Broadcast volume adjusting method and system

By obtaining the spokesperson and ambient audio signals for voice transcribing and text comparison, and adjusting the broadcast volume, the problem of unclear sound transmission caused by fixed volume adjustment methods in the existing technology is solved, and the automatic adjustment of the broadcast volume is realized, which is suitable for a variety of purposes. Scenarios.

CN119071688APending Publication Date: 2024-12-03GUANGZHOU BAOLUN ELECTRONICS CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410991142.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the prior art, the broadcast volume adjustment method is fixed and cannot be adjusted in real time according to changes in different scenes, resulting in unclear voice transmission of spokespersons.

Method used

By obtaining the audio signals of the spokesperson and the environment, performing voice transliteration to obtain voice text, and comparing text according to preset deviation requirements, adjusting the broadcast volume level, realizing self-test sound reinforcement effect, suitable for diverse scenarios, and reducing manual detection. Steps to improve the clarity of sound transmission.

Benefits of technology

It improves the clarity of the speaker's voice transmission, avoids the problem of too small or too large volume caused by fixed adjustment methods, and realizes automatic up and down adjustment of the broadcast volume level, which is suitable for diverse scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119071688A_ABST
    Figure CN119071688A_ABST
Patent Text Reader

Abstract

The invention provides a broadcast volume adjusting method and system, and the method comprises the steps: obtaining a first digital audio signal based on the broadcast voice of a spokesman; acquiring a first voice text based on the first digital audio signal; acquiring a second voice text based on the first digital audio signal and an environment audio signal; based on a preset deviation requirement, performing deviation comparison on the first voice text and the second voice text through a preset text word number to obtain a plurality of text deviation results; and when the continuous preset deviation times of the plurality of text deviation results do not meet the preset deviation requirement, adjusting the broadcast volume level. The problem that in the prior art, volume adjustment setting is fixed and cannot be adjusted according to changes of application scenes in real time, and consequently sound transmission of a spokesman is not clear is solved. The broadcast volume adjusting method provided by the invention is suitable for diversified scenes, and the sound transmission definition of the spokesman is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of volume control, and in particular to a broadcast volume adjustment method and system. Background Art

[0002] In scenarios such as subways, high-speed trains and airports, radio, as a news dissemination medium, is generally used for notifications, broadcasts and emergency alarms. However, in different environments, there is still the problem that the public cannot effectively receive key information due to the fixed method of adjusting the radio volume.

[0003] In the prior art, a fixed voice playback task or music playback task is segmented through a segmentation module, and the ambient noise value is obtained through a sound pickup module according to the intervals between the segments. Then, a fixed formula is used to calculate the relationship between the speaker volume and the ambient noise, so as to automatically adjust the speaker volume. Since the formula of this technology is fixed, it cannot be universally used for different application scenarios. The volume may be too loud or too low, and it is impossible to know whether the on-site speech can be clearly heard. In addition, the scope of application is limited, and it cannot be used for real-time speech. Summary of the invention

[0004] Based on the above problems, the present invention proposes a broadcast volume adjustment method and system to solve the problem that the volume adjustment setting in the prior art is fixed and cannot be adjusted in real time according to changes in application scenarios, resulting in unclear transmission of the speaker's voice.

[0005] To achieve the above object, an embodiment of the present invention provides a method for adjusting broadcast volume, comprising:

[0006] Based on the speaker's broadcast voice, obtaining a first digital audio signal;

[0007] Based on the first digital audio signal, obtaining a first voice text;

[0008] Acquire a second voice text based on the first digital audio signal and the ambient audio signal;

[0009] Based on the preset deviation requirement, the first voice text and the second voice text are compared for deviation by a preset number of text words to obtain a number of text deviation results;

[0010] When the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times, the broadcast volume level is adjusted.

