Ericsson and Vodafone Demonstrate AI-Powered Call Translation

Ericsson and Vodafone Demonstrate AI-Powered Call Translation

Vodafone and Ericsson have partnered to trial network-native artificial intelligence for voice services.

In laboratory conditions, the companies demonstrated two AI-powered services: real-time noise cancellation and live language translation during mobile calls.

The trial was designed to show how AI could improve the experience of a standard mobile phone call. Real-time noise cancellation is intended to provide clearer audio, while in-call translation is designed to help people communicate across language barriers. Vodafone said the services do not require specialized applications or new phone hardware.

The demonstration combined a Vodafone-developed application server and AI engines with Ericsson’s IP Multimedia Subsystem (IMS). APIs were used to connect the telecommunications and AI components. Ericsson said this architecture enables the network to apply AI-based processing to voice calls as they take place.

Two applications were demonstrated:

• AI-based noise cancellation: The service identifies and removes background noise in real time to improve call clarity.
• Live language translation: AI translates a conversation between two different languages while the call is in progress.

“AI is giving the mobile network back its voice. More than 50 years after the first mobile call, innovation is accelerating and shifting back into the network,” said Marco Zangani, director of network strategy and architecture at Vodafone. “Over the past few years, we have built the infrastructure, data capabilities and safeguards needed to unlock AI for our customers to converse more clearly.”

Nadine Allen, head of UK and responsible for Vodafone Group at Ericsson, said the demonstration was a step toward more intelligent and programmable networks that can create new value for customers.