Voice recognition method and device

A technology of speech recognition and speech data, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of speech recognition results deviating from the normal context, etc., and achieve the effect of deviating from the normal context.

Pending Publication Date: 2021-03-12
BEIJING THUNISOFT INFORMATION TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present application provides a speech recognition method to solve the problem in the prior art that the speech recognition result deviates from the normal context

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Voice recognition method and device
  • Voice recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present application.

[0036] Please refer to figure 1 , the application discloses a speech recognition method, including:

[0037] S100: Obtain input voice data.

[0038] The voice data is voice stream data input in real time, or file stream data in an audio file.

[0039] Among them, the voice stream data acquisition can usually be generated by real-time rec...

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

No PUM Login to view more

Abstract

The invention discloses a voice recognition method and a voice recognition device. The method comprises the following steps: acquiring input voice data; decoding the voice data through a decoding model to generate a voice recognition intermediate result; matching the voice recognition intermediate result based on a core word pinyin and tone sequence in a core word database; and outputting a matching result according to the matching state of the pinyin in the tone sequence and the intermediate result in the voice recognition. The problem that the voice recognition result deviates from the normal context can be solved by matching the voice recognition intermediate result with the core word pinyin and tone sequence in the core word database.

Description

technical field [0001] The invention relates to the field of voice recognition, in particular to a voice recognition method and a device thereof. Background technique [0002] The decoding of speech recognition has a lot to do with the application scenario, and users always expect the speech recognition model to be able to perform certain directional decoding and recognition on the user's scene corpus. At present, speech recognition is performed based on user hot words. When uploading hot words, it is necessary to manually define hot words and set their weight values. If the settings of these weight values ​​are quite different, the speech recognition results will seriously deviate from the normal context, and the number of uploaded hot words is also limited, making it difficult for users to select hot words. Contents of the invention [0003] The embodiment of the present application provides a voice recognition method to solve the problem in the prior art that the voice...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/22G10L15/06G10L15/08G10L25/12
CPCG10L15/22G10L15/063G10L15/08G10L25/12G10L2015/088
Inventor 沈来信朱相宇王映新孙明东贾师惠
Owner BEIJING THUNISOFT INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products