[0011] The embodiment of the present invention proposes a broadcast volume adjustment method, which obtains a first audio signal and an ambient audio signal, and obtains a first voice text and a second voice text through voice transcription, converts the volume adjustment problem into a text comparison problem according to deviation requirements, and adjusts the volume by judging whether the text content is clear and correct. The method has a self-checking sound reinforcement effect function, reduces the steps of manual detection, improves the accuracy of data processing, and improves the clarity of the speaker's voice transmission. At the same time, since the volume is adjusted by text comparison, there is no restriction on the broadcast format, and it is suitable for a variety of scenarios, preventing the volume from being too small or too large due to the non-universality of the fixed adjustment method, and further improves the clarity of the speaker's voice transmission.

[0012] Further, the acquiring of the second voice text based on the first digital audio signal and the ambient audio signal is specifically:

[0013] Acquire a first digital audio signal corresponding to the speaker's broadcast voice;

[0014] Performing analog amplification on the first digital audio signal to obtain an analog audio signal;

[0015] Constructing a second digital audio signal by acquiring the analog audio signal and the ambient audio signal;

[0016] A second voice text is obtained by performing voice transcription on the second digital audio signal.

[0017] Furthermore, based on the preset deviation requirement, the first voice text and the second voice text are compared for deviation by a preset number of text words to obtain several text deviation results, specifically:

[0018] According to a preset number of text words, the first voice text and the second voice text are compared word by word to obtain a number of text comparison results;

[0019] According to the preset deviation requirement, the plurality of text comparison results are subjected to deviation comparison to obtain a plurality of text deviation results.

[0020] Further, when the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times, the broadcast volume level is adjusted, specifically:

[0021] By comparing the plurality of text deviation results one by one, when a preset number of deviations occur continuously and fail to meet the preset deviation requirement, increasing the broadcast volume level by one level;

[0022] When the plurality of text deviation results all meet the preset deviation requirement, the current broadcast volume level is maintained.

[0023] Furthermore, the method further includes reacquiring the first voice text and the second voice text whenever the broadcast volume level is adjusted;

[0024] Based on the reacquired first voice text and the second voice text, updating a number of text deviation results;

[0025] When the plurality of text deviation results all meet the preset deviation requirements, maintaining the current broadcast volume level;

[0026] When the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times, the broadcast volume level is increased by one level, and the above steps are repeated until the text deviation result meets the preset deviation requirement.

[0027] A broadcast volume adjustment method proposed in an embodiment of the present invention automatically increases a volume level when the text deviation is large, and then detects again to determine whether it is clear. If it is not clear, the volume level is automatically increased again. If it is clear, the volume level is maintained, thereby realizing automatic upward adjustment of the broadcast volume level.

[0028] Furthermore, the method further comprises the following steps:

[0029] When the first digital audio signal is not received continuously within a preset time, based on a preset time interval, an average decibel value of the broadcast environment noise is picked up to obtain a noise point at a first moment and a noise point at a second moment;

[0030] The noise comparison result is obtained by comparing the difference between the average decibel value of the noise point at the first moment and the average decibel value of the noise point at the second moment;

[0031] Based on the noise comparison result, the broadcast volume is adjusted and the noise point at the first moment and the noise point at the second moment are updated.

[0032] Further, based on the noise comparison result, the broadcast volume is adjusted and the noise point at the first moment and the noise point at the second moment are updated, specifically:

[0033] When the noise comparison result meets the preset volume drop threshold, the broadcast volume is reduced according to the volume adjustment formula, and the average decibel value of the noise point at the second moment is updated as the noise point at the first moment, and the noise point at the next moment is obtained as the noise point at the second moment;

[0034] When the noise comparison result does not meet the preset volume drop threshold, the broadcast volume is not adjusted and the noise point at the first moment and the noise point at the second moment are not updated.

[0035] Furthermore, the volume adjustment formula is: decreased volume level = (noise point at the second moment - noise point at the first moment) / N, wherein the decreased volume level is an integer; N is a preset volume decrease threshold; each time a decreased volume level is calculated, the broadcast volume is reduced by one level.

[0036] A broadcast volume adjustment method proposed in an embodiment of the present invention automatically reduces the broadcast volume level according to changes in ambient noise by means of ambient noise detection, thereby achieving automatic reduction adjustment of the broadcast volume level so that a suitable sound reinforcement volume can be obtained when the broadcast is played again next time.

[0037] The embodiment of the present invention also provides a broadcast volume adjustment system, comprising: an audio signal acquisition module, a first text conversion module, a second text conversion module, a text comparison module and a first volume adjustment module;

[0038] The audio signal acquisition module is used to acquire a first digital audio signal based on the speaker's broadcast voice;

[0039] The first text conversion module is used to obtain a first voice text based on the first digital audio signal;

[0040] The second text conversion module is used to obtain a second voice text based on the first digital audio signal and the ambient audio signal;

[0041] The text comparison module is used to perform a deviation comparison on the first voice text and the second voice text based on a preset deviation requirement and a preset number of text words to obtain a plurality of text deviation results;

[0042] The first volume adjustment module is used to adjust the broadcast volume level when the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times.

[0043] The embodiment of the present invention proposes a broadcast volume adjustment system, which obtains a first audio signal and an ambient audio signal through a first text conversion module, an audio signal acquisition module and a second text conversion module, obtains a first voice text and a second voice text through voice transcription, converts the volume adjustment problem into a text comparison problem according to deviation requirements, and determines whether the text content is clear and correct through a text comparison module, thereby adjusting the volume through a first volume adjustment module. The system has a self-checking sound reinforcement effect function, reduces the steps of manual detection, improves the accuracy of data processing, and improves the clarity of the speaker's voice transmission. At the same time, since the volume is adjusted by text comparison through the text comparison module, there is no restriction on the broadcast form, and it is suitable for a variety of scenarios, preventing the volume from being too small or too large due to the non-universality of the fixed adjustment method, and further improves the clarity of the speaker's voice transmission.

[0044] Furthermore, it also includes: a noise recognition module, a noise comparison module and a second volume adjustment module;

[0045] The noise recognition module is used to pick up the average decibel value of the broadcast environment noise based on the preset time interval when the first digital audio signal is not received continuously within the preset time, and obtain the noise point at the first moment and the noise point at the second moment;

[0046] The noise comparison module is used to obtain a noise comparison result by comparing the difference between the average decibel value of the noise point at the first moment and the average decibel value of the noise point at the second moment;

[0047] The second volume adjustment module is used to adjust the broadcast volume and update the noise point at the first moment and the noise point at the second moment based on the noise comparison result.

[0048] A broadcast volume adjustment system proposed in an embodiment of the present invention automatically reduces the broadcast volume level according to changes in the ambient noise by using an ambient noise detection method through a noise recognition module, and then automatically adjusts the broadcast volume level through a second volume adjustment module, so that there can be an appropriate sound reinforcement volume when the broadcast is played again next time. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flow chart of a method for adjusting the volume of a broadcast provided in accordance with an embodiment of the present invention Figure 1 ;

[0050] Figure 2 A flow chart of a method for adjusting the volume of a broadcast provided in accordance with an embodiment of the present invention Figure 2 ;

[0051] Figure 3 A flow chart of a method for adjusting the volume of a broadcast provided in accordance with an embodiment of the present invention Figure 3 ;

[0052] Figure 4 A schematic diagram of a module structure of a broadcast volume adjustment system provided in an embodiment of the present invention Figure 1 ;

[0053] Figure 5 A schematic diagram of a module structure of a broadcast volume adjustment system provided in an embodiment of the present invention Figure 2 ;

[0054] Figure 6 A schematic diagram of the structure of a broadcast volume adjustment application module of a broadcast volume adjustment method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] The existing technology calculates the relationship between the speaker volume and the ambient noise based on a fixed formula to automatically adjust the speaker volume; for different scenarios, the speaker volume may be too low and the ambient noise may be too high, causing people to not be able to hear the broadcast content; or the speaker volume may be too high, seriously affecting people's normal communication and even causing noise pollution; the existing technology does not have the ability to check whether the broadcast content is clear, and requires manual inspection, which will lead to increased manpower investment. For the real-time speech of the speaker, the existing technology cannot segment his speech, so there is no gap to obtain the ambient noise, resulting in the staff not being able to automatically adjust the speaker volume when speaking in real time. In order to solve the above problems, a broadcast volume adjustment method of the present invention is proposed.

[0057] In the embodiments of the present invention, see Figure 6 , Figure 6 A schematic diagram of a broadcast volume adjustment application module structure of a broadcast volume adjustment method provided by an embodiment of the present invention. Figure 6 The application module shown explains the step flow of an embodiment of the present invention, and the application module includes: a speech transcription module 601, a broadcast server 602, a microphone 603, a pickup 604, a power amplification module 608 and a speaker 609, wherein the pickup 604 also includes a pickup module 605, a processor 606 and an audio processing module 607; when the scene is large, multiple pickups and multiple speakers can be connected to meet scenes of different sizes.

[0058] It is worth mentioning that Figure 6 The broadcast volume adjustment application module shown is only used as one possible implementation method of the embodiment of the present invention, and is not specifically limited and will not be described in detail below.

[0059] Example 1

[0060] See also Figure 1 , Figure 1 A flow chart of a method for adjusting the volume of a broadcast provided in accordance with an embodiment of the present invention Figure 1 .like Figure 1 As shown, the embodiment of the present invention provides a broadcast volume adjustment method, including steps 101 to 105, each step is specifically as follows:

[0061] Step 101, obtaining a first digital audio signal based on a speaker's broadcast voice;

[0062] As an example of this embodiment, the speaker speaks through microphone 603, and the speech content is converted into an analog audio signal, and the corresponding digital audio signal (equivalent to the first audio signal) is obtained through digital-to-analog conversion; the specific digital-to-analog conversion method can be obtained using conventional existing technologies.

[0063] Step 102, obtaining a first voice text based on the first digital audio signal;

[0064] As an example of this embodiment, a digital audio signal obtained from a microphone is transmitted to a broadcast server 602 for distribution, and a segment of a digital audio signal is sent to a speech transcription module 601 for speech transcription to obtain a speech text (equivalent to a first speech text) corresponding to the digital audio signal. The specific speech transcription process can be implemented using existing conventional technologies.

[0065] Step 103, acquiring a second voice text based on the first digital audio signal and the ambient audio signal;

[0066] As an example of this embodiment, a first digital audio signal corresponding to the speaker's broadcast voice is obtained; the first digital audio signal is analog-amplified to obtain an analog audio signal; a second digital audio signal is constructed by obtaining the analog audio signal and the ambient audio signal; and a second voice text is obtained by voice-transcription of the second digital audio signal. Specifically, another digital audio signal is allocated by the broadcast server 602 to be sent to the power amplifier module 608 for amplification processing, and then broadcasted through the speaker 609, and at the same time, the microphone 604 picks up the broadcast and ambient sound emitted by the speaker 609 through the pickup module 605 to obtain the analog audio signal and the ambient audio signal, and then the processor 606 and the audio processing module 607 perform digital-to-analog conversion and sound effect processing in sequence to obtain the corresponding digital audio signal (equivalent to the second digital audio signal), and then the digital audio signal (equivalent to the second digital audio signal) is transcribed into the corresponding voice text (equivalent to the second voice text) through the voice transcription module 601. A specific explanation is that the digital audio signal used to generate the second voice text in this step is the same segment as the digital audio signal used to generate the first voice text in step 102. The digital audio signal is copied through the broadcast server 602, one segment is used to generate the first voice text, and the other segment is used to generate the second voice text.

[0067] Step 104, based on a preset deviation requirement, performing a deviation comparison on the first voice text and the second voice text by using a preset number of text words to obtain a number of text deviation results;

[0068] As an example of this embodiment, according to a preset number of text characters, the first voice text and the second voice text are compared word by word to obtain a number of text comparison results; according to a preset deviation requirement, the several text comparison results are compared for deviation to obtain a number of text deviation results. One specific implementation method is to receive the first voice text (hereinafter referred to as text 1) and the second voice text (hereinafter referred to as text 2) through the broadcast server 602, compare the content of text 2 with the content of text 1, compare 20 characters once, obtain a number of text comparison results, and determine whether a number of text comparison results have a 20% deviation to obtain a number of text deviation results.

[0069] Step 105: When the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times, adjusting the broadcast volume level.

[0070] As an example of this embodiment, by comparing the several text deviation results one by one, when the preset deviation number of times does not meet the preset deviation requirement, the broadcast volume level is increased by one level; when the several text deviation results all meet the preset deviation requirement, the current broadcast volume level is maintained. One specific implementation method is that when text 2 deviates from text 1 by more than 20% in two consecutive text comparisons, it is determined that the broadcast sound in the live sound picked up by the microphone 604 has been interfered by the environmental noise, resulting in a serious deviation in the content of text 2. At this time, the broadcast server 602 sends a signal to increase the volume level to the power amplifier module 608 to increase the gain, so that the volume of the speaker 609 is increased by one volume level.

[0071] As another example of this embodiment, see Figure 2 , Figure 2 A flow chart of a method for adjusting the volume of a broadcast provided in accordance with an embodiment of the present invention Figure 2 ;like Figure 2As shown. Step 201, whenever the broadcast volume level is adjusted, the first voice text and the second voice text are retrieved; Step 202, based on the retrieved first voice text and the second voice text, a number of text deviation results are updated; Step 203, when the several text deviation results all meet the preset deviation requirements, the current broadcast volume level is maintained; Step 204, when the several text deviation results do not meet the preset deviation requirements for consecutive preset deviation times, the broadcast volume level is increased by one level, and the above steps are repeated until the text deviation results meet the preset deviation requirements. One specific implementation method is to repeat steps 101-104 to perform another text comparison. If there are two consecutive text comparisons again, the deviation of text 2 from text 1 exceeds 20%, then the broadcast server 602 determines that the broadcast sound is still disturbed by environmental noise, and then sends a signal to increase the volume level of the speaker 609; if there are no two consecutive text comparisons, the deviation of text 2 from text 1 exceeds 20%, then the broadcast server 602 determines that the broadcast sound is no longer disturbed by environmental noise, and people on the scene can clearly hear the broadcast content, and the speaker 609 maintains the volume level for sound amplification. It is worth mentioning that when the broadcast sound has reached the maximum adjustable upper limit and is still judged to be interfered by environmental noise, it is prompted that the current equipment no longer meets the on-site requirements. Please replace it with a device that meets the requirements in time.

[0072] As another example of this embodiment, see Figure 3 , Figure 3 A flow chart of a method for adjusting the volume of a broadcast provided in accordance with an embodiment of the present invention Figure 3 ;like Figure 3 As shown, in step 301, when the first digital audio signal is not received continuously within a preset time, based on a preset time interval, the average decibel value of the broadcast environment noise is picked up to obtain the noise point at the first moment and the noise point at the second moment;

[0073] As an example of this embodiment, when the broadcast server 602 does not receive the audio signal of the microphone 603 for 2 consecutive seconds or the voice playing task and the music playing task in the broadcast server 602 are not being played, an instruction is automatically sent to turn on the noise detection mode of the pickup 604, that is, the audio processing module 607 of the pickup 604 is turned off, and the environmental noise is picked up once every 3 seconds, and the average decibel value is taken, and the average decibel value of the environmental noise picked up by the pickup 604 for the first time is recorded in the broadcast server 602 as noise recording point 1 (equivalent to the noise point at the first moment); the average decibel value of the environmental noise picked up each time thereafter is used as noise recording point 2 (equivalent to the noise point at the second moment). The audio processing module 607 has a variety of audio processing algorithms, such as: automatic gain, automatic mixing, feedback suppression, noise elimination, echo elimination, equalizer, compressor and limiter, etc.

