The 2016 Speech Industry Star Performers: [24]7

Article Featured Image

[24]7 Brings Deep Neural Networks to IVR Systems

While Apple’s Siri and Microsoft’s Cortana brought deep neural networking to consumer applications, [24]7 is the first to introduce it in interactive voice response (IVR) systems. [24]7 increased speech recognition accuracy in IVR systems to better than 95 percent last year when it integrated Microsoft’s Deep Neural Networks (DNN) into its Customer Engagement Platform. For some customers, that represented a 25 percent increase, prompting many observers to hail the move as a gigantic stride forward for companies looking to deliver better self-service to customers.

Deep neural networking, as it applies to speech recognition, seeks to emulate the human brain in understanding and processing the spoken word. For customers dialing into IVR systems, deep neural networking results in fewer out-of-grammar errors, mismatches, and no-matches, reducing the need to zero out or speak to an agent, according to Patrick Nguyen, chief technology officer at [24]7. “As a consumer, you’ll find that the IVR understands you more reliably,” he says. “DNN will make the experience much better for the customer.”

That’s the hope at Avis Budget Group, the first customer to use [24]7’s speech solutions with DNN technology. “Our customers call from all types of noisy environments, and IVR systems have struggled in the past to make out the customer intent over and above the cacophony of airports and other busy public spaces,” said Gerard Insall, chief information officer at Avis Budget Group, in a statement. “This new platform will help us to counter many of these issues and enable our customers to effortlessly complete their transactions in the IVR.”

A few years ago, deep neural networking worked its way into a number of consumer speech applications, including Microsoft’s Cortana mobile assistant and Skype Translator, but [24]7 was the first to apply it in a business context. Pairing IVR with deep neural networking was “long overdue,” Nguyen says.

It also wasn’t unexpected. The integration of the two technologies continues a close relationship between Microsoft and [24]7 that dates back to 2012, when Microsoft turned over most of its enterprise IVR business to [24]7. As part of that deal, the two firms also agreed to a shared technology road map and a long-term intellectual property licensing agreement.

And though [24]7’s IVR is the first to roll out deep neural networking, Nguyen expects such technology to be the future of IVR systems. “With the improvements in performance and accuracy we’re seeing, it will increase people’s comfort using speech self-service,” he says. “People will be much more willing to use IVRs when dealing with companies.”

Beyond its moves into neural networking, [24]7’s other innovations in speech technology include the infusion of predictive analytics and natural language understanding into omnichannel customer engagements. Last year, for example, the company produced the industry’s first natural language technology that spans both virtual agent and speech self-service. It ensures that customers will receive the same answers whether they pose their questions to a virtual assistant on the Web site or to the IVR on the phone. Both channels draw from and feed into the same natural language source.

Also this past year, [24]7 became the only speech company capable of fully integrating virtual assistant technology into a suite of self-service and assisted-service offerings.

“[24]7 has been an early innovator in applying advanced predictive modeling and data analytics to customer engagement,” said PV Kannan, CEO and cofounder of [24]7, in a statement. “Adding DNN is a major milestone in that lineage. With the increasing proliferation of mobile devices and branded mobile apps, we know that more difficult journeys will go to self-service, so major companies need these next-generation solutions to meet customer expectations effectively.”

Jeff Kagan, a wireless and technology industry analyst, agrees. He calls the fusion of neural networking with IVR and virtual assistant technologies “one of the hottest areas of development today,” noting that these modalities “will be the mainstream way we communicate with the world all around us.”

The technology, he adds, is more effective and easier to use today than it was just a few years ago. “This kind of technology will grow and let us use it in an increasing number of things we do every day,” he says.

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues