For persons with speech impairments, Xiaomi is developing a “unique and individualized” voice

Xiaomi has created Text-To-Speech, a new accessibility technology that allows people with speech impairments to generate a “unique and individualized” voice.

This effort was commissioned by Xiaomi AI Lab, a research division of the Chinese technology giant, and gives a personalized speech proposal in place of the normal monotonous and electronic voice of intelligent voice assistants.

Text-To-Speech is part of the research project Own My Voice (My own voice), which is led by Xiaomi’s Technical Committee and is based on the company’s commitment to the worldwide Tech for Good movement, which promotes the use of technology for the common good.

According to the manufacturer, the initiative Own My Voice demonstrates that spontaneous-style text-to-speech technology may be used to increase accessibility and user experience.

The researchers behind this project have created a new concept for “unique and individualized” voice synthesis for those with speech problems, allowing them to access more humanized services.

Text-To-Speech does this by combining algorithms with superior voice technology created by Xiaomi to secure the synthesized voice’s specificity, confidentiality, and authenticity.

This technology allows intelligent assistants’ synthesized voices to sound like actual people, including intonation, pauses, speed, and other speech characteristics.

As the business points out, this “replaces the monotonous and unnatural experience of the electronic voice” of the devices with one that is more natural, near, and human.

This technique is currently applicable to a variety of smartphones that have Xiaomi’s Xiaoai artificial intelligence (AI) voice assistant.

In relation to the development of this technology, Zhu Xi, chairman of the Tech for Good Committee, stated, “If we detect and attend to the requirements of minority groups at an early stage, the technology diffusion process could be shortened.”

The company has stated that it will continue to solicit feedback from Text-To-Speech recipients and will investigate the possibilities of expanding the project’s reach.

By Editor

Leave a Reply