Method for identifying conference speech as text, electronic device and storage medium

A speech recognition and text technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems affecting the readability and analysis of conference texts, inability to recognize taboo sensitive words, inaccurate keyword recognition, etc., to reduce the workload of proofreading , Improve the unreasonable part of the text expression, and ensure the effect of correctness

Active Publication Date: 2018-11-20
PING AN TECH (SHENZHEN) CO LTD
View PDF6 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the biggest problem in speech recognition is the accuracy of speech recognition. Even Nuance, which has the highest speech recognition accuracy among existing devices, cannot avoid the following problems: frequent occurrence of irrelevant words such as modal particles makes text analysis difficult Increased, inaccurate recognition of some professional keywords, and inability to recognize taboo sensitive words, etc., have affected the readability and analysis of the conference text

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
  • Method for identifying conference speech as text, electronic device and storage medium
  • Method for identifying conference speech as text, electronic device and storage medium
  • Method for identifying conference speech as text, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] figure 1 It is a flowchart of a method for recognizing conference speech as text provided in the first embodiment of the present invention. According to different needs, the execution order in this flowchart can be changed, and some steps can be omitted.

[0052] S11. Convert the conference speech to be recognized into text through the speech recognition technology, as the initial speech recognition text.

[0053] In this embodiment, the specific process of converting the conference voice to be recognized into text through the voice recognition technology includes:

[0054] 1) Extract the audio feature of the conference speech to be recognized and convert it into an acoustic feature vector of preset length;

[0055] 2) Decode the feature vector into word order according to the decoding algorithm;

[0056] 3) Obtain the subwords corresponding to the word order through the HMM phoneme model, and the subwords are initials and finals;

[0057] 4) Combine multiple sub-words into text ...

Embodiment 2

[0104] figure 2 It is a diagram of functional modules in a preferred embodiment of the device for recognizing conference speech as text in the present invention.

[0105] In some embodiments, the apparatus 20 for recognizing conference speech as text runs in an electronic device. The apparatus 20 for recognizing conference speech as text may include multiple functional modules composed of program code segments. The program code of each program segment in the device 20 for recognizing conference speech as text can be stored in a memory and executed by at least one processor to execute (see figure 1 And related descriptions) to recognize conference speech as text.

[0106] In this embodiment, the apparatus 20 for recognizing conference speech as text of the electronic device can be divided into multiple functional modules according to the functions it performs. The functional modules may include: an identification module 201, a matching module 202, a generation module 203, a detect...

Embodiment 3

[0158] image 3 It is a schematic diagram of the electronic device provided in the fifth embodiment of the present invention.

[0159] The electronic device 3 includes a memory 31, at least one processor 32, a computer program 33 stored in the memory 31 and running on the at least one processor 32, and at least one communication bus 34.

[0160] When the at least one processor 32 executes the computer program 33, the steps in the foregoing method for recognizing conference speech as text are implemented.

[0161] Exemplarily, the computer program 33 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 31 and executed by the at least one processor 32, To complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 33 in the electronic dev...

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 relates to a method for identifying the conference speech as a text. The method comprises steps that the to-be-identified conference speech is converted through the speech identificationtechnology into the text as an initial speech identification text; the initial speech identification text is matched with a preset text database to obtain the matched speech identification text; a speech identification text draft in an editable status is generated according to the matched speech identification text; after receiving editing operation on the speech identification text draft is detected, a speech identification text in an uneditable state is generated according to the speech identification text after editing operation as a final speech identification text. The invention furtherprovides an electronic device taking the conference speech as the text, and a storage medium. The method is advantaged in that after preliminary identification of the to-be-identified speech, first matching with the preset text database is performed, second confirmation is performed manually, correctness of the text output content is effectively guaranteed, the proofreader workload of the conference content is reduced, and efficiency is improved.

Description

Technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a method, electronic equipment and storage medium for recognizing conference speech as text. Background technique [0002] Automatic Speech Recognition (ASR) is the core technology in the fields of machine translation, robot control, and the next generation of human-computer interaction interfaces. It enables computers to "dictate" continuous speech spoken by different people to achieve "voice" "To "text" conversion. [0003] At present, with the continuous development of speech recognition technology, the applications based on speech recognition are becoming more and more extensive. Such technology has penetrated into family life, office fields, entertainment and other aspects. Users input voices by using external or built-in microphones on personal computers, laptops, tablet computers, dedicated learning terminals, smart phones, and other terminals, and complete vo...

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): G10L15/26
CPCG10L15/26
Inventor 王健宗于夕畔肖京
Owner PING AN TECH (SHENZHEN) CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap