Photo/Illutration Employees of SoftBank Corp. who work on the development of AI voice-conversion technology. From left, Toshiyuki Nakatani, Toshio Imamura and Shuhei Takahara. (Provided by SoftBank Corp.)

Good news for call center operators who are worn down by hostile customers with unreasonable demands—artificial intelligence technology can alter angry voices into calm ones.

This should alleviate the tremendous stress of customer interaction on call operators—if AI has not completely replaced their jobs by then.

SoftBank Corp. announced that it has developed voice-altering technology to protect employees from customer harassment.

The goal is to reduce the psychological burden on call center operators by changing the voices of complaining customers to calmer tones.

The company launched a study on “emotion canceling” three years ago, which uses AI voice-processing technology to change the voice of a person over a phone call.

Toshiyuki Nakatani, a SoftBank employee, came up with the idea after watching a TV program about customer harassment.

“If the customers’ yelling voice sounded like Kitaro’s Eyeball Dad, it would be less scary,” he said, referring to a character in the popular anime series “Gegege no Kitaro.”

The voice-altering AI learned many expressions, including yelling and accusatory tones, to improve vocal conversions. Ten actors were hired to perform more than 100 phrases with various emotions, training the AI with more than 10,000 pieces of voice data.

The technology does not change the wording, but the pitch and inflection of the voice is softened.

For instance, a woman’s high-pitched voice is lowered in tone to sound less resonant. A man’s bass tone, which may be frightening, is raised to a higher pitch to sound softer.

However, if an operator cannot tell if a customer is angry, the operator may not be able to react properly, which could just upset the customer further.

Therefore, the developers made sure that a slight element of anger remains audible.

According to the company, the biggest burdens on operators are hearing abusive language and being trapped in long conversations with customers who will not get off the line—such as when making persistent requests for apologies.

With the new technology, if the AI determines that the conversation is too long or too abusive, a warning message will be sent out, such as, “We regret to inform you that we will terminate our service.”

With technology rapidly advancing, could AI handle customer complaints entirely instead of human operators?

Nakatani said, “AI is good at handling complaints and can do so for long hours, but what angry customers want is for a human to apologize to them.”

Because it is difficult for AI to completely replace operators, Nakatani said he hopes that AI “will become a mental shield that prevents operators from overstraining their nerves.”

The company plans to further improve the accuracy of the technology by having AI learn voice data and hopes to sell the technology starting from fiscal 2025.

Related News