Η Xiaomi presents its latest application of advanced algorithms and self-developing speech technology in the field of accessibility
Η technology Text-to-Speech, developed by Xiaomi AI Lab, is used to create a unique and customized voice for speech-impaired users.
The user can now communicate with other people using the «his own voice»Instead of the standard electronic voice. As part of the research project “Own My Voice", Headed by Xiaomi Technical Committee, this successful endeavor demonstrates Xiaomi's commitment to "Tech for GoodAnd the achievement of its goal "to enable the whole world to enjoy a better life through innovative technologies".
Why Xiaomi started the project
Xiaomi cares about people and tries to meet their diverse needs through technological innovations. In this context, he discovered the desire of many users with speech disorders to acquire their own unique voices for their daily communication and created the group "Own My Voice", Which invited a user with speech disorders to acquire his own voice. THE Zhuxi, Member of the Commission Technology of Tech for Good to Xiaomi Corporation, said:
How Xiaomi implemented this project
In order to be able to provide the most appropriate and personalized voice to the recipient, the project team collaborated with more than 200 volunteers inside Xiaomi who lent their voices. They then used the voice-tag matching algorithm to match the volunteer's voice data with those of the recipient's voice.
Through this approach, they found the most appropriate voice as the basic voice reference sound for the recipient. Wanting to protect privacy, each selected true voice was processed with sophisticated audio media to produce a new unique voice sound. In the next step, they used the immediate response technology Text-to-speech technology to train the AI model, making this new voice gradually acquire a natural rhythm and tone that can honestly express a person's feelings and tone.
The program "Own My VoiceCombines a variety of state-of-the-art speech algorithms developed by Xiaomi to ensure the uniqueness, security and high authenticity of synthetic voice, creating a new idea for custom speech composition for speech-impaired users.
What is the significance of this project?
The backbone of this project consists of a team of speech technology experts from Xiaomi AI Lab. From 2017 have published 37 studies on speaking in the proceedings of leading international conferences, such as International Conference on Acoustics, Speech and Signal Processing (ICASSP). The success of "Own My Voice”Is based mainly on the Text-to-Speech technology developed by the team. The spontaneous style of technology Text-to-speech it essentially makes the synthetic voice sound true to its tone, pause, speed and other characteristics.
This replaces the monotonous and unnatural feeling of the electronic voice with a more natural one. So far, this technology is available in many smart devices equipped with XiaoAI, Xiaomi's voice AI assistant.
The play "Own My Voice”Shows that the Text-to-Speech technology can also be widely adopted in accessibility areas and improve the user experience. O Zhuxi add:
Going forward, Xiaomi will continue to listen to the comments of each voice receiver and study the possible expansion of the project to a wider range. Xiaomi will continue to support accessibility through new technologies, trying to meet the different needs of people through technological innovation.
Do not forget to follow it Xiaomi-miui.gr on Google News to be informed immediately about all our new articles! You can also if you use RSS reader, add our page to your list by simply following this link >> https://news.xiaomi-miui.gr/feed/gn
Follow us on Telegram so that you are the first to learn our every news!
