Interactive Voice Response Applications in University Environment
Explore the world of Interactive Voice Response (IVR) applications in an educational setting through examples like SMS communication, voice applications, advantages of voice and text, technology core features, and social good initiatives. Discover how IVR technology is used for educational purposes and social impact, along with a case study on voice-based messaging in Ghana. Learn about creating voice applications for help lines and community information systems, leveraging Asterisk software, and implementing IVR for various social services.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
IVR Applications Lecture 7: CSE 490c 10/10/2018 University of Washington, Autumn 2018 1
Announcements Homework 3 One page user manual for SMS Application Programming Assignment 1 You should have SMS communication working You should be planning the business logic of the application 10/10/2018 University of Washington, Autumn 2018 2
Interactive Voice Response (IVR) Voice versus text Structure of Voice Applications Examples 10/10/2018 University of Washington, Autumn 2018 3
Voice and Text Advantages of Text Advantages of Voice 10/10/2018 University of Washington, Autumn 2018 4
Interactive Voice Response Applications we hate Robo calls Automatic surveys Customer service help lines 10/10/2018 University of Washington, Autumn 2018 5
Core Technology Convert Telephony to software Asterisk: Open Source Software Implementation of a Private Branch Exchange Operations Make calls Receive calls Route calls Record speech Playback speech Manipulate speech files Detect key presses Automatic Speech Recognition (ASR) 10/10/2018 University of Washington, Autumn 2018 6
IVR for Social Good Voice based messaging Help Lines Community Information Systems Redress and reporting Social Networks 10/10/2018 University of Washington, Autumn 2018 7
Voice based messaging Mobile Midwife application Motech, Ghana, 2010 Strong formative work SMS and Voice calls Alerts and reminders Actionable information Educational information Messages in English, Senya, Fante Topic identification Expensive to create local language messages Strong preference for voice messages Cost issues not resolved 10/10/2018 University of Washington, Autumn 2018 8
Help lines HealthLine Pakistan (2008) Health information by voice Touch tone Press 1 for Malaria, Press 2 for Diarrhea, Press 3 for Speech What disease do you want to hear about? Poor man s speech recognition Phonemes trained on English Represent Sindhi words with phonemes 10/10/2018 University of Washington, Autumn 2018 9
Community Information Systems Awaaz De Voice Forum Farmer information recorded by farmers Farmers call in to leave advice on farming Other farmers call in to listen to advice Farmers preferred getting information from other farmers as opposed to agricultural experts Neil Patel developed Awaaz De as PhD project from Stanford, moved to Gujarat and started a social enterprise 10/10/2018 University of Washington, Autumn 2018 10
Redress and Reporting CGNet Swara Report local problems Ila Dhageyso Reporting problems to Government of Somaliland Government reporting lines Challenge of processing voice input Need for taking actions Governments don t always want to hear this info 10/10/2018 University of Washington, Autumn 2018 11
Voice Based Social Networks Posting voice messages Jokes, Songs, Poems Listening to posts of others Mechanisms for selecting posts, ranking posts Content moderation is a challenge User moderation can work Example systems Sangeet Swara Baang Deployments have had viral growth Strong uptake by visually impaired 10/10/2018 University of Washington, Autumn 2018 12
IVR Challenge 10/10/2018 University of Washington, Autumn 2018 13
Sustainability: Who pays Cost per connection relatively high Service is a public good Government covers the cost Donors Pay Subsidies Service generates income Advertising models Linked to income generation Service supports a business Job Listings Service delivers value to operator Agricultural cooperative Information reporting 10/10/2018 University of Washington, Autumn 2018 14