The xiaomi It has now revealed voice technology to help people with speech disorders. More specifically, the projectown my voiceAllows audio receivers to have unique, personalized sounds.
This is one of the latest bets from Xiaomi, a consumer electronics company and smart manufacturer with smartphones and smart devices connected to an Internet of Things platform at its core. Now, the technology has just revealed its latest application of advanced algorithms and self-developed voice technology in the field of accessibility.
Xiaomi unveils new text-to-speech technology
technology text to speech The spontaneous method, developed by Xiaomi AI Lab, was used to generate a unique and personalized voice for a user with a speech disability.
The user can now communicate with others using his ‘voice’. This is instead of the typical monotonous electronic sound in general. Thus, as part of the “Own My Voice” pre-investigation project led by the Xiaomi Technical Committee, this successful attempt demonstrates Xiaomi’s commitment to “Technology for Good”. Likewise, it aims to fulfill its mission of “allowing everyone in the world to lead a better life through innovative technology.”
Text-to-speech technology developed by Xiaomi AI Lab
Xiaomi cares about people and strives to meet their needs through technological innovation. Also discover that many users with speech disorders desire their unique voices for everyday communication.
To this end, the project team created “Own My Voice” to invite a user with speech disorders to act as the voice receiver. “We are excited to explore the multiple values that technological innovation brings us, such as responding to users’ demands for their identity and building their identity,” said Zhu Xi, Head of the Technology Committee on “Technology for Good” at Xiaomi.
More than 200 volunteers within Xiaomi “donate” their votes
In order to generate the most appropriate and personalized voice for the recipient, the team has recruited more than 200 volunteers within Xiaomi to donate their voices. They then used a voice matching algorithm to match the characteristics of the voices donated by volunteers with those of the recipient’s voice.
Therefore, through this approach, they find the most suitable sound as the primary reference sound for the receiver. Then, with personalization and privacy protection in mind, the selected real sound was manipulated through complex acoustic modifications to create a new and original acoustic sound.
In the next step, they used the automatically designed text-to-speech technology to train the AI model. Here the making of this new sound gradually acquires a natural rhythm and tone capable of truly expressing the emotion and tone of the human being.
In short, the projectown my voice“It combines a variety of the most advanced algorithms with Xiaomi’s self-developed speech technology to ensure the privacy, security and high fidelity of the synthesized voice. Thus, creating a customized speech synthesis idea for users with speech disorders.
The project emerged from Xiaomi AI Lab
The backbone of this project is a group of speech technology experts from Xiaomi AI Lab. This body has, since 2017, published 37 Theses on Speech in Proceedings of Major International Conferences.
Among these, we highlight the International Conference on Acoustics, Speech and Signal Processing (ICASSP). By the way, the success of “Own My Voice” is mainly based on the automatically designed text-to-speech technology they developed.
Spontaneous style text-to-speech technology makes the voice synthesized like a real human in tone, pause, speed and other characteristics. This replaces the monotonous and unnatural sensation of electronic sound with a more natural sound.
Therefore, currently, this technology is applicable to many smart devices equipped with XiaoweiXiaomi’s AI voice assistant.
The “Own My Voice” project demonstrates that automated text-to-speech technology can also be widely adopted in the areas of accessibility and user experience improvement.
Zhu Xi added, “If we notice and address the needs of minorities at an early stage, the process of technology deployment can be greatly shortened. This allows the advantages of new technologies to become accessible to users with disabilities without delay.”
From now on, Xiaomi will continue to receive feedback from audio receivers and will continue to study the feasibility of this project in a larger scale.
Finally, Xiaomi will continue to enable accessibility with the latest technologies, and strive to meet people’s diverse needs through technological innovation.
4gnews editors recommend the following: