Multifunctional integrated song ordering machine

Abstract

The invention discloses a multifunctional integrated song ordering machine, and the machine comprises an acquisition module which is in wireless communication connection with N microphones, and is used for obtaining N paths of singing sound information outputted by the N microphones, and N is greater than or equal to 2; the division module is connected with the acquisition module and is used for acquiring accompaniment audio and original singing audio of the current on-demand song and dividing the on-demand song into a plurality of singing intervals according to the accompaniment audio and the original singing audio; the control module is connected with the dividing module and the playing device, and the control module is used for dividing the middle N paths of singing sound information into first singing information and at least one piece of second singing information in the singing interval, adjusting the accompaniment audio and the original singing audio according to the first singing information and the second singing information and outputting the accompaniment audio and the original singing audio to the playing device; wherein the singing effect of the first singing information is better than that of the second singing information. According to the technical scheme of the invention, the playing device can play the accompaniment audio and the original audio which are more accordant with the overall chorus effect of the current playing interval.

Description

Technical Field

[0001] The present invention relates to the technical field of a multifunctional integrated song requesting machine, in particular to a multifunctional integrated song requesting machine. Background Art

[0002] There are two types of karaoke machines: commercial and home. Commercial karaoke machines are usually found in entertainment venues such as KTV boxes or mini KTVs. Usually, karaoke machines need to have multiple functions such as song selection, accompaniment selection, original singer selection, intelligent accompaniment function, venue equipment linkage, etc. In traditional karaoke machine technology, the intelligent accompaniment function is usually designed to adjust the accompaniment audio and original singer audio according to the user's actual singing effect, so as to achieve a more perfect overall singing effect for the user.

[0003] However, the intelligent singing accompaniment function currently only supports the use of a single user singing, and it is not supported in a multi-person chorus scenario, which cannot meet the needs of commercial karaoke machines. Summary of the invention

[0004] The main purpose of the present invention is to provide a multifunctional integrated song requesting machine, aiming to solve the defect that the intelligent singing accompaniment function does not support the multi-person chorus scene.

[0005] To achieve the above object, the multifunctional integrated song requesting machine proposed by the present invention is used to be connected with N microphones and playback devices, and the multifunctional integrated song requesting machine comprises: The acquisition module is wirelessly connected to the N microphones to obtain N channels of singing sound information output by the N microphones, where N is greater than or equal to 2; A division module, used to obtain the accompaniment audio and the original singing audio of the current on-demand song, and divide the on-demand song into a plurality of singing intervals according to the accompaniment audio and the original singing audio; and A control module connected to the acquisition module, the division module and the playback device, the control module is used to divide the N channels of singing sound information into first singing information and at least one second singing information in the singing interval, and to adjust the accompaniment audio and the original singing audio according to the first singing information and the second singing information and output them to the playback device; Among them, the singing effect of the first singing information is better than that of the second singing information.

[0006] Optionally, each of the singing intervals includes a collection interval and an adjustment interval that are performed in sequence; For each of the singing intervals, the control module is used to perform a score evaluation on each of the singing sound information based on multiple evaluation dimensions, and determine the first singing information and the second singing information according to the score evaluation result of each of the singing sound information; The control module is also used to adjust the accompaniment audio and the original singing audio according to the first singing information and the second singing information in the adjustment interval and output them to the playback device; Among them, the ratio of the duration of the collection interval to the duration of the singing interval does not exceed 20%.

[0007] Optionally, the control module is further used to adjust the accompaniment audio and the original singing audio according to the first singing information and each of the second singing information in the previous singing interval in the Mth acquisition interval, and output them to the playback device; Among them, M≥2.

[0008] Optionally, the multiple evaluation dimensions are singing beat, singing emotion and singing pitch; The control module is used to perform weighted calculation on the evaluation score of the singing beat, the evaluation score of the singing emotion and the evaluation score of the singing pitch to obtain the score evaluation result of the singing sound information.

[0009] Optionally, the control module is used to determine the singing sound information with the highest evaluation score among the N channels of singing sound information as the first singing information in the singing interval, and to determine the remaining singing sound information as the second singing information.

