Subtitle display methods in video conferencing

By calculating the ratio of subtitle area to screen size and the number of characters, the subtitle display is automatically adjusted, solving the problem of non-adjustable subtitle position and size in traditional video conferencing. This improves the readability and comprehensibility of subtitles and enhances meeting efficiency.

CN116886853BActive Publication Date: 2026-11-17GUANGZHOU BAOLUN ELECTRONICS CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202310916047.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-07-24
Publication Date
2026-11-17
Estimated Expiration
2043-07-24

AI Technical Summary

Technical Problem

Traditional video conferencing methods for displaying subtitles cannot automatically adjust the position and size of the subtitles, and when too many subtitles are generated, they are difficult to read and understand.

Method used

The system collects speech through a microphone and converts it into an electrical signal. The speech recognition unit generates subtitles, and the central control unit calculates the ratio of the subtitle area to the screen to determine whether to adjust the font size, interrupt word processing, or perform word association operations. The subtitle display is then adjusted according to preset standards.

Benefits of technology

It achieves a reasonable ratio between subtitles and screen, complete character count, and clear semantics, thus improving the efficiency of meeting operations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116886853B_ABST
    Figure CN116886853B_ABST
Patent Text Reader

Abstract

This invention relates to the field of video conferencing technology, and more particularly to a method for displaying subtitles in video conferencing. The method includes: Step S1, a microphone generates an electrical signal; Step S2, speech recognition is performed and subtitles are generated; Step S3, the ratio of the subtitle area to the total screen area is calculated and determined; Step S4, if a preset standard is met, it is determined whether word association operation should be performed, and if it is determined that word association operation is required, the corresponding standard in the word association database is adjusted to the corresponding value based on historical conference speech; Step S5, the central control unit uses the adjusted operating parameters to process the speech in the conference for subtitle display. Compared with the prior art, the beneficial effect of this invention is that by calculating the ratio of subtitle to screen area, the subtitle situation can be quickly determined and corrected, making the proportion of subtitles to screen more reasonable, thereby making the subtitle content easier to read and understand, and thus improving the efficiency of the conference.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of video conferencing technology, and more particularly to a method for displaying subtitles in video conferencing. Background Technology

[0002] Traditional methods of displaying subtitles in video conferencing involve the following steps: During the video conference, at least two smart terminals participating in the conference are connected to a voice intelligent server; each smart terminal sends the collected audio data to the voice intelligent server; after receiving the audio data, the voice intelligent server transcribes the audio data into text data and sends the text data to each smart terminal so that the smart terminals can overlay the text data onto the video conference screen to display subtitles.

[0003] Chinese Patent Publication No. 202111644825.3 discloses a method, device, and storage medium for displaying subtitles in a video conference, comprising: a smart terminal acquiring video conference data; acquiring target text data obtained by transcribing target audio data; converting the target text data into subtitle image data; fusing the subtitle image data with the target image data to obtain fused image data; and sending the fused image data to each participating terminal through a conference control device for display by the participating terminals. It is evident that the aforementioned method, device, and storage medium for displaying subtitles in a video conference has the following problems: it cannot automatically adjust the position and size of the generated subtitles, and when there are too many generated subtitles, they are difficult to read and understand. Summary of the Invention

[0004] To address this, the present invention provides a method for displaying subtitles in video conferencing, which overcomes the problems in the prior art where the position and size of generated subtitles cannot be automatically adjusted, and where too many subtitles are difficult to read and understand.

[0005] To achieve the above objectives, the present invention provides a method for displaying subtitles in a video conference. This includes: Step S1: The microphone collects the test voice and converts the collected test voice into an electrical signal; In step S2, the voice recognition unit recognizes the audio information output by the microphone to generate subtitles that match the audio information and sends the subtitles to the display unit, which then displays the subtitles using the corresponding font size. Step S3: The central control unit calculates the ratio of the area of ​​the subtitles displayed in the display unit to the total area of ​​the screen and determines whether the subtitles output by the display unit meet the preset standard based on the ratio. When the central control unit determines that the subtitles output by the display unit do not meet the preset standard, it determines whether to perform interruption word correction processing on the words in the subtitles or adjust the font size of the subtitles to the corresponding value. Step S4: When the central control unit determines that the subtitles output by the display unit meet the preset standard, it determines whether to perform word association operation during the subtitle generation process based on the duration between the time node of the corresponding voice collected by the microphone and the time node of the output subtitles. When it determines that word association operation is required, it adjusts the corresponding parameters in the association word library to the corresponding values ​​based on the conference voice in the historical collection records of the microphone. In step S5, when the central control unit determines that the duration meets the preset standard, it selects the adjusted operating parameters to perform subtitle display processing on the audio in the meeting.

