Video: Demo: Gridspace Grace Autonomous Call Center Agent
Learn more about AI and intelligent agent design at the next SpeechTEK conference.
Read the complete transcript of this clip:
Anthony Scodary: Call centers are, in a way, the mechanization or industrialization of conversational commercial speech, and as we have millions of Americans and many more millions world-wide working in call centers, it is the industrialization of speech that is responsible in part for the growth of the commercial enterprise. What I want to show you is an example of the industrialization of that industrialization. I'm going to show you something not many people have seen. It's our work on dialogue systems, taking these fundamental building blocks and building a autonomous call center agent named Grace.
[Begin Demo]
Grace: Good morning, thanks for calling Harper Valley National Bank. My name is Grace. How can I help you today?
Chris Johnson: Yes, last night I was entertaining some clients and I think I left my wallet at the restaurant and to be safe I want to replace my debit card.
Grace: Before I can help you with that I'll have to authenticate you, okay?
Chris Johnson: Okay.
Grace: May I ask who I'm talking with, first and last name, please?
Chris Johnson: My name is Chris Johnson.
Grace: Mmhm. And what was the name of your first pet?
Chris Johnson: Professor Sparkles.
Grace: Okay great, that's Professor Sparkles. All right, let me check that information you gave me. Okay, Mr. Johnson, just checking your name. Looking through your security questions. Professor Sparkles. Oh my God, that's precious.
Chris Johnson: He was precious.
Grace: Okay, I just submitted your request. All right, thank you Mr. Johnson, you are authenticated. Okay, should I go ahead and submit that request for your new debit card?
Chris Johnson: Yes.
Grace: Okay. Let's check on that card. Just seeing how long that'll take. Okay, so I expedited that brand new card. I also went ahead and waived the normal fee for you,
Chris Johnson: Oh, thank you.
Grace: It should arrive in three business days, sir.
Chris Johnson: Great.
Grace: Is there anything else I can do for you?
Chris Johnson: Yeah, I should probably make sure no money was stolen from my old card. Can you tell me my checking account balance?
Grace: Mmhm. Okay, Mr. Johnson, I'm going to look up that checking balance for you. Okay, bringing up your checking account. Okay. All right Mr. Johnson, I see here that your checking account balance is $37.35.
Chris Johnson: Okay, that's.
Grace: Can I help you with anything else?
Chris Johnson: I would like to transfer a thousand dollars for my savings to my--
Grace: Would you like help with something else?
Chris Johnson: Yes, I would like to transfer $1,000 from my savings to my checking account.
Grace: I'd be happy to make that transfer Mr. Johnson.
Chris Johnson: Thank you.
Grace: Just to confirm you want me to move $1,000 from your savings to your checking?
Chris Johnson: Yes.
Grace: Right?
Chris Johnson: Yes.
Grace: All right, Mr. Johnson, I'm initiating that transfer. Okay, Mr. Johnson, I submitted that. It should go through in 3-5 business days.
Chris Johnson: Thank you.
Grace: Would you like help with something else?
Chris Johnson: No, that does it. I appreciate it.
Grace: Mmhm. Okay sir, have a great day!
Chris Johnson: You too, goodbye!
[END DEMO]
Anthony Scodary: All right, wasn't Grace great? So in that conversation you saw probably a dozen or so transactions all featuring those building blocks that we talked about, entities, meaning, emotional content, and a lot of fundamental dialogue acts, and flowing through the system. First, you know you're hitting speech recognition, recognizing the words that are said, then a dialogue system with the bot, and then our speech synthesis model, and then that goes through the internet through phones, through the air, through sound waves, into the brain, and then back out through the vocal tract all the way back to our speech recognition.
This is a very complex, nonlinear system, where there are going to be errors in every step of this process. Understanding the conversation holistically, and understanding these fundamental atoms that make up a dialogue, is absolutely essential to both being able to handle the kind of unpredictability and nonlinearity of the call, and to handle this transaction in a way that is task-oriented and reaches a fundamental conclusion.
Related Articles
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.
06 Sep 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.
30 Aug 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.
21 Aug 2019
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.
16 Aug 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.
08 Aug 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.
26 Jul 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.
19 Jul 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.
12 Jul 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.
05 Jul 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.
28 Jun 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.
21 Jun 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.
14 Jun 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.
10 Jun 2019