Home  Cassandra  Essays  Video  Presentation  News  FAQ  About


ejTalk News

What's New

ejTalk engine is featured in an extended session at MobileVoice 2013


Advanced Dialog Workshop: A hands-on experience with a new speech dialog framework

ejTalk's Emmett Coin with the help of other members of the AVIOS Advanced Dialog Group presented a hands-on workshop that allowed attendees to experiment with the ejTalk language and framework.

View presentation here

Mobile Voice Conference site

Emmett Coin presents at SpeechTEK 2012


Heading Toward Intelligent Agents: Examining the Path Ahead

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?

conference site here

SpeechTEK 2011


Emmett Coin presents "Personal Agents Get Smarter: Controlling Conversational Chaos"

The assistive agent designed for Baby Boomers and beyond illustrates the various challenges and solutions pertaining to the idea of natural conversation. Problems such as adaptation to task familiarity, conversational move differences as a function of domain distance and history, and the automatic modulation of transitional pleasantries are discussed. Learn about the dilemmas ahead for advanced dialogue systems and how to solve them in a modular, comprehensible way.

conference site here

Cassandra wins 2010 SpeechTEK Avatar Challenge!


ejTalk is Experts' Prize Winner!

Jim Larson, SpeechTEK Europe Conference Chair said:

"Cassandra, the female avatar from ejTalk, caught the attention of many people. Cassandra contains a sophisticated artificial intelligence engine that enables the avatar to converse with - and not just speak to - the user."

See more at the SpeechTEK conference site.

Emmett Coin (our Industrial Poet) at Mobile Voice Conference 2010


Emmett will describe how to deal with conversations about tables of data (think spreadsheets or multi-column lists) in a generic way. Cassandra will of course present some of the examples. This talk references the "Cassandra Spaces Out" video below.

Slides here

Mobile Voice Conference site

Cassandra Spaces Out!


Another cool demo of Cassandra on YouTube. This one focuses on table data ... this time she goes 'round and 'round about the planets!

See the video here

Cassandra enters the SpeechTEK Avatar Challenge


Our very own Cassandra has entered the ruthless world of pageants. You can see her on the SpeechTEK competition page (as well as in our demo section on our site).

Her entry is an example of how she could assist (tutor?) on a subject such as plays. She uses data of the sort that is available in various "student notes" sources that are available on the web and in books. That data was structured semantically in XML and she uses that to converse about the elements of the play.

SpeechTEK 2009


Emmett Coin talks about "New Dialog Engine Paradigms"

The rate of improvement in the richness and complexity of human-computer dialogue is slowing. Why? Doesn’ t the end user want more sophistication, power, and naturalness? Or, with current technology, is it just too difficult to make anything much more complicated? As developers, what incremental design upgrade could you use today? Do we know what steps to take? As a business paying for the development of a voice system, what more could a system do for your customers? If there is a will in the community to do better, then why aren’ t we? What should our next steps be?

conference site here

Voice Search Conference 2009


Emmett Coin presents "Synthetic Agent Relationship Adaptation Via Meta-Dialog: What people expect from an intelligent agent"

Slides here

Example audio here

SpeechTEK 2008


Emmett Coin presents "Advancing Toward Intelligent Agents"

Voice applications began as almost pure speech recognition systems: speaking choices, numbers, etc. Primitive directed dialogues followed. Now many applications support some sort of mixed initiative as they progress toward less rigid behaviors. Sadly, these methods are already failing to meet the expectations of users, not to mention leading to paralyzing complexity for developers. Going forward, voice systems will incorporate other existing and proven technologies to make applications smarter. These technologies have the potential to dramatically reduce the complexity of development for today’s sophisticated voice applications. This session will compare and contrast the benefits and limitations of these technologies ranging across natural language processing, rule-based and case-based reasoning, statistical, and connectionist (neural net) approaches.

conference site here

SpeechTEK 2007


Emmett Coin discusses "Enhancing Recognition Using Pre- and Post-ASR Manipulation"

The basic automatic speech recognition (ASR) result string is sufficient for most tasks. But in longer sessions or in more challenging environments an application can benefit greatly with even small amounts of error reduction. This presentation describes some computationally lightweight post-ASR methods that use standard, readily available ASR result information to enhance performance. These techniques can improve out-of-vocabulary (OOV) rejection, improve the correct recognition of marginal results when there are expectations, and salvage parts of utterances.

conference site here

A Fresh Look

Welcome to ejTalk's brand new website. We hope you enjoy the new design and we encourage you to browse the links. Start with the philosophy, read about our family, learn why Cassandra is so special and keep up to date with the current issues we face in our Blog section.

The News portion of the site is meant to keep you updated on the latest developments we've made. As our first order of business, we'd like to introduce you to Cassandra.

She just learned about dates and times. Emmett talks a little bit about the process behind this simple, yet challenging feat in the Essay Section.