angle-up angle-right angle-down angle-left close user menu open menu closed search globe bars phone store

Interview With an Avatar: A Real-Time Cloud-Based Virtual Dialog Agent for Educational and Job Training Applications

Author(s):
Ramanarayanan, Vikram; Pautler, David; Lange, Patrick; Suendermann-Oeft, David
Publication Year:
2018
Report Number:
RM-18-02
Source:
ETS Research Memorandum
Document Type:
Report
Page Count:
18
Subject/Key Words:
Avatars (Computer graphics) Cloud Computing Crowdsourcing Help Assistant-Language-Enabled and Free (HALEF) Immersive Computing Technology Job Interviews Job Training Real-Time Systems Simulation-Based Assessment Spoken Dialog System (SDS) Workplace Assessment and Training

Abstract

Recent advances in immersive computing technology have the potential to accelerate development of engaging intelligent agents that can guide one or multiple phases of learner instruction as well as formative or summative assessment. In this spirit, we present a multimodal dialog system equipped with a virtual human avatar interlocutor. The agent, developed in Unity with WebGL support, leverages the Help Assistant–Language-Enabled and Free open-source cloud-based standard-compliant dialog framework. We designed and implemented a conversational job interview task based on the proposed framework. In this scenario, the avatar plays the role of an interviewer and responds to user input in real time to provide an immersive user experience. Initial crowdsourcing experiments demonstrate the promise of this approach.

Read More