routinely and often daily. A less commonly used, but potentially very important arena for using ASR, is the health domain. For some people, the impact on life could be enormous. The goal of this work is to develop an easy-to-use, non-invasive, inexpensive speech-based diagnostic test for dementia that can easily be applied in a clinician’s office or even at home. While considerable work has been published along these lines, increasing dramatically recently, it is primarily of theoretical value and not yet practical to apply. A large gap exists between current scientific understanding, and the creation of a diagnostic test for dementia. The aim of this paper is to bridge this gap between theory and practice by engineering a practical test. Experimental evidence suggests that strong discrimination between subjects with a diagnosis of probable Alzheimer’s vs. matched normal controls can be achieved with a combination of acoustic features from speech, linguistic features extracted from a transcription of the speech, and results of a mini mental state exam. A fully automatic speech recognition system tuned for the speech-to-text aspect of this application, including automatic punctuation, is also described.

Sign in / Sign up

Export Citation Format

Share Document