Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multimedia text recognition evaluation method, device and equipment and readable storage medium

A text recognition and evaluation method technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of low application efficiency, one-sided evaluation of evaluation results, etc., and achieve the effect of improving intuition, efficiency and convenience

Pending Publication Date: 2022-04-05
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, when the evaluation result of ASR recognition is determined by the above method, the judgment granularity of the evaluation result is relatively one-sided, and the application efficiency is 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
  • Multimedia text recognition evaluation method, device and equipment and readable storage medium
  • Multimedia text recognition evaluation method, device and equipment and readable storage medium
  • Multimedia text recognition evaluation method, device and equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0032] In the field of ASR speech recognition evaluation, the main evaluation scheme is to mark the video / audio text and the recognized text, and calculate the character error rate (Character Error Rate, CER) and sentence error rate (Sentence Error Rate, Sentence Error Rate, SER) index, but when the audio and video corpus is wrongly marked, it cannot be restored to the original text positioning. Without detailed context, it is not easy to find the context relationship between typos, which leads to inaccurate positioning analysis, so the practical value is low.

[0033] In view of the above problems, an evaluation method for multimedia text recognition is provided in the embodiment of the present application. figure 1 is a schemat...

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 an evaluation method, device and equipment for multimedia text recognition and a readable storage medium, and relates to the field of interface interaction. The method comprises the following steps: displaying a multimedia uploading interface; receiving a file uploading operation in the multimedia uploading interface; a text recognition evaluation result is displayed based on the file uploading operation, the text recognition evaluation result comprises an alignment analysis result of the characters, and in the alignment analysis result, the alignment conditions of a first alignment position in the text recognition result and a second alignment position in the reference text content are expressed with corresponding expression features. According to the method, the intuitiveness of comparison between the text recognition result and the reference text content is improved, the recognition effect of the text recognition result can be directly reflected, and the efficiency and convenience of evaluating the text recognition result are improved.

Description

technical field [0001] The embodiments of the present application relate to the field of interface interaction, and in particular to an evaluation method, device, equipment and readable storage medium for multimedia text recognition. Background technique [0002] Automatic speech recognition technology (Automatic Speech Recognition, ASR) refers to recognizing the speech content to obtain the text content corresponding to the speech content, wherein the speech content can be a piece of audio content or an audio part in a piece of video. [0003] The evaluation process of ASR recognition refers to matching the text content obtained by ASR recognition with the standard content to determine the accuracy of the ASR recognition result. Usually, the word error rate and sentence error rate between the ASR recognition result and the standard content are calculated by the edit distance algorithm. Error rate. [0004] However, when the evaluation result of ASR recognition is determine...

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): G10L15/01G10L15/26
Inventor 胡晓培
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products