Voice recognition method and system
A speech recognition and speech storage technology, applied in speech recognition, speech analysis, transmission systems, etc., can solve the problems of inability to guarantee clear and accurate speech recognition, inability to recognize very well, and low recognition accuracy, and achieve guaranteed use effects and Use efficiency, high practicability, and the effect of improving the use function
Inactive Publication Date: 2019-03-29
合肥凯捷技术有限公司
View PDF5 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] With the development of speech recognition technology, the application field of speech recognition system is more and more extensive. Speech recognition technology analyzes the speech language used by human beings for communication and converts the speech language into characters or text data. When the scene is noisy or there are many people speaking at the same time, the voice of the person you want to recognize cannot be recognized well, the recognition accuracy is very low, and the recognition of voice cannot be guaranteed to be clear and accurate, and the existing technology can only recognize one language. , so it is limited
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
Embodiment 1
[0021] see figure 1 The present invention provides a technical solution: a voice recognition system, including a voice storage database, a voice recognition module and a central processing unit, the voice storage database includes a collection module, and the collection module includes a main microphone and an auxiliary microphone, The acquisition module is connected with a storage module, and the voice storage database is connected with a voice recognition module through a communication interface;
[0022] Described voice recognition module is provided with MCU module and receiving module, and described receiving module includes receiving chip, and the output end of described receiving module is connected with conversion module by CAN communication bus, and described conversion module is provided with conversion chip, so The output end of the conversion module is connected to the processing module and the translation module through the CAN communication bus, the processing ch...
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 PUM
Login to View More Abstract
The invention discloses a voice recognition method and system. The system comprises a voice storage database, a voice recognition module and a central processor, the voice storage database comprises acollection module, and the collection module comprises a main microphone and an auxiliary microphone; a storage module is connected to the collection module, a voice recognition module is connected to the voice storage database through a communication interface, through the main microphone and the auxiliary microphone in the voice storage database, voice sound wave information of a specific personal is input to the collection module, a receiving chip of a receiving module senses voice information of an external sound source, then a conversion module is utilized for converting recognized vibration signal information into electric signals, a processing chip of a processing module is utilized for processing the electric signals, when received voice does not belong to a specified language, atranslation module can translate the electric signals into specified language information through a translation chip, and then the processing chip of the processing module is utilized for processing the translated electric signals.
Description
technical field [0001] The invention relates to the technical field of voice recognition, in particular to a voice recognition method and a voice recognition system. Background technique [0002] With the development of speech recognition technology, the application field of speech recognition system is more and more extensive. Speech recognition technology analyzes the speech language used by human beings for communication and converts the speech language into characters or text data. When the scene is noisy or there are many people speaking at the same time, the voice of the person you want to recognize cannot be recognized well, the recognition accuracy is very low, and the recognition of voice cannot be guaranteed to be clear and accurate, and the existing technology can only recognize one language. , so it is limited. Contents of the invention [0003] The object of the present invention is to provide a voice recognition method and a voice recognition system to solve...
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): G10L15/22G10L15/26H04L12/40
CPCH04L12/40G10L15/22G10L15/26H04L2012/40215
Inventor 殷国龙程庚陈雅芹黄健孙昊
Owner 合肥凯捷技术有限公司