Unlock instant, AI-driven research and patent intelligence for your innovation.

Speech recognition method, device and equipment and computer readable medium

A speech recognition and speech technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems affecting the normal use of functions, low speech recognition accuracy, lack of speaker language background or context, etc., to achieve the goal of improving accuracy Effect

Pending Publication Date: 2021-06-29
CHINA CONSTRUCTION BANK
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because the current speech recognition system lacks the language background or context of the speaker, it is easy to make mistakes when recognizing polyphonic phrases
For example, "Longxin" is recognized as "Nongxin", which will reduce the overall recognition accuracy and affect the normal use of functions
[0003] In the course of realizing the present invention, the inventor finds that there are at least the following problems in the prior art: the accuracy of speech recognition is relatively low

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
  • Speech recognition method, device and equipment and computer readable medium
  • Speech recognition method, device and equipment and computer readable medium
  • Speech recognition method, device and equipment and computer readable medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] Exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present invention to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0060] At present, the accuracy of speech recognition can be improved in limited scenarios, such as risk control, credit card or mobile banking, etc. But it can't achieve good results in open scenes. For example, in a certain scenario, there will be "public and private accounts" and "corporate accounts". Both phrases will appear, so they both need to be identified. In th...

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, device and equipment and a computer readable medium, and relates to the technical field of artificial intelligence. A specific embodiment of the method comprises the following steps: inputting user voice into an acoustic model; allowing the acoustic model to output user phonemes to a language model, and allowing the language model to output a user character sequence; replacing characters in the user character sequence through a dictionary to obtain a plurality of voice approximate words; and outputting the plurality of voice approximate words, and determining an output character sequence of the user voice based on a received instruction and the plurality of voice approximate words. According to the embodiment, the accuracy of speech recognition can be improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a speech recognition method, device, equipment and computer-readable medium. Background technique [0002] Outputting text through speech recognition has become a gradually popular way of human-computer interaction. However, because the current speech recognition system lacks the language background or context of the speaker, it is easy to make mistakes when recognizing polyphonic phrases. For example, "Longxin" is recognized as "Rongxin", which will reduce the overall recognition accuracy and affect the normal use of functions. [0003] During the process of implementing the present invention, the inventors found at least the following problems in the prior art: the accuracy rate of speech recognition is low. Contents of the invention [0004] In view of this, embodiments of the present invention provide a voice recognition method, device, device, and...

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
IPC IPC(8): G10L15/02G10L15/183G10L15/26
CPCG10L15/02G10L15/183G10L15/26G10L2015/025
Inventor 周永吉郭敏鸿范会善王炼马亮亮章铃娜姜京京
Owner CHINA CONSTRUCTION BANK