Category Archives: Wednesday

SD302: A Hike on the Slopes of Uncanny Valley

SUNRISE DISCUSSIONS – Wednesday 26 April 
08:00 – 08:45

The IVR community has created seemingly natural interactions over a couple of turns—in short, faking it. Recent assistants, such as Siri, Alexa, and Google Voice, have tended toward one-shot question/answer approaches that have little dialogue context and multi-modal presentation of information—in short, a smart-Alec with short-term memory problems in a box. This discussion session looks at these trends and ask questions about what people really want from spoken agents and where spoken dialogue systems might be headed.

Presented by: David Attwater

SD303: Patent & IP Update

SUNRISE DISCUSSIONS – Wednesday 26 April 
08:00 – 08:45

The field of intellectual property (IP) is rapidly evolving both with changes in the law and the speech. This interactive discussion provides an overview of the intellectual property issues of automated assistants, protections available for these technologies, IP risks in commercialization, and current best practices for protecting speech technologies and defending against assertion, as well as strategies for the future.

Presented by: Steven M. Hoffberg, Jordan Cohen

KEYNOTE PANEL – The Future of Conversational Robots

KEYNOTE – Wednesday 26 April 
09:00 – 10:00

Amazon Echo, Google Home, and the Jibo social robots promise to enable users to perform many useful tasks, including control devices connected with the internet such as home appliances and industrial robots; educate and train users with self-improvement activities; entertain users with passive and active games and activities; perform transactions such as pay bills; shop for goods and services; solve problems such as diagnose illnesses; debug and repair products; calculate taxes; mediate conflicts; and protect and secure home and business. This panel begins with short demonstrations of products, followed by a discussion of issues such as these: What is a conversational robot and how do they differ from other current interactive technologies? What capabilities do conversational robots have beyond just searching the web, answering questions, and presenting information? How can you replace negative perceptions of robots with positive insights? What technologies, tools, and standards will to enable widespread creation and distribution of content for conversational robots?

Presented by: Leor Grebler, Sunil Vemuri, Roberto Pieraccini

B301: Blending Self-Service & Assisted Service

Track B: SELF-SERVICE TECHNOLOGIES – Wednesday 26 April 
10:45 – 11:30

When using an automated speech system, there is often a need for an “assist” from a human. This discussion identifies benefits of cooperation between virtual assistants and human agents to improve the customer experience and, ultimately, create a more informed self-service experience. We also explore the latest trends toward a blended approach and the latest systems designed to enable seamless interplay between virtual assistants and humans and discuss how human agents organically train automated machines.

Presented by: Paul Tepper

A301: Speech Analysis Detects Early-Stage Diseases

Track A: INNOVATIVE USES OF ASR – Wednesday 26 April 
10:45 – 11:30

It is remarkably difficult to detect Alzheimer’s and other diseases early enough to do anything about them. Canary Speech and Cobalt Speech and Language have joined forces to develop the speech recognition technologies for these applications. Learn how ASR is being developed to detect early signs of Alzheimer’s and other diseases while using the unique business model developed by two companies.

Presented by: Jeff Adams

D301: Now Trending: Voice Biometrics

Track D: INFRASTRUCTURE – Wednesday 26 April 
10:45 – 11:30

An overview of voice biometrics, including how the technology uniquely balances security and convenience, while bringing a new level of personalization to customer service; We compare the features and benefits of voice biometrics technology to other authentication technologies, and explore use cases for biometrics and real-world examples of deployments – from large financial institutions, telecom providers, government organizations, and more; We discuss how consumer behavior and preferences impact adoption of voice biometrics.

Presented by: Advait Deshpande

D302: An Intelligent Assistant for High-Level Task Understanding

Track D: INFRASTRUCTURE – Wednesday 26 April 
11:45 – 12:30

Current intelligent agents (IAs) are limited to specific domains. However, people often engage in activities that span multiple domains and have to manage context and information transfer on their own. An ideal personal IA would be able discover such (recurring) activities and learn their structure, to support interaction with the user. The result would be custom applications supporting personal activities. We discuss our work creating agents that autonomously configure spoken language interfaces for this purpose.

Presented by: Alexander Rudnicky