Google Cloud’s Speaker ID adds speech identification

Get a free Techzine subscription!

Contact Centers can now have callers authenticate by voice.

Google has announced that their customers who use their Contact Center AI service to automate their call center operations can now enable Speaker ID. This is a machine learning-based voice identification feature that allows callers to authenticate themselves easily by saying a few words.

The Contact Center AI platform uses Google’s Dialogflow CX conversational artificial intelligence engine to automate customer service interactions with callers. The ML engine enables virtual agents that can handle routine calls and text message queries. They can also and provide answers to common customer queries. If the caller has a more complex problem, it can hand the call over to a human agent.

Introducing Agent Assist

Now those human agents have access to a new feature in Contact Center AI, called Agent Assist. It relies on natural language processing to understand the caller’s intent and provide helpful resources to the agent so they can deal with them more efficiently.

Calum Barnes, Product Manager of Speaker ID, described the service in a blog post. “Speaker ID brings Google’s speech identification technology directly to Google Cloud customers and our contact center partners. Instead of subjecting callers to tedious and circuitous authentication processes, such as phone trees or menus, with Speaker ID, our customers and partners can now initiate service using the most intuitive interface of all: voice.”

“Speaker ID lets your callers authenticate over the phone, using their own voice,” Barnes says. Using machine learning (ML)-based voice identification, Speaker ID identifies and verifies the caller.

Along with full audio integration, Speaker ID also has pre-built Dialogflow CX components available to easily add enrollment and verification flows to existing or new Dialogflow CX bots. Customers can also configure Dialogflow CX to perform passive verification. This provides a speaker validation check based on the caller’s usual interaction with the voice bot. Users don’t need to be prompted or speak a specific phrase.