Genderless voice developed for virtual assistants to help tackle stereotypes

The voice, which has been nicknamed Q, was presented at the South by Southwest (SXSW) creative festival in Texas and is designed to be perceived as neither male or female.

Built by creative agency Virtue, Copenhagen Pride and equality campaign organisation EqualAI, the voice is also designed to reflect the growing number of people who define themselves as gender-neutral.

“There is no reason that a voice has to be gendered,” said Julie Carpenter, a research fellow in the ethics and emerging sciences group at California State Polytechnic University, who advised the project Q team. “Emerging technology is being designed to rely on these ancient stereotypes.”

The developers said they hope to eventually have Q supported by major platforms which use voice technology in virtual assistants, including Apple, Amazon and Google.

The final voice was created using a number of recorded voices from people who do not identify as male or female, which were then modulated to make them sound genderless, before being tested on over 4,500 people in Europe to gauge how they were perceived.

Testers were asked to grade the voice between one and five, with one meaning a male voice and five a female one, with the voice modulated and tested again until it was widely perceived as gender neutral, the developers said.

“People seem to have a preference for female voices when the role of the AI is more supportive and to assist or help someone, while they associate male voices with an authoritative tone or an area of expertise,” Carpenter said.

“Q adds to a global discussion about who is designing gendered technology, why those choices are made and how people feed into expectations about things like trustworthiness, intelligence and reliability of a technology based on cultural biases rooted in their belief system about groups of people.

“Q is a step forward in true innovation because it forces a critical examination of these belief systems.”

A spokeswoman for Microsoft said they had researched voice options for Cortana and found “a female voice best supports our goal of creating a digital assistant”. The spokeswoman added that the company had also explored adding a male voice option to Cortana.

The researchers found that male voices are usually pitched between 85-180Hz, while women’s are typically between 140-255Hz. This helped to identify a potential neutral range where the two overlapped.

It was not just pitch that defined the perceived gender of a voice: men tend to have a ‘flatter’ speech style that varies in pitch less and they also pronounce the letters ‘s’ and ‘t’ more abruptly, said Nis Norgaard, a sound designer at Thirty Sounds Good studio, who produced Q.