18473701. DATA PROCESSING METHOD, DEVICE WAKE-UP METHOD, ELECTRONIC DEVICE AND STORAGE MEDIUM simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
DATA PROCESSING METHOD, DEVICE WAKE-UP METHOD, ELECTRONIC DEVICE AND STORAGE MEDIUM
Organization Name
Inventor(s)
Xiangfeng Meng of Beijing (CN)
DATA PROCESSING METHOD, DEVICE WAKE-UP METHOD, ELECTRONIC DEVICE AND STORAGE MEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18473701 titled 'DATA PROCESSING METHOD, DEVICE WAKE-UP METHOD, ELECTRONIC DEVICE AND STORAGE MEDIUM
Simplified Explanation
The patent application describes a data processing method, a device wake-up method, an electronic device, and a storage medium. The data processing method involves converting speech into a keyword phone sequence and generating a similar pronunciation sequence corresponding to the keyword phone sequence. This allows for effective coverage of real-life sounds with a smaller model, improving the ability to distinguish confusing pronunciations.
- The data processing method converts speech into a keyword phone sequence.
- A similar pronunciation sequence generator acquires a similar phone sequence corresponding to the keyword phone sequence.
- The method replaces the search method of large-scale speech databases with a sequence generation manner.
- The electronic device performs the data processing method, which can be done by an artificial intelligence (AI) model.
Potential applications of this technology:
- Speech recognition systems
- Voice assistants
- Language learning tools
Problems solved by this technology:
- Improved ability to distinguish confusing pronunciations
- Effective coverage of real-life sounds
Benefits of this technology:
- More accurate speech recognition
- Enhanced performance of voice assistants
- Improved language learning experience
Original Abstract Submitted
A data processing method, a device wake-up method, an electronic device, and a storage medium are provided. In the data processing method, speech to be processed is converted into a keyword phone sequence, and a similar pronunciation sequence generator acquires a similar phone sequence corresponding to the keyword phone sequence in a sequence generation manner, thereby acquiring a first data processed result corresponding to the speech to be processed. By replacing the search method of large-scale speech databases with this generation manner, effective coverage of possible real-life sounds can be achieved with a smaller model, thus improving the ability to distinguish confusing pronunciations. The above data processing method performed by the electronic device can be performed by an artificial intelligence (AI) model.
