Are you interested in REQUESTS? Save with our coupons on WHATSAPP o TELEGRAM!

Xiaomi self-developed speech technology helps those with speech disorders

Technology Text-to-speech in a spontaneous style, developed by Xiaomi AI Lab in China, it is one of the last frontiers when it comes to voice recognition and the use of devices via voice. The project that It is born inside the laboratory it takes the name of "Own My Voice". Allows recipients who unfortunately suffer from speech disorders to have unique and personalized voices to communicate with other people. Let's see in detail what it is and since when the Chinese company has been working on it.

Xiaomi has unveiled its latest application of advanced algorithms and self-developed speech technology that helps those with speech disorders

Xiaomi cares about people and strives to meet their different needs through technological innovation. Over the past few years, the Chinese brand has discovered the desire of many users with speech disorders own your own voice, even unique, to be used for daily communication. For this reason Xiaomi has set up the project team "Own My Voice". Zhu Xi, coordinator of the Technology Committee on Xiaomi's Tech for Good, said:

We are excited to explore the multiple values ​​that technological innovation offers us, such as responding to user requests for personal identity and identity building

In order to generate the most suitable and personalized voice for the language impaired user, the Xiaomi project team has recruited more than 200 volunteers inside to give your voice. The voiceprint matching algorithm was used to match the characteristics of the voices donated by the volunteers with those of the recipient's voice. Through this approach, it was found the most suitable voice as a reference sound basic voice for the recipient. 

xiaomi helps those with language problems

Read also: Mi Band 7 comes out with a lot of date and price | Photo

Subsequently, the scholars used spontaneous-style speech synthesis technology for train the artificial intelligence model. This allowed a natural rhythm and intonation capable of gradually being added to this new voice truthfully express the emotion and the tone of a human being.

Zhu Xi added:

If we notice and address the needs of minority groups at an early stage, the process of spreading the technology could be greatly reduced. This allows the benefits of new technologies to become immediately accessible to users with special needs

The backbone of this project is a group of voice technology experts by Xiaomi AI Lab. From 2017 have published 37 articles to this effect and have been present in important circles such as theInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP). The success of "Own My Voice”Mainly depends on the spontaneous style of the Text-To-Speech technology they developed. The spontaneous style of technology Text-To-Speech essentially makes the synthesized voice look like a real human being in its intonation, pause, speed and other characteristics. This replaces the monotonous, unnatural feel of the electronic voice with a more natural one.

Gianluca Cobucci
Gianluca Cobucci

Passionate about code, languages ​​and languages, man-machine interfaces. All that is technological evolution is of interest to me. I try to divulge my passion with the utmost clarity, relying on reliable sources and not "on the first pass".

Subscribe
Notify
guest

0 Post comments
Inline feedback
View all comments
XiaomiToday.it
Logo