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

Audio output method and system

An output method and output system technology, applied in the field of audio output methods and systems, can solve the problems of limited English proficiency, missing voice information, non-standard pronunciation, etc., to avoid inaccurate pronunciation, wide application scenarios, and simple implementation methods. Effect

Inactive Publication Date: 2020-03-13
SUNING CLOUD COMPUTING CO LTD
View PDF8 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for some people, it is still difficult to convey the words clearly and accurately. For example, some people have limited English proficiency, may not have standard pronunciation, and there are many repeated words. less than the heart's request
For example, for some people, due to problems such as typos and too fast speaking, it may be difficult for listeners to understand this way of speaking, and even cause misunderstandings, resulting in the omission of voice information or loss of key points or even repetition of useless information
[0003] The existing audio prompt method is to promote interaction through text methods such as teleprompters, but this method lacks the fluency of interaction, does not achieve the rhythmic effect of language expression, and cannot obtain the expected interactive feedback. say, and even lose the delivery of valid information

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
  • Audio output method and system
  • Audio output method and system
  • Audio output method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] like figure 1 As shown, the embodiment of the present invention provides an audio output method, including the following steps:

[0033] S1: Obtain the continuous voice information collected by the client, segment the voice information into segments, decode the segmented voice information, and convert the segmented voice information into first text information and store;

[0034] S2: Filter the first text information, and then extract keywords, and mark the keywords according to the number of occurrences, when the number of times the same keyword is marked exceeds a preset threshold and the keyword If it is not in the standard lexicon, then the keyword will be imported into the standard lexicon;

[0035] S3: Using the method of machine learning, search the extracted keywords in the standard thesaurus and match them, form the matched words containing the keywords into second text information, and perform a search on the second text Prioritize the relevance of informat...

Embodiment 2

[0049] like image 3 As shown, the embodiment of the present invention also provides an audio output system, including:

[0050] The collection input module 1 is used to obtain the continuous voice information collected by the client 5, carry out segmentation and cutting of the voice information, decode the voice information after segmentation, and then decode the voice information after cutting converted into the first text information and stored;

[0051] The keyword processing module 2 is used to filter the first text information, and then extract the keywords, and mark the keywords according to the number of occurrences, when the number of times the same keyword is marked exceeds the preset threshold and the keyword is not in the standard thesaurus, then the keyword is imported into the standard thesaurus;

[0052] The search association module 3 is used to use the method of machine learning to match the extracted keywords after searching in the standard thesaurus, and f...

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 audio output method and system, and the method comprises the following steps: obtaining continuous voice information collected by a client, segmenting the voice information,decoding the segmented voice information, converting the voice information into first text information, and storing the first text information; filtering the first text information, extracting keywords, marking the keywords according to the occurrence frequency, and importing the keywords into a standard word bank when the marking frequency of the same keyword exceeds a preset threshold value andthe keywords are not in the standard word bank; matching the extracted keywords after searching by using a machine learning method, forming second text information by using the matched characters containing the keywords, and arranging the second text information; and converting the second text information into corresponding standard audios according to the sequence of the priorities and outputting the standard audios. According to the embodiment of the invention, the audio information can be recognized, the processed audio information can be quickly and accurately output, and the language expression effect is improved.

Description

technical field [0001] The invention relates to the field of voice recognition, in particular to an audio output method and system. Background technique [0002] Audio is a necessary means to promote effective interaction between people and between people and sounding bodies. Most of the existing knowledge, information, interactive entertainment, and emotional expression use audio as the medium for information transmission, and all of these are reflected without exception. Audio has the characteristics of high communication efficiency and easy acceptance. With the development of the information age, audio needs to carry more and more information. At this time, it is necessary to interact this piece of audio in some way. However, for some people, it is still difficult to convey the words clearly and accurately. For example, some people have limited English proficiency, may not have standard pronunciation, and there are many repeated words. Less than the heart's request. Fo...

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): G10L15/04G10L15/26G10L19/20G06F16/14G06N20/00G06F3/16
CPCG10L15/04G10L15/26G10L19/20G06F16/14G06N20/00G06F3/162
Inventor 蔡继发宋飞豹倪合强姚寿柏
Owner SUNING CLOUD COMPUTING CO LTD