[0010] Optionally, the control module is further configured to, when the score evaluation results of multiple channels of the singing sound information are the highest and the same, determine the singing sound information with the highest sum of evaluation scores of preset evaluation dimensions as the first singing sound information, and determine the remaining singing sound information as the second singing sound information; Among them, the preset evaluation dimensions are the singing rhythm and the singing pitch.

[0011] Optionally, the control module is used to adjust the output weight of the original singing audio according to the singing beat score and singing pitch score of the first singing information; The control module is used to adjust the output proportion of the accompaniment audio according to the singing emotion scores of the first singing information and the second singing information.

[0012] Optionally, the control module is used to turn off or reduce the output magnification of the original singing audio when the sum of the singing beat score and the singing pitch score of the first singing information is within a first preset score range; When the sum of the singing beat score and the singing pitch score of the first singing information is within the second preset score range, the output magnification of the original singing audio is adjusted to the initial original singing output magnification or increased to the first target magnification; When the sum of the singing beat score and the singing pitch score of the first singing information is within a third preset score range, increasing the output magnification of the original singing audio to a second target magnification; Among them, the first target ratio is greater than the initial original singer output ratio and less than the second target ratio; the scores corresponding to the first preset score interval, the second preset score interval, and the third preset score interval decrease in sequence.

[0013] Optionally, the control module is used to calculate an average value of the singing emotion scores of the first singing information and the second singing information; When the average value calculation result is within a fourth preset score interval, increasing the output magnification of the accompaniment audio to a third target magnification; When the average value calculation result is within the fifth preset score interval, increasing the output magnification of the accompaniment audio to a fourth target magnification; When the average value calculation result is within the sixth preset score interval, adjusting the output magnification of the accompaniment audio to the initial accompaniment output magnification; Among them, the fourth target magnification is greater than the initial accompaniment output magnification and less than the third target magnification; the scores corresponding to the fourth preset score interval, the fifth preset score interval, and the sixth preset score interval decrease in sequence.

[0014] Optionally, the multifunctional integrated song requesting machine further includes: A filtering module is connected to the N microphones and the control module respectively; for the singing sound information output by any microphone, the filtering module is used to filter the singing sound information output by the accompaniment audio, the original singing audio and the other N-1 microphones and then output it to the control module; Among them, the filtering process is used to filter out the audio components corresponding to the accompaniment audio, the original singing audio, and the singing sound information output by the other N-1 microphones. The technical solution of the present invention divides the singing interval into multiple singing intervals and determines the most suitable first singing information and second singing information in real time in each singing interval, and adjusts the accompaniment audio and original singing audio in the singing interval according to the first singing information and the second singing information. This allows the playback device to play accompaniment audio and original singing audio that are more in line with the overall chorus effect of the current performance interval, thereby realizing the intelligent accompaniment function in the scene of multiple chorus, thereby solving the defect that the intelligent accompaniment function does not support the multi-person chorus scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0016] Figure 1 A schematic diagram of a module of an embodiment of a multifunctional integrated song requesting machine of the present invention; Figure 2 It is a module schematic diagram of another embodiment of the multifunctional integrated song requesting machine of the present invention.

[0017] Description of Figure Numbers: Label name Label name 10 Acquisition module 30 Control Module 20 Divide modules 40 Filter module The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] 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.

[0019] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention. In a multi-person chorus scenario, since multiple microphones have signal inputs at the same time, and in a multi-person chorus scenario, the singing levels of the singers generally vary greatly, according to the current adjustment logic of the intelligent accompaniment function, it is easy for the intelligent accompaniment function to have inconsistent adjustment results based on the outputs of different microphones. For example, based on the microphone signal input of a user with poor singing effect, the original singing audio should be increased, while based on the microphone signal input of a user with good singing effect, the adjustment result is to reduce the original singing audio. In order to avoid the above inconsistent adjustment results, the intelligent accompaniment function in the current prior art is only allowed to be turned on in the scenario of a user singing alone.

[0020] In order to solve the above problems, the present invention proposes a multifunctional integrated song requesting machine, the purpose of which is to realize an intelligent accompaniment function that can be used in a multi-person chorus scene.