[0006] Further, in step S3, for a single-sentence subtitle displayed by the display unit, the central control unit records the ratio of the area of ​​the subtitle in the screen to the total area of ​​the screen as the subtitle ratio, and determines a method for judging whether the subtitle meets a preset standard based on the subtitle ratio, wherein: The first determination method is that the central control unit determines that the subtitle meets the preset standard. The central control unit records the duration between the time node when the microphone collects the speech corresponding to the subtitle and the time node when the subtitle is output to determine whether to perform word association operation during the subtitle generation process. The first determination method satisfies that the proportion of the subtitle is less than the first-level preset subtitle proportion preset in the central control unit. The second determination method is that the central control unit determines that the subtitle does not meet the preset standard, and the central control module determines whether to perform interruption word correction processing on the subtitle based on the number of characters in the subtitle; the second determination method satisfies that the proportion of the subtitle is greater than or equal to the proportion of the first-level preset subtitle and less than or equal to the proportion of the second-level preset subtitle preset in the central control unit, and the proportion of the second-level preset subtitle is greater than the proportion of the first-level preset subtitle. The third determination method is that the central control unit determines that the subtitle does not meet the preset standard, and determines the adjustment method for the subtitle font size based on the difference between the subtitle ratio and the secondary preset subtitle ratio; the third determination method satisfies that the subtitle ratio is greater than the secondary preset subtitle ratio.

[0007] Furthermore, under the first determination method, the central control unit records the time interval between the time node when the microphone picks up the speech corresponding to the subtitle and the time node when the subtitle is output as the delay time, and determines whether to generate the corresponding associative word library based on the delay time, wherein: The first association determination method is as follows: if the central control unit determines that the delay time does not meet the preset standard, the central control unit controls the microphone to re-acquire speech and performs word association operation during the process of generating subtitles based on the speech information by the speech recognition unit. When the speech recognition unit performs word association operation, if the characters output by the speech recognition unit are the same as the preset number of characters before the corresponding associated words in the associated word library, the central control unit controls the speech recognition unit to directly generate the associated words in the corresponding position in the subtitles; the first association determination method satisfies that the delay time is greater than or equal to the preset delay time in the central control unit. The second association determination method is that the central control unit determines whether the delay time meets the preset standard, and determines whether the next subtitle meets the preset standard; the second association determination method satisfies that the delay time is less than the preset delay time.

[0008] Furthermore, the central control unit, under the first association determination method, collects the conference audio from the microphone's historical recordings, extracts words from them, and arranges the words in descending order of their frequency of occurrence. The central control module selects a preset number of words from the sorted words and uses the selected set of words as the association word library. It also determines a preset quantity standard selection method for each association word based on the number of characters in each word, wherein: The first selection method is that the central control unit uses a first preset quantity as the preset quantity standard for the associated words; the first selection method satisfies that the number of characters in the words is greater than the preset first-level preset number of characters in the central control unit; The second selection method is that the central control unit uses a second preset quantity as the preset quantity standard for the associated words; the second selection method satisfies that the word count is less than or equal to the first-level preset word count and greater than or equal to the second-level preset word count preset in the central control unit, and the first-level preset word count is greater than the second-level preset word count; The third selection method is that the central control unit uses a third preset quantity as the preset quantity standard for the associated words; the third selection method satisfies that the number of characters in the words is less than the second-level preset number of characters.