[0074] Step 302, obtaining a noise comparison result by comparing the difference between the average decibel values ​​of the noise point at the first moment and the noise point at the second moment;

[0075] As an example of this embodiment, when the noise comparison result meets the preset volume drop threshold, the broadcast volume is reduced according to the volume adjustment formula and the average decibel value of the noise point at the second moment is updated as the noise point at the first moment, and the noise point at the next moment is obtained as the noise point at the second moment; when the noise comparison result does not meet the preset volume drop threshold, the broadcast volume is not adjusted and the noise point at the first moment and the noise point at the second moment are not updated. One specific implementation method is to compare noise recording point 2 with noise recording point 1. If the average decibel value of noise recording point 2 compared with noise recording point 1 drops by more than 5dB, the speaker volume level is automatically adjusted according to the formula of reducing one volume level for every 5dB drop.

[0076] As another example of this embodiment, the volume adjustment formula is: volume reduction level = (noise point at the second moment - noise point at the first moment) / N, where the volume reduction level is an integer; N is a preset volume reduction threshold; each time a volume reduction level is calculated, the broadcast volume is reduced by one level. For a specific example, the volume reduction level = (noise recording point 2 - noise recording point 1) / 5, which is an integer.

[0077] Step 303, based on the noise comparison result, adjust the broadcast volume and update the noise point at the first moment and the noise point at the second moment. In one specific example, after the volume is adjusted, the value of noise recording point 1 is updated to the value of noise recording point 2, and the above logic is continued to automatically adjust the volume level of the speaker 609; if the average decibel value of noise recording point 2 compared with noise recording point 1 decreases by less than 5dB, the volume level of the speaker 609 will not be reduced, the value of noise recording point 1 will not be updated, and the value of noise recording point 2 will continue to be updated and compared in real time according to the average decibel value of the on-site environmental noise; when the volume level of the speaker 609 drops to the default on-site volume level, the volume of the speaker 609 maintains the default volume level and no longer decreases, and the noise detection mode is turned off, that is, the audio processing module 607 of the pickup 604 is turned on.

[0078] As another example of this embodiment, the environmental noise detection mode can be manually turned on to execute the automatic adjustment process of the speaker volume level from step 301 to step 303; or the system volume can be restored to the default design volume level with one click.

[0079] The embodiment of the present invention provides a broadcast volume adjustment method. By acquiring a first audio signal and an ambient audio signal, and obtaining a first voice text and a second voice text through voice transcription, the volume adjustment problem is converted into a text comparison problem according to the deviation requirement. By judging whether the text content is clear and correct, the volume is adjusted. The method has a self-checking sound reinforcement effect function, reduces the steps of manual detection, improves the accuracy of data processing, and improves the clarity of the speaker's voice transmission. At the same time, since the volume is adjusted by text comparison, there is no restriction on the broadcast form, and it is suitable for a variety of scenes, and the situation that the volume is too small or too large due to the non-universality of the fixed adjustment method is prevented, and the clarity of the speaker's voice transmission is further improved. When the text deviation is large, a volume level is automatically increased, and then it is detected again to determine whether it is clear. If it is not clear, a volume level is automatically increased. If it is clear, the volume level is maintained, thereby realizing automatic increase adjustment of the broadcast volume level, and the broadcast volume level is automatically reduced according to the change of the ambient noise by detecting the ambient noise, and the automatic decrease adjustment of the broadcast volume level is realized, so that there can be a suitable sound reinforcement volume when the broadcast is replayed next time.

[0080] Example 2

[0081] See also Figure 4 , Figure 4 A schematic diagram of a module structure of a broadcast volume adjustment system provided in an embodiment of the present invention Figure 1 .like Figure 4 As shown, an embodiment of the present invention provides a broadcast volume adjustment system, comprising:

[0082] An audio signal acquisition module 401, a first text conversion module 402, a second text conversion module 403, a text comparison module 404 and a first volume adjustment module 405;

[0083] The audio signal acquisition module 401 is used to acquire a first digital audio signal based on the speaker's broadcast voice;

[0084] The first text conversion module 402 is used to obtain a first voice text based on the first digital audio signal;

[0085] The second text conversion module 403 is used to obtain a second voice text based on the first digital audio signal and the ambient audio signal;

[0086] The text comparison module 404 is used to perform a deviation comparison on the first voice text and the second voice text based on a preset deviation requirement and a preset number of text words to obtain a number of text deviation results;

[0087] The first volume adjustment module 405 is used to adjust the broadcast volume level when the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times.

