Mobile Voice Conference 2015
Creating an Advanced Dialog Application, An in-depth look at the process [PDF]
[PPTX version with embedded WMV windows videos]
This one hour presentation to the full conference was a joint effort by the AVIOS Advanced Dialog Group. It examines a single turn in an advanced dialog from Business through Architecture and ending in an actual Implementation.
Note: The implementation tools, a.k.a. ourCassandra Project is going public soon!)
Mobile Voice Conference 2013
Advanced Dialog Workshop: Hands-on experience with a conversational framework
This was the presentation for the 1 hour and 40 minute workshop. It gives a quick overview of the ejTalker platform. It also explains some techniques and concepts for Rules, Adaptation, Variability and Memory.
Be sure to checkout (on the last slide) the other experts in the field that contributed to this workshop!
Note: the server mentioned in the slides was local to the classroom and is not accessable from the cloud. (The Cassandra Project exists to change that!)
Mobile Voice Conference 2013
Mastering Multiple Modalities
This presentation examines the interplay of truly multimodal conversation management
SpeechTEK Conference 2012
Heading Toward Intelligent Agents: Examining the Path Ahead
Session SD101:
What makes artificial agents intelligent? We perform group thought experiments where we assume that individual technical or resource obstacles can be removed. What if we could find (or build) vast amounts of marked conversational data and “remember” all individual user-agent interactions over all time? What if speech synthesis could be as subtle and nuanced as human speech? What if speech recognition worked at human levels of accuracy? What if we could add some new magical component? Where is the biggest gap in today’s intelligent, conversational, synthetic agent platform?
Mobile Voice Conference 2012
Multi-turn Context Sensitive Exchanges: They change the game
SpeechTEK Conference 2011
Personal Agents Get Smarter and Controlling Conversational Chaos
Session D303 – Smart Synthetic Agents:
The assistive agent designed for Baby Boomers and beyond illustrates the various challenges and solutions pertaining to the idea of natural conversation.
SpeechTEK Europe 2010: Avatar Challenge
Experts’ Prize Winner
Cassandra is one manifestation of the ejTalker conversation engine. ejTalker coordinates all the aspects of the conversation: Speech recognition, synthesis, avatar display, Multimodal interactions (e.g. touch screens). Inherent in the engine is a persistent memory of previous conversational states and data, inheritance of base behaviors, adaptive behaviors (ellipsis), response generation variation, etc.
| 