[0009] Furthermore, under the second determination method, the central control unit counts the number of characters in the subtitle and determines whether to perform interruption word correction processing on the subtitle based on the number of characters, wherein: The first correction determination method is that the central control unit determines that the number of characters does not meet the preset standard, and reduces the number of subtitle characters to the corresponding value according to the difference between the number of characters in a single sentence and the preset number of characters; the first correction determination method satisfies that the number of characters in a single sentence is greater than or equal to the preset number of characters; The second correction determination method is that the central control unit determines that the number of characters meets the preset standard, verifies the integrity of the words at the end of the subtitle sentence, and determines whether to perform interruption word correction processing on the subtitle based on the integrity; the second correction determination method is satisfied that the number of characters in a single sentence is less than the preset number of characters.

[0010] Furthermore, under the first correction determination method, the central control unit records the difference between the number of characters in the subtitle and the preset number of characters as the character count difference, and divides the identified text in the subtitle into word groups. The central control unit divides the text that can form words into a word group, and determines the interruption method for the characters in the subtitle based on the character count difference, wherein: The first interruption method is that the central control unit uses a first interruption coefficient to adjust the number of word groups in the current subtitle to the first number of word groups; the first interruption method satisfies that the word count difference is less than the preset first-level preset word count difference in the central control unit; The second interruption method is that the central control unit uses a second interruption coefficient to adjust the number of word groups in the current subtitle to the second number of word groups; the second interruption method satisfies that the word count difference is greater than or equal to the first-level preset word count difference and less than or equal to the second-level preset word count difference preset in the central control unit, and the second-level preset word count difference is greater than the first-level preset word count difference; The third interruption method is that the central control unit uses a third interruption coefficient to adjust the number of word groups in the current sentence subtitle to the third number of word groups; the third interruption method satisfies that the word count difference is greater than the secondary preset word count difference.

[0011] Furthermore, under the second correction determination method, the central control unit verifies whether the words at the end of the sentence are complete to determine the subtitle output method, wherein: The first output method is that the central control unit determines whether to perform word association operation based on the delay time after judging that the subtitle is qualified; the first output method satisfies that the sentence-end phrase is complete and has a corresponding meaning; The second output method is that the central control unit determines that the single sentence is unqualified and completes the sentence with words at the end; the second output method satisfies the condition that the sentence phrase at the end is incomplete.

[0012] Furthermore, in the second output mode, the central control unit calculates the probability of the incomplete word by combining historical records and the text of the incomplete word, and selects the word with the highest probability to complete the incomplete word.

[0013] Furthermore, under the third determination method, the central control unit records the difference between the subtitle proportion and the secondary preset subtitle proportion as the proportion difference, and determines the adjustment method for the subtitle font size based on the proportion difference, wherein: The first proportion adjustment method is that the central control unit uses a first adjustment coefficient to adjust the font size of the subtitle to the first font size; the first proportion adjustment method satisfies that the proportion difference is greater than a preset first-level proportion difference in the central control unit; The second proportion adjustment method is that the central control unit uses a second adjustment coefficient to adjust the font size of the subtitle to the second font size; the second proportion adjustment method satisfies that the proportion difference is less than or equal to the first-level preset proportion difference and greater than or equal to the second-level preset proportion difference preset in the central control unit, and the first-level preset proportion difference is greater than the second-level preset proportion difference; The third proportion adjustment method is that the central control unit uses a third adjustment coefficient to adjust the font size of the subtitle to the third font size; the third proportion adjustment method satisfies that the proportion difference is less than the preset secondary proportion difference in the central control unit.

[0014] Furthermore, the central control unit determines the preset number of characters based on the number of subtitle characters generated within a preset time period in the central control unit.

[0015] Compared with existing technologies, the beneficial effects of this invention are that by calculating the ratio of subtitle area to the total screen area, the subtitle situation can be quickly determined, and the subtitles can be quickly corrected to make the proportion of subtitles to the screen more reasonable. This makes the subtitle content easier to read and understand, thereby improving the efficiency of the meeting. Simultaneously, by correcting the number of subtitle characters, this invention can make the subtitles more complete and semantically clearer. Alternatively, if the subtitles are too long, they can be interrupted while maintaining semantic integrity, thus making the subtitle content easier to read and understand, thereby improving the efficiency of the meeting.