[0088] As an example of this embodiment, see Figure 5 , Figure 5 A schematic diagram of a module structure of a broadcast volume adjustment system provided in an embodiment of the present invention Figure 2 ;like Figure 5 As shown, the embodiment of the present invention provides a broadcast volume adjustment system, which also includes: a noise identification module 501, a noise comparison module 502 and a second volume adjustment module 503;

[0089] The noise identification module 501 is used to pick up the average decibel value of the broadcast environment noise based on the preset time interval when the first digital audio signal is not received continuously within the preset time, and obtain the noise point at the first moment and the noise point at the second moment;

[0090] The noise comparison module 502 is used to obtain a noise comparison result by comparing the difference between the average decibel value of the noise point at the first moment and the average decibel value of the noise point at the second moment;

[0091] The second volume adjustment module 503 is used to adjust the broadcast volume and update the noise point at the first moment and the noise point at the second moment based on the noise comparison result.

[0092] The embodiment of the present invention provides a broadcast volume adjustment system, which obtains a first audio signal and an ambient audio signal through a first text conversion module, an audio signal acquisition module and a second text conversion module, obtains a first voice text and a second voice text through voice transcription, converts the volume adjustment problem into a text comparison problem according to the deviation requirement, and determines whether the text content is clear and correct through the text comparison module, so as to adjust the volume through the first volume adjustment module, has a self-checking sound reinforcement effect function, reduces the steps of manual detection, improves the accuracy of data processing, and improves the clarity of the speaker's voice transmission; at the same time, because the volume is adjusted by text comparison through the text comparison module, there is no restriction on the broadcast form, and it is suitable for various scenes, and the situation that the volume is too small or too large due to the non-universality of the fixed adjustment method is prevented, and the clarity of the speaker's voice transmission is further improved. The noise recognition module adopts the environmental noise detection method to automatically reduce the broadcast volume level according to the change of the environmental noise, and then the second volume adjustment module is used to realize the automatic reduction adjustment of the broadcast volume level, so that there can be a suitable sound reinforcement volume when the broadcast is replayed next time.

[0093] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

[0094] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0095] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

Claims

1. A method for adjusting broadcast volume, characterized in that: include: Based on the speaker's broadcast voice, obtaining a first digital audio signal; Based on the first digital audio signal, obtaining a first voice text; Acquire a second voice text based on the first digital audio signal and the ambient audio signal; Based on the preset deviation requirement, the first voice text and the second voice text are compared for deviation by a preset number of text words to obtain a number of text deviation results; When the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times, the broadcast volume level is adjusted.

2. A broadcast volume adjustment method as claimed in claim 1, characterized in that: The acquiring of the second voice text based on the first digital audio signal and the ambient audio signal is specifically: Acquire a first digital audio signal corresponding to the speaker's broadcast voice; Performing analog amplification on the first digital audio signal to obtain an analog audio signal; Constructing a second digital audio signal by acquiring the analog audio signal and the ambient audio signal; A second voice text is obtained by performing voice transcription on the second digital audio signal.

3. A broadcast volume adjustment method as claimed in claim 1, characterized in that: Based on the preset deviation requirement, the first voice text and the second voice text are compared for deviation by a preset number of text words to obtain several text deviation results, specifically: According to a preset number of text words, the first voice text and the second voice text are compared word by word to obtain a number of text comparison results; According to the preset deviation requirement, the plurality of text comparison results are subjected to deviation comparison to obtain a plurality of text deviation results.

