Tech delivers a more human 311

Tech delivers a more human 311

Dallas has upgraded its city information phone system with technology that listens, understands and replies to callers with conversational dialogue.

The system allows callers to speak naturally when making a request instead of having to press a number or be prompted to say a specific phrase.

“We want to reinvent the relationship people have with technology by having technology behave more like a human,” said Robert Weideman, the executive vice president and general manager of the enterprise division at Nuance.

Nuance’s conversational interactive voice response (IVR) software (coined “Easy Speak” by Dallas311) is housed on servers like any other business software and is connected to the city’s phone system. When a caller dials 311 the software answers the phone and a human-synthesized voice says, “Thanks for calling Dallas311, how may I help you?”

Weideman said the required response to this question is the big upgrade -- because there is not a required response. Someone having trouble with a neighbor’s loud dog could say, “A dog is barking in my back yard, it’s really annoying, I need someone to help me,” and the system would know to transfer the call to animal control.

“Our primary goal with the new IVR system from Nuance is to make it easy, fast and convenient for people to get information,” Dallas311 Assistant Director Margaret Wright said in a statement. “Adding natural language capabilities to our IVR allows us to quickly get callers to the right place to find what they need, minimizing their time on the phone. It also cuts the time that our city agents spend redirecting and transferring calls and allows them to focus on answering questions,” she said.

Conversational call systems started to take off about three years ago, Weideman said. The improvements came from consumer expectations supported by advances in technology. Better natural language understanding and dialogue helped, but so did improved cloud resources. IVR relies on data, he said, and the more data a city has on conversations, then the better the call will be.

Older automated phone systems that ask a caller to press a number for a particular service don’t scale well when there are many options; and systems that require a particular phrase are tripped up by anything other than what they’re designed to recognize, Weideman said.

But then Siri showed up on mobile phones and people expected to be able to talk to their technology. Automated phone systems soon caught up. “It moved from being a niche market to being a mainstream market very quickly,” he said, “in a matter of months.”

Nuance’s technology is used not just for Dallas311, but also at Amtrak, the Department of Veterans Affairs and Domino’s Pizza.

Editor's note: This story was changed Nov. 29 to clarify the origin of the 'Easy Speak' name.

About the Author

Matt Leonard is a reporter/producer at GCN.

Before joining GCN, Leonard worked as a local reporter for The Smithfield Times in southeastern Virginia. In his time there he wrote about town council meetings, local crime and what to do if a beaver dam floods your back yard. Over the last few years, he has spent time at The Commonwealth Times, The Denver Post and WTVR-CBS 6. He is a graduate of Virginia Commonwealth University, where he received the faculty award for print and online journalism.

Leonard can be contacted at mleonard@gcn.com or follow him on Twitter @Matt_Lnrd.

Click here for previous articles by Leonard.


inside gcn

  • artificial intelligence (ktsdesign/Shutterstock.com)

    Machine learning with limited data

Reader Comments

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above

More from 1105 Public Sector Media Group