[0016] Furthermore, by calculating the proportion of subtitles and comparing it with a preset standard, the present invention can quickly determine the corresponding judgment method, and perform corresponding processing according to different judgment results, thereby making the subtitle content easier to read and understand, and thus further improving the efficiency of meeting operation.

[0017] Furthermore, the present invention calculates the delay time and compares it with a preset standard to determine whether to generate the corresponding associative operation, thereby shortening the time for recognizing language and converting it into text by predicting words, thus further improving the efficiency of meeting operation.

[0018] Furthermore, this invention sorts subtitles by historical usage frequency and selects corresponding feature-related words based on selection coefficients for subtitles with different character counts. This allows the central control unit to quickly generate corresponding subtitles after recognizing the related words, shortening the time spent generating subtitles. Simultaneously, by selecting different numbers of related words based on their character counts in the related word library, the invention can more accurately select the corresponding words, improving the accuracy of the related word library. This makes the subtitle content easier to read and understand, further improving meeting efficiency. Furthermore, this invention quickly determines the correction method for subtitles by judging whether the number of subtitle characters meets a preset standard, thereby rapidly adjusting the number of subtitle characters. This makes the subtitle content easier to read and understand, further improving meeting efficiency.

[0019] Furthermore, this invention determines the corresponding interruption method by calculating the difference in the number of characters, which can quickly adjust the number of characters in the subtitles. By dividing the text into phrases to segment the subtitles, semantic integrity is maintained during interruptions, making the subtitle content easier to read and understand, thereby further improving the efficiency of the meeting.

[0020] Furthermore, this invention verifies the identified sentence by checking whether the words at the end of the subtitle are complete, preventing the formation of subtitles before a sentence is finished, which would cause the sentence to be segmented and unclear. When the subtitles are incomplete, a feature word library is used to supplement them, making the subtitle content easier to read and understand, thereby further improving the efficiency of the meeting.

[0021] Furthermore, by combining historical records to calculate probabilities, this invention can supplement incomplete parts of subtitles, making individual sentences more complete, thereby making the subtitle content easier to read and understand, and thus further improving the efficiency of meeting operations.

[0022] Furthermore, by calculating the ratio difference and comparing it with a preset standard, the present invention can quickly determine the adjustment method corresponding to the subtitles, thereby quickly adjusting the subtitle ratio to make the ratio of subtitles to the screen more reasonable, making the subtitle content easier to read and understand, and thus further improving the efficiency of the meeting.

[0023] Furthermore, by determining the preset number of characters based on actual conditions, this invention prevents the use of the same standard in different situations from resulting in too many or too few characters in the subtitles, making the number of characters in the subtitle output more stable, thereby making the subtitle content easier to read and understand, and thus further improving the efficiency of the meeting. Attached Figure Description

[0024] Figure 1This is a flowchart of the subtitle display method in video conferencing according to the present invention; Figure 2 This is a flowchart illustrating the determination method described in this invention. Figure 3 This is a flowchart illustrating the associative word selection method described in this invention. Figure 4 This is a flowchart illustrating the subtitle interruption determination method described in this invention. Detailed Implementation

[0025] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0026] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0027] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0028] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0029] Please see Figure 1 The diagram shown is a flowchart of the subtitle display method in video conferencing according to the present invention, including: Step S1: The microphone collects the test voice and converts the collected test voice into an electrical signal; In step S2, the voice recognition unit recognizes the audio information output by the microphone to generate subtitles that match the audio information and sends the subtitles to the display unit, which then displays the subtitles using the corresponding font size. Step S3: The central control unit calculates the ratio of the area of ​​the subtitles displayed in the display unit to the total area of ​​the screen and determines whether the subtitles output by the display unit meet the preset standard based on the ratio. When the central control unit determines that the subtitles output by the display unit do not meet the preset standard, it determines whether to perform interruption word correction processing on the words in the subtitles or adjust the font size of the subtitles to the corresponding value. Step S4: When the central control unit determines that the subtitles output by the display unit meet the preset standard, it determines whether to perform word association operation during the subtitle generation process based on the duration between the time node of the corresponding voice collected by the microphone and the time node of the output subtitles. When it determines that word association operation is required, it adjusts the corresponding parameters in the association word library to the corresponding values ​​based on the conference voice in the historical collection records of the microphone. In step S5, when the central control unit determines that the duration meets the preset standard, it selects the adjusted operating parameters to perform subtitle display processing on the audio in the meeting.

[0030] Please see Figure 2 As shown, it is a flowchart of the determination method of the present invention. In step S3, for a single subtitle displayed by the display unit, the central control unit records the ratio of the area of ​​the subtitle in the screen to the total area of ​​the screen as the subtitle ratio, and determines whether the subtitle meets the preset standard based on the subtitle ratio. The first determination method involves the central control unit determining that the subtitle meets a preset standard. The central control unit records the duration between the time node when the microphone picks up the speech corresponding to the subtitle and the time node when the subtitle is output to determine whether to perform word association operation during the subtitle generation process. The first determination method satisfies that the proportion of the subtitle is less than 10% of the preset first-level subtitle proportion in the central control unit. The second determination method is that the central control unit determines that the subtitle does not meet the preset standard, and the central control module determines whether to perform interruption word correction processing on the subtitle based on the number of characters in the subtitle; the second determination method satisfies that the proportion of the subtitle is greater than or equal to the proportion of the first-level preset subtitle and less than or equal to the proportion of the second-level preset subtitle in the central control unit (25%). The third determination method is that the central control unit determines that the subtitle does not meet the preset standard, and determines the adjustment method for the subtitle font size based on the difference between the subtitle ratio and the secondary preset subtitle ratio; the third determination method satisfies that the subtitle ratio is greater than the secondary preset subtitle ratio.

[0031] Specifically, under the first determination method, the central control unit records the time interval between the time node when the microphone picks up the speech corresponding to the subtitle and the time node when the subtitle is output as the delay time, and determines whether to generate the corresponding associative word library based on the delay time, wherein: The first association determination method is as follows: if the central control unit determines that the delay time does not meet the preset standard, the central control unit controls the microphone to re-acquire speech and performs word association operation during the process of generating subtitles based on the speech information by the speech recognition unit. When the speech recognition unit performs word association operation, if the characters output by the speech recognition unit are the same as the preset number of characters before the corresponding associated words in the associated word library, the central control unit controls the speech recognition unit to directly generate the associated words in the corresponding position in the subtitles; the first association determination method satisfies that the delay time is greater than or equal to the preset delay time of 0.5s in the central control unit. The second association determination method is that the central control unit determines whether the delay time meets the preset standard, and determines whether the next subtitle meets the preset standard; the second association determination method satisfies that the delay time is less than the preset delay time.

[0032] Please see Figure 3 The above describes a flowchart of the word association selection method of the present invention. The central control unit, under the first association determination method, collects conference audio from the microphone's historical recordings, extracts words from them, and arranges the words in descending order of their frequency of occurrence. The central control module selects a preset number of words from the sorted words and uses the selected set of words as the word association library. It also determines a preset selection method for each word association based on the number of characters in each word, wherein: The first selection method is that the central control unit uses a first preset quantity of 3 as the preset quantity standard for the associated words; the first selection method satisfies that the number of characters in the words is greater than the preset first-level preset number of characters of 5 in the central control unit; The second selection method is that the central control unit uses a second preset quantity 2 as the preset quantity standard for the associated words; the second selection method satisfies that the number of words is less than or equal to the first-level preset number of words and greater than or equal to the second-level preset number of words 3 preset in the central control unit; The third selection method is that the central control unit uses a third preset quantity of 1 as the preset quantity standard for the associated words; the third selection method satisfies that the number of characters in the words is less than the second-level preset number of characters.

[0033] Specifically, under the second determination method, the central control unit counts the number of characters in the subtitle and determines whether to perform interruption word correction processing on the subtitle based on the number of characters, wherein: The first correction determination method is that the central control unit determines that the number of characters does not meet the preset standard, and reduces the number of subtitle characters to the corresponding value according to the difference between the number of characters in a single sentence and the preset number of characters; the first correction determination method satisfies that the number of characters in a single sentence is greater than or equal to the preset number of characters 20; The second correction determination method is that the central control unit determines that the number of characters meets the preset standard, verifies the integrity of the words at the end of the subtitle sentence, and determines whether to perform interruption word correction processing on the subtitle based on the integrity; the second correction determination method is satisfied that the number of characters in a single sentence is less than the preset number of characters.