4. A method for adjusting broadcast volume as claimed in claim 1, characterized in that: When the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times, the broadcast volume level is adjusted, specifically: By comparing the plurality of text deviation results one by one, when a preset number of deviations occur continuously and fail to meet the preset deviation requirement, increasing the broadcast volume level by one level; When the plurality of text deviation results all meet the preset deviation requirement, the current broadcast volume level is maintained.

5. A broadcast volume adjustment method as claimed in claim 1, characterized in that: Also includes: Whenever the broadcast volume level is adjusted, the first voice text and the second voice text are reacquired; Based on the reacquired first voice text and the second voice text, updating a number of text deviation results; When the plurality of text deviation results all meet the preset deviation requirements, maintaining the current broadcast volume level; When the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times, the broadcast volume level is increased by one level, and the above steps are repeated until the text deviation result meets the preset deviation requirement.

6. A broadcast volume adjustment method according to any one of claims 1 to 5, characterized in that: The following steps are also included: When the first digital audio signal is not received continuously within a preset time, based on a preset time interval, an average decibel value of the broadcast environment noise is picked up to obtain a noise point at a first moment and a noise point at a second moment; The noise comparison result is obtained by comparing the difference between the average decibel value of the noise point at the first moment and the average decibel value of the noise point at the second moment; Based on the noise comparison result, the broadcast volume is adjusted and the noise point at the first moment and the noise point at the second moment are updated.

7. A broadcast volume adjustment method as claimed in claim 6, characterized in that: Based on the noise comparison result, the broadcast volume is adjusted and the noise point at the first moment and the noise point at the second moment are updated, specifically: When the noise comparison result meets the preset volume drop threshold, the broadcast volume is reduced according to the volume adjustment formula, and the average decibel value of the noise point at the second moment is updated as the noise point at the first moment, and the noise point at the next moment is obtained as the noise point at the second moment; When the noise comparison result does not meet the preset volume drop threshold, the broadcast volume is not adjusted and the noise point at the first moment and the noise point at the second moment are not updated.

8. A broadcast volume adjustment method as claimed in claim 7, characterized in that: The volume adjustment formula is: decreased volume level = (noise point at the second moment - noise point at the first moment) / N, wherein the decreased volume level is an integer; N is a preset volume decrease threshold; each time a decreased volume level is calculated, the broadcast volume is reduced by one level.

9. A broadcast volume adjustment system, characterized in that: The method for adjusting the broadcast volume according to any one of claims 1 to 8 is implemented, comprising: An audio signal acquisition module, a first text conversion module, a second text conversion module, a text comparison module and a first volume adjustment module; The audio signal acquisition module is used to acquire a first digital audio signal based on the speaker's broadcast voice; The first text conversion module is used to obtain a first voice text based on the first digital audio signal; The second text conversion module is used to obtain a second voice text based on the first digital audio signal and the ambient audio signal; The text comparison module is used to perform a deviation comparison on the first voice text and the second voice text based on a preset deviation requirement and a preset number of text words to obtain a plurality of text deviation results; The first volume adjustment module is used to adjust the broadcast volume level when the plurality of text deviation results fail to meet the preset deviation requirement for consecutive preset deviation times.

10. A broadcast volume adjustment system as claimed in claim 9, characterized in that: Also includes: A noise recognition module, a noise comparison module and a second volume adjustment module; The noise recognition module is used to pick up the average decibel value of the broadcast environment noise based on the preset time interval when the first digital audio signal is not received continuously within the preset time, and obtain the noise point at the first moment and the noise point at the second moment; The noise comparison module is used to obtain a noise comparison result by comparing the difference between the average decibel value of the noise point at the first moment and the average decibel value of the noise point at the second moment; The second volume adjustment module is used to adjust the broadcast volume and update the noise point at the first moment and the noise point at the second moment based on the noise comparison result.

Citation Information

Patent Citations

  • Voice playing method and system

    CN105281693A

  • Method and device for adjusting audio playing volume and audio playing system

    CN115904299A

  • Automatic broadcast sound conditioning device, automatic broadcast sound conditioning method, and program

    JP2022158605A

  • Method and apparatus for controlling automatically sound level in mobile sounder

    KR1020080071860A