Voice processing method and device and distributed system
A technology of speech processing and natural language processing, applied in the field of information processing, can solve the problems of inability to access or replace modules, affecting the experience of multi-scenario applications of voice interaction, recognition rate or performance not meeting the standards at the same time, etc.
Pending Publication Date: 2020-10-27
BANMA ZHIXING NETWORK HONGKONG CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Existing voice interaction solutions are provided by a certain manufacturer to realize all the modules on the entire interactive link, and cannot access or replace modules of other manufacturers, such as Amazon echo, Google speakers, etc.
Since th
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Login to View More PUM
Login to View More Abstract
The invention discloses a voice processing method, a voice processing device and a distributed system. The method comprises the following steps: receiving voice data; performing voice processing on the voice data, wherein the voice processing comprises the following steps: selecting one or more voice recognition components from a plurality of voice recognition components to process the voice databased on scene information; and/or based on the scene information, selecting one or more natural language processing components from a plurality of natural language processing components to process the text corresponding to the voice data. The voice processing link may also include functions such as wakeup, voiceprint, and speech synthesis. The components executing the functions can be dynamicallyselected according to scenes, so that different application scenes can be flexibly dealt with, and respective optimal use experience is provided.
Description
technical field [0001] The present invention relates to the field of information processing, in particular to a language processing method, device and distributed system. Background technique [0002] Generally, the voice interaction device of the terminal can upload the received voice to the cloud, and use the powerful processing capability of the cloud to perform voice recognition and natural language understanding. Or, in the case of poor networking conditions or relatively simple application scenarios, the voice interaction device can also complete the entire voice interaction link locally. [0003] With the development of voice interaction technology, there are more and more application scenarios involving voice interaction. At the same time, the voice interaction link is relatively long, which will involve different module units such as audio data collection, front-end signal processing, wake-up response, voice recognition, and voiceprint. Recognition, natural languag...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G10L15/18G10L15/26G10L15/30G10L15/065
CPCG10L15/065G10L15/18G10L15/26G10L15/30
Inventor 钟学书杨扬邹一新李兴伟袁志俊王恺张贤佳
Owner BANMA ZHIXING NETWORK HONGKONG CO LTD