[0034] Please see Figure 4 As shown, this is a flowchart of the subtitle interruption method determination process according to the present invention. Under the first correction determination method, the central control unit records the difference between the number of subtitle characters and the preset number of characters as the character count difference, and divides the identified text in the subtitle into word groups. The central control unit divides the text that can form words into a word group, and determines the interruption method for the characters in the subtitle based on the character count difference, wherein: The first interruption method is that the central control unit uses a first interruption coefficient of 0.7 to adjust the number of word groups in the current subtitle to the first number of word groups; the first interruption method satisfies that the word count difference is less than the preset first-level preset word count difference of 10 in the central control unit; The second interruption method is that the central control unit uses a second interruption coefficient of 0.6 to adjust the number of word groups in the current subtitle to the second number of word groups; the second interruption method satisfies that the word count difference is greater than or equal to the first-level preset word count difference and less than or equal to the second-level preset word count difference of 20 preset in the central control unit; The third interruption method is that the central control unit uses a third interruption coefficient of 0.5 to adjust the number of word groups in the current sentence subtitle to the third number of word groups; the third interruption method satisfies that the word count difference is greater than the secondary preset word count difference.

[0035] Specifically, under the second correction determination method, the central control unit verifies whether the words at the end of the subtitle are complete to determine the subtitle output method, wherein: The first output method is that the central control unit determines whether to perform word association operation based on the delay time when the subtitle is deemed qualified; the first output method satisfies that the words at the end of the subtitle are complete and have corresponding meanings. The second output method is that the central control unit determines that the single sentence is unqualified and completes the words at the end of the subtitle; the second output method satisfies the condition that the words at the end of the subtitle are incomplete.

[0036] Specifically, in the second output mode, the central control unit calculates the probability of the incomplete word by combining historical records and the text of the incomplete word, and selects the word with the highest probability to complete the incomplete word.

[0037] Specifically, under the third determination method, the central control unit records the difference between the subtitle proportion and the secondary preset subtitle proportion as the proportion difference, and determines the adjustment method for the subtitle font size based on the proportion difference, wherein: The first proportion adjustment method is that the central control unit uses a first adjustment coefficient of 0.7 to adjust the font size of the subtitle to the first font size; the first proportion adjustment method satisfies that the proportion difference is greater than 15% of the preset first-level proportion difference in the central control unit; The second proportion adjustment method is that the central control unit uses a second adjustment coefficient of 0.8 to adjust the font size of the subtitle to the second font size; the second proportion adjustment method satisfies that the proportion difference is less than or equal to the first-level preset proportion difference and greater than or equal to the second-level preset proportion difference preset in the central control unit by 8%; The third proportion adjustment method is that the central control unit uses a third adjustment coefficient of 0.9 to adjust the font size of the subtitle to the third font size; the third proportion adjustment method satisfies that the proportion difference is less than the preset secondary proportion difference in the central control unit.

[0038] Specifically, the central control unit determines the preset number of characters based on the number of subtitle characters generated within a preset time period in the central control unit.

[0039] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0040] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for displaying subtitles in a video conference, characterized in that, include: Step S1: The microphone collects the test voice and converts the collected test voice into an electrical signal; In step S2, the voice recognition unit recognizes the audio information output by the microphone to generate subtitles that match the audio information and sends the subtitles to the display unit, which then displays the subtitles using the corresponding font size. Step S3: The central control unit calculates the ratio of the area of ​​the subtitles displayed in the display unit to the total area of ​​the screen and determines whether the subtitles output by the display unit meet the preset standard based on the ratio. When the central control unit determines that the subtitles output by the display unit do not meet the preset standard, it determines whether to perform interruption word correction processing on the words in the subtitles or adjust the font size of the subtitles to the corresponding value. Step S4: When the central control unit determines that the subtitles output by the display unit meet the preset standard, it determines whether to perform word association operation during the subtitle generation process based on the duration between the time node of the corresponding voice collected by the microphone and the time node of the output subtitles. When it determines that word association operation is required, it adjusts the corresponding parameters in the association word library to the corresponding values ​​based on the conference voice in the historical collection records of the microphone. In step S5, when the central control unit determines that the duration meets the preset standard, it selects the adjusted operating parameters to perform subtitle display processing on the audio in the meeting.

