Accent-based speech recognition processing method, electronic device and storage medium
A technology of speech recognition and processing methods, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of different, low speech recognition accuracy, and difficulty in user pronunciation reaching standard Mandarin, and achieve the effect of improving the accuracy.
Active Publication Date: 2021-04-06
SHENZHEN AIMORE ACOUSTICS INC
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In traditional technology, the research and development of speech recognition is basically based on standard Mandarin. However, in practical applications, it is often difficult for users to pronounce standard Mandarin, and usually carry different accents.
Since traditional speech recognition algorithms are all based on standard Mandarin, when faced with a speech with an accent, the accent cannot be recognized, resulting in a low accuracy rate of speech recognition
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 Construction
[0033] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation manners described here are only used to explain the present application, and do not limit the protection scope of the present application.
[0034] The accent-based speech recognition processing method provided by this application can be applied to such as figure 1 shown in the application environment. Wherein, the user interacts with the electronic device 102 by sending sound signals. Specifically, the user sends out a sound signal, and the electronic device 102 collects the sound signal sent by the user through a microphone array to obtain a voice command carrying relevant information, and analyzes the voice command. Taking the sound signal as the sound signal for accent training as an...
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 present application relates to an accent-based speech recognition processing method, electronic equipment and a storage medium. The method includes: receiving and recognizing a preset number of training voice commands, obtaining voice recognition results corresponding to each training voice signal; Compare the recognition results to obtain the comparison result; when the comparison result meets the consistency condition, perform fuzzy matching between the speech recognition result and the standard voice command to obtain the candidate standard voice command; confirm the candidate standard voice command, determine and train The standard voice command that the voice command matches; according to the training voice command and the matching standard voice command, the accent feature of the training voice command is determined, and the accent feature is used to correct and recognize the voice command to be recognized that carries the corresponding accent feature. Using accent training to get the accent features of corrected voice commands, so as to improve the recognition accuracy.
Description
technical field [0001] The present application relates to the technical field of speech recognition, in particular to an accent-based speech recognition processing method, electronic equipment and a storage medium. Background technique [0002] With the development of mobile Internet, Internet of Vehicles and smart home, voice recognition has played an increasingly important role. For example, the interaction with the in-vehicle information communication system can be realized through voice, and the smart home can be controlled through voice commands. With the wide application of speech recognition technology, improving the accuracy of speech recognition has become the focus and difficulty faced by the development of speech recognition technology. [0003] In traditional technologies, the research and development of speech recognition is basically based on standard Mandarin. However, in practical applications, the user's pronunciation is often difficult to reach the level o...
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 Patent Type & Authority Patents(China)
IPC IPC(8): G10L15/02G10L15/06G10L15/22G10L15/26
CPCG10L15/02G10L15/063G10L15/22G10L15/26
Inventor 谢冠宏廖明进高铭坤
Owner SHENZHEN AIMORE ACOUSTICS INC