Video: Enabling Transparency in VUI Design
Learn more about VUI design at the next SpeechTEK conference.
Read the complete transcript of this clip:
Diana Deibel: When you're enabling transparency, there's the Alexa Skills versus the Google Duplex kind of way of thinking of it, which is also the user-initiated versus system-initiated approach. But you can do this with system-initiated too.
Alexa is always, very obviously, contained. So, when you say, "Hey Alexa, open up this skill, Let's do this," the user is initiating it. They know they're talking to a machine. There's no mystery there.
With something like Google Duplex, it was basically trying to trick people into not knowing that it was a machine. And people got super creeped out by that because we weren't being clear that this is a machine talking to them.
I've also done a ton of these outbound robot-calls and something I found--just crazy--was that, we had to, because again of HIPAA and health rules, we had to get certain pieces of information before we could disclose health stuff, and when you're calling somebody, you don't necessarily know who you're gonna get.
So, there was one phone call that we did for a very stringent healthcare system, who needed not only the date of birth, but also the social security number of the person before they could disclose any health information. And upon hearing this, the whole design team was like, "What? No one's ever gonna give that over the phone."
But we were able to build enough trust by saying things like, "Hey, I'm calling from this particular doctor, from this particular health system, for this person. Are you this person?" And if they said, "Yes," we would say "Okay. I really want to give you some health information but I can't because of the laws and we want to make sure that we're not disclosing your information with somebody who's not you. So the only way that I can check that is by checking information that I have in my system. The information I have in my system is your birthdate and your social security number. Can you verify those for me?"
An extraordinary amount of people verified that. We would have over 30% acceptance rate, which to me is insane, that sounds like a phishing scam. It does not sound like something you would ever do. But, because we were able to tell them who we were, why we needed the information, that it was for their protection and their privacy, people were willing to disclose it.
Another thing to sort of answer for yourself is having the system answer, "Why do I want your information and what am I gonna do with it?" So the same sort of thing with that call. We were telling them, "Here's why I need this information. Then we check it against our records to make sure that you are who you say you are. And if I don't know that, then I won't give out your information."
So, that's really helpful people know you're not just taking it and then going and doing whatever with it. I'm just, "I just need your social security number, don't worry about it." And then how do I know what I know about you? That goes back to that data source. How do I know that you like dogs? Well, if I tell you I got it from your Facebook page, this is out in the public, fine. Then at least I know maybe I need to make that private. Or great, I don't care, that's out in the world. I'm really happy about that.
But if you're just telling me that you know that I like dogs, that's where I start to get creeped out, that maybe you're able to access things that I don't want you to access or that I didn't allow you. That's when your phone's listening to you and you start to get creeped out.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Conversational Technologies Principal Deborah Dahl explains how more targeted enterprise knowledge could make VAs more effective in organizations in this clip from her keynote at SpeechTEK 2019.
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.