2. The subtitle display method in video conferencing according to claim 1, characterized in that, In step S3, for a single-sentence subtitle displayed by the display unit, the central control unit records the ratio of the subtitle's area on the screen to the total screen area as the subtitle ratio, and determines whether the subtitle meets a preset standard based on the subtitle ratio, wherein: The first determination method is that the central control unit determines that the subtitle meets the preset standard. The central control unit records the duration between the time node when the microphone collects the speech corresponding to the subtitle and the time node when the subtitle is output to determine whether to perform word association operation during the subtitle generation process. The first determination method satisfies that the proportion of the subtitle is less than the first-level preset subtitle proportion preset in the central control unit. The second determination method is that the central control unit determines that the subtitle does not meet the preset standard, and the central control module determines whether to perform interruption word correction processing on the subtitle based on the number of characters in the subtitle; the second determination method satisfies that the proportion of the subtitle is greater than or equal to the proportion of the first-level preset subtitle and less than or equal to the proportion of the second-level preset subtitle preset in the central control unit, and the proportion of the second-level preset subtitle is greater than the proportion of the first-level preset subtitle. The third determination method is that the central control unit determines that the subtitle does not meet the preset standard, and determines the adjustment method for the subtitle font size based on the difference between the subtitle ratio and the secondary preset subtitle ratio; the third determination method satisfies that the subtitle ratio is greater than the secondary preset subtitle ratio.

3. The subtitle display method in video conferencing according to claim 2, characterized in that, Under the first determination method, the central control unit records the time interval between the time node when the microphone picks up the speech corresponding to the subtitle and the time node when the subtitle is output as the delay time, and determines whether to generate the corresponding associative word library based on the delay time, wherein: The first association determination method is that if the central control unit determines that the delay time does not meet the preset standard, the central control unit controls the microphone to re-acquire the voice and performs word association operation during the process of the voice recognition unit generating subtitles based on the voice information. When the voice recognition unit performs word association operation, if the characters output by the voice recognition unit are the same as the preset number of characters before the corresponding associated words in the associated word library, the central control unit controls the voice recognition unit to directly generate the associated words in the corresponding position in the subtitles; the first association determination method satisfies that the delay time is greater than or equal to the preset delay time in the central control unit. The second association determination method is that the central control unit determines whether the delay time meets the preset standard, and determines whether the next subtitle meets the preset standard; the second association determination method satisfies that the delay time is less than the preset delay time.

4. The subtitle display method in video conferencing according to claim 3, characterized in that, The central control unit, under the first association determination method, collects conference audio from the microphone's historical recordings, extracts words from them, and arranges the words in descending order of frequency of occurrence. The central control module selects a preset number of words from the sorted words and uses the selected set of words as the association word library. It then determines a preset quantity selection method for each association word based on the number of characters in each word, wherein: The first selection method is that the central control unit uses a first preset quantity as the preset quantity standard for the associated words; the first selection method satisfies that the number of characters in the words is greater than the preset first-level preset number of characters in the central control unit; The second selection method is that the central control unit uses a second preset quantity as the preset quantity standard for the associated words; the second selection method satisfies that the word count is less than or equal to the first-level preset word count and greater than or equal to the second-level preset word count preset in the central control unit, and the first-level preset word count is greater than the second-level preset word count; The third selection method is that the central control unit uses a third preset quantity as the preset quantity standard for the associated words; the third selection method satisfies that the number of characters in the words is less than the second-level preset number of characters; Wherein, the second preset quantity is greater than the third preset quantity and less than the first preset quantity.

