▼ Scroll to Site ▼

Video: More Targeted Knowledge Can Improve Today's VAs

Learn more about conversational systems at the next SpeechTEK conference.

Watch Deborah Dahl's complete keynote from SpeechTEK 2019, Just Like Talking to a Person: How to Get There From Here, in the SpeechTEK Video Portal.

Interested in attending a SpeechTEK event? Visit SpeechTEK.com to sign up for conference alerts, discounts, and more.

Read the complete transcript of this clip:

Deborah Dahl: One thing that's really great about today's artificial systems is they know a lot, and we saw that example with the Phillies. They know a lot about generic information, and there are a lot of resources for generic information. I think knowledge graphs are the most popular.

There's also the DBpedia, which is kind of a structured version of Wikipedia. There's Wolfram Alpha and another academic one called Cyc. There's a lot of generic knowledge available in structured forms that we can tap into to build these systems. But they're already pretty good with generic knowledge.

Where they start to be less good is with enterprise information. You can't just go to some website and find out about your company's products and inventory and employees and retail locations. That's all something that has to be taught to the virtual assistant if you want it to build an enterprise application that could answer those kinds of questions. So, most of the time a lot of that information is in databases, and the problem is hooking that database up to the virtual assistant, and that can involve a lot of work.

The other kind of information that's hard to get is personal information about the user. That's "How do I take my coffee, what's my route to work?" Any kind of personal information that's useful in an application. We don't have a good way to acquire that.

I can see three ways to acquire it; none of them are perfect. One is when the user sets up an application, go through some kind of quiz, which can get really tedious. "What's your name? Do you have any siblings? "What kind of car do you drive? "Tell me about your route to work."

People don't have a lot of patience for that. The second one is the system can learn through interacting. And that can be used to learn things that maybe the user isn't even aware of, like their average commute time.

Maybe they don't really pay attention to it, but the system can learn that. The problem with that is it needs to be set up to do that, and it might take awhile to learn all the things that it would be good for it to learn. And the third way to get information about the user is mining the web for information about you. That's pretty creepy. I don't think you would be very happy if your virtual assistant suddenly said, "Oh, how's your sister Gretchen? "I see she posted on Facebook."

People are used to the automated systems knowing where they are, so that's not too creepy. But there's a lot of information about everybody on the web and you have to be careful about mining it.

SpeechTek Covers
Free
for qualified subscribers
Subscribe Now Current Issue Past Issues
Related Articles

Video: How to Assess if a Conversational UI Is Right for You

Allstate Conversational Designer Katie Lower outlines working models for assessing the viability of a conversational interface with multiple teams within an organization in this clip from her presentation at SpeechTEK 2019.

Video: How to Map the Customer Journey (and Why)

Allstate Conversational Designer Katie Lower defines the customer journey map as a visualization of the customer's process and explains why it's valuable in this clip from her presentation at SpeechTEK 2019.

Video: Implications of a Speech UI

Grand Studio Lead Designer Diana Deibel discusses the ethical implications of speech UIs and remaining cognizant of the inherent human elements of speech and conversation in this clip from her presentation at SpeechTEK 2019.

Video: Enabling Transparency in VUI Design

Grand Studio Lead Designer Diana Deibel discusses multiple approaches to making VUI design transparent--the Google vs. Alexa, system-initiated vs. user-initiated--in this clip from her presentation at SpeechTEK 2019.

Video: What Is the Minimum Amount of Speech for Authentication?

Pindrop Director of Product Marketing Ben Cunningham discusses best practices for voice authentication in IVR design in this clip from his panel at SpeechTEK 2019.

Video: Demo: Gridspace Grace Autonomous Call Center Agent

Gridspace Co-Founder and Co-Head of Engineering Anthony Scodary demonstrates Grace, Gridspace's new automonous call center agent, in this clip from his keynote at SpeechTEK 2019.

Video: Current Challenges in Enterprise Speech Tech

Orion Labs Head of Product Ellen Juhlin and Voicea CMO Cory Treffiletti discuss persisting challenges in speech-to-text, AI identifying intent, user expectations, and more in enterprise speech tech applications in this clip from their panel at SpeechTEK 2019.

Video: Emerging Trends in Speech Tech Adoption

451 Research Senior Analyst Raul Castanon discusses new findings of a recent survey on speech technology adoption in the enterprise and how adoption of devices in the consumer space have impacted enterprise adoption in this clip from his panel at SpeechTEK 2019.

Video: How to Make Your VUI Inclusive

Grand Studio Lead Designer Diana Deibel discusses best practices for culturally inclusive access in voice UI design in this clip from her presentation at SpeechTEK 2019.

Video: How to Interpret the Transaction in Every Conversation

Gridspace Co-Founder and Co-Head of Engineering Anthony Scodary discusses the transactional nature of speech and how that understanding impacts effective, AI-driven call center analytics in this clip from his keynote at SpeechTEK 2019.

Video: 6 Ways to Improve VAs via Better Language Understanding

Conversational Technologies Principal Deborah Dahl lays out a plan for making more virtual assistants more effective in this clip from her keynote at SpeechTEK 2019.

Video: The Current State of Conversational Systems

Conversational Technologies Principal Deborah Dahl discusses the state of the art for the three pillars of conversational systems in this clip from her keynote at SpeechTEK 2019.

Video: How to Leverage Text-Independent Biometrics

Nuance Communications' Roanne Levitt delineates the differences between text-dependent and text-independent biometrics and what the advent of text-independent means for IVR applications in this clip from SpeechTEK 2019.