[0021] Reference Figure 1 , the multifunctional integrated karaoke machine includes: The acquisition module is wirelessly connected to the N microphones to obtain N channels of singing sound information output by the N microphones, where N is greater than or equal to 2; A division module, used to obtain the accompaniment audio and the original singing audio of the current on-demand song, and divide the on-demand song into multiple singing intervals according to the accompaniment audio and the original singing audio; and A control module connected to the acquisition module, the division module and the playback device, the control module is used to divide the N-channel singing sound information into first singing information and at least one second singing information in the singing interval, and to adjust the accompaniment audio and the original singing audio according to the first singing information and each second singing information and output them to the playback device; Among them, the singing effect of the first singing information is better than that of the second singing information.

[0022] In this embodiment, the multifunctional integrated song requesting machine is used to connect with N microphones and playback devices. N is determined by the number of users currently singing together, and in this solution, N is at least 2. The acquisition module can be wirelessly connected to the N microphones through wireless communication methods such as Bluetooth communication and wifi communication, so that when different users sing, the microphones collect the singing voices of the users and output the singing voice information. The accompaniment audio will last throughout the entire singing process, while the original singing audio will only appear when singing is needed and will not last throughout the entire singing process.

[0023] The division module is configured to first distinguish each complete lyric according to the lyric information, then determine the singing time period in which each complete lyric appears in combination with the original singing audio, and finally take each determined singing time period as a singing interval. It can be understood that there is part of the singing audio in each singing interval.

[0024] After entering each singing interval, the control module can determine the best singing sound information among the N singing sound information as the first singing information, and the other singing sound information with less than the best singing effect as the second singing information, and in each singing interval, adjust the output accompaniment audio and original singing audio according to the currently determined first singing information and second singing information, and output the adjusted accompaniment audio and original singing audio to the playback device for playback, so that the playback device can play the accompaniment audio and original singing audio that are more in line with the overall chorus effect of the current performance interval. It can be understood that the sum of the number of first singing information and second singing information is N.

[0025] In this way, since each chorus singer has his or her own parts that he or she is good at singing and prefers to sing, and these parts of each chorus singer are often not the same, the technical solution of the present invention divides the singing intervals into multiple singing intervals and determines the most suitable first singing information and second singing information in real time in each singing interval, and adjusts the accompaniment audio and original singing audio in this singing interval according to the first singing information and the second singing information. This allows the playback device to play accompaniment audio and original singing audio that are more in line with the overall chorus effect of the current performance interval, thereby realizing the intelligent accompaniment function in the scenario of multiple chorus, thereby solving the defect that the intelligent accompaniment function does not support multi-person chorus scenarios. Reference Figure 1 ,Each singing interval includes a collection interval and an adjustment interval that are performed in sequence; For each singing interval, the control module is used to evaluate the scores of each singing sound information based on multiple evaluation dimensions, and determine the first singing information and the second singing information according to the score evaluation results of each singing sound information; The control module is also used to adjust the accompaniment audio and the original singing audio according to the first singing information and the second singing information in the adjustment interval and output them to the playback device.

[0026] In this embodiment, the singing interval includes a collection interval and an adjustment interval, and the duration of the collection interval is shorter than the duration of the adjustment interval. The evaluation dimension is a dimension related to the singing effect. The control module can score the singing sound information for each singing sound information according to multiple evaluation dimensions in the collection interval of each singing interval, and then determine the singing sound information with the best singing effect as the first singing information according to the final score evaluation results of the multiple evaluation dimensions, and use the other singing sound information as the second singing information.

[0027] In an optional embodiment, the ratio of the duration of the collection interval to the duration of the singing interval does not exceed 20%.

[0028] Such a setting can ensure that the duration of the acquisition interval will not be too long, and at the same time ensure that the adjustment interval can occupy a relatively sufficient proportion of the entire singing interval, which is conducive to ensuring the user's chorus experience.

[0029] During the test, it was found that since multiple singing intervals are prone to continuous occurrence, and the accompaniment audio and original audio are also in a playing state in the collection interval, if the initial output multiples of the accompaniment audio and the original audio are used for output in the collection interval, it is easy to cause the accompaniment audio and the original audio to have poor continuity in two consecutive singing intervals, which greatly affects the overall chorus effect of the user.