5. The subtitle display method in video conferencing according to claim 3, characterized in that, Under the second determination method, the central control unit counts the number of characters in the subtitle and determines the correction determination method for the subtitle based on the number of characters, wherein: The first correction determination method is that the central control unit determines that the number of characters does not meet the preset standard, and reduces the number of subtitle characters to the corresponding value according to the difference between the number of subtitle characters and the preset number of characters; the first correction determination method satisfies that the number of subtitle characters is greater than or equal to the preset number of characters; The second correction determination method is that the central control unit determines that the number of characters meets the preset standard, verifies the integrity of the words at the end of the subtitle sentence, and determines whether to perform interruption word correction processing on the subtitle based on the integrity; the second correction determination method is satisfied that the number of subtitle characters is less than the preset number of characters.

6. The subtitle display method in video conferencing according to claim 5, characterized in that, Under the first correction determination method, the central control unit records the difference between the number of characters in the subtitle and the preset number of characters as the character count difference, and divides the identified text in the subtitle into word groups. The central control unit groups the text that can form words into a word group, and determines the interruption method for the characters in the subtitle based on the character count difference, wherein: The first interruption method is that the central control unit uses a first interruption coefficient to adjust the number of word groups in the current subtitle to the first number of word groups; the first interruption method satisfies that the word count difference is less than the preset first-level preset word count difference in the central control unit; The second interruption method is that the central control unit uses a second interruption coefficient to adjust the number of word groups in the current subtitle to the second number of word groups; the second interruption method satisfies that the word count difference is greater than or equal to the first-level preset word count difference and less than or equal to the second-level preset word count difference preset in the central control unit, and the second-level preset word count difference is greater than the first-level preset word count difference; The third interruption method is that the central control unit uses a third interruption coefficient to adjust the number of word groups in the current sentence subtitle to the third number of word groups; the third interruption method satisfies the condition that the word count difference is greater than the secondary preset word count difference; Wherein, the second interrupt coefficient is greater than the third interrupt coefficient and less than the first interrupt coefficient.

7. The subtitle display method in video conferencing according to claim 5, characterized in that, Under the second correction determination method, the central control unit verifies whether the words at the end of the subtitle are complete to determine the subtitle output method, wherein: The first output method is that the central control unit determines whether to perform word association operation based on the delay time when the subtitle is deemed qualified; the first output method satisfies that the words at the end of the subtitle are complete and have corresponding meanings. The second output method is that the central control unit determines that the subtitle is unqualified and completes the words at the end of the subtitle; the second output method satisfies the condition that the words at the end of the subtitle are incomplete.

8. The subtitle display method in video conferencing according to claim 7, characterized in that, In the second output mode, the central control unit calculates the probability of the incomplete word by combining historical records and the text of the incomplete word, and selects the word with the highest probability to complete the incomplete word.

9. The subtitle display method in video conferencing according to claim 2, characterized in that, Under the third determination method, the central control unit records the difference between the subtitle proportion and the secondary preset subtitle proportion as the proportion difference, and determines the adjustment method for the subtitle font size based on the proportion difference, wherein: The first proportion adjustment method is that the central control unit uses a first adjustment coefficient to adjust the font size of the subtitle to the first font size; the first proportion adjustment method satisfies that the proportion difference is greater than a preset first-level proportion difference in the central control unit; The second proportion adjustment method is that the central control unit uses a second adjustment coefficient to adjust the font size of the subtitle to the second font size; the second proportion adjustment method satisfies that the proportion difference is less than or equal to the first-level preset proportion difference and greater than or equal to the second-level preset proportion difference preset in the central control unit, and the first-level preset proportion difference is greater than the second-level preset proportion difference; The third proportion adjustment method is that the central control unit uses a third adjustment coefficient to adjust the font size of the subtitle to the third font size; the third proportion adjustment method satisfies that the proportion difference is less than the preset secondary proportion difference in the central control unit; Wherein, the second adjustment coefficient is less than the third adjustment coefficient and greater than the first adjustment coefficient.

10. The method for displaying subtitles in a video conference according to claim 5, characterized in that, The central control unit determines the preset number of characters based on the number of subtitle characters generated within a preset time period.

Citation Information

Patent Citations

  • Subtitle display method and device in video conference and storage medium

    CN114339126A

  • Video conference association prompting method and system

    CN104639869A

  • Subtitle generation method, subtitle test method and subtitle processing equipment

    CN114125571A