[0030] To address this problem, the control module is also used to adjust the accompaniment audio and the original singing audio according to the first singing information and the second singing information in the previous singing interval in the Mth acquisition interval and output them to the playback device; Among them, M≥2.

[0031] In actual tests, it was found that in the case of continuous singing intervals, although the singing effects of each user fluctuated in different singing intervals, the ranking of the overall singing effect did not change much, that is, the first singing information, the second singing information and the singing sound information were most likely the same. Based on this, the technical solution of the present invention allows the control module to inherit the first singing information and the second singing information in the previous singing interval in the new collection interval, and adjusts the accompaniment audio and the original singing audio based on this in the new collection interval, so as to ensure the continuity of the accompaniment audio and the original singing audio in the two singing intervals to the greatest extent possible, which is conducive to reducing the impact on the overall chorus effect of the user.

[0032] Optionally, the multiple evaluation dimensions are singing beat, singing emotion and singing pitch; In this embodiment, the control module can obtain the original audio information of the original singing audio in the current collection interval and the music score information of the current singing song in the current collection interval. The evaluation score of the singing beat dimension (i.e., the singing beat score) can be determined by extracting the offset of the singing sound information relative to the original audio information of the interval; the evaluation score of the singing pitch dimension (i.e., the singing pitch score) can be determined by comparing the frequency value of the singing sound information and the original audio information of the interval; the evaluation score of the singing emotion dimension (i.e., the singing emotion score) can be determined by comparing the sound intensity of the singing sound information and the music score information of the interval.

[0033] It should be noted that the purpose of scoring each singing sound information in the technical solution of the present invention is not to comment on the singing effect of the user, but to screen out the first singing information that is closer to the original singer, and in the multi-person chorus scene, the evaluation scores obtained by many evaluation criteria are seriously distorted, such as the singing volume, singing range, singing timbre, lyrics accuracy, etc., which are often used to comment on the performance of a single user. In view of this, the technical solution of the present invention selects the three evaluation dimensions of singing beat, singing emotion and singing pitch to ensure that the final score evaluation result matches the actual singing effect and level while being less affected by the chorus scene.

[0034] The control module is used to perform weighted calculation on the scores of the three evaluation dimensions of singing beat, singing emotion and singing pitch to obtain the final score evaluation result of the singing sound information. The weighted calculation is specifically: the product of the singing beat score and the first preset weighted value, the product of the singing pitch score and the second preset weighted value, and the product of the singing emotion score and the third preset weighted value are summed up, and the sum calculation result is used as the final score evaluation result of the singing sound information. Among them, the first preset weighted value, the second preset weighted value, and the third preset weighted value can be determined through a large number of preliminary experiments, and this embodiment does not limit this.

[0035] Optionally, the control module is used to determine the singing sound information with the highest evaluation score among the N singing sound information as the first singing information in the singing interval, and to determine the remaining singing sound information as the second singing information.

[0036] With such arrangement, when only one singing voice information has the highest final score evaluation result, the singing voice information with the best singing effect can be used as the first singing information.

[0037] Optionally, the control module is used to, when the score evaluation results of multiple channels of singing sound information are the highest and the same, determine the singing sound information with the highest sum of evaluation scores of preset evaluation dimensions as the first singing information, and determine the remaining singing sound information as the second singing information; the preset evaluation dimensions are singing beat and singing pitch.

[0038] In this embodiment, if the control module calculates that the final score evaluation results of at least two channels of singing sound information are the highest, it will return to calculate the sum of the scores of the singing beat and singing pitch of these channels of singing sound information, and take the singing sound information with the highest sum of the scores of the singing beat and singing pitch as the first singing information. In other words, when the final score evaluation results of at least two channels of singing sound information are the highest, the singing pitch score is removed, and the first singing information is determined by the two evaluation dimensions of singing beat and singing pitch that best reflect the actual singing level of the singer. It should be noted that in actual tests, it was found that there are great differences in the roles of the original audio and the accompaniment audio in the chorus scene and the solo scene. The biggest difference is that in the solo scene, since there is only one singer singing, if the singer's level is poor, it is often necessary to have relatively strong original audio and accompaniment audio to assist in presenting a better singing effect. The chorus scene is different. Since there are many singers in the chorus environment, it is easy for the first singing information with the best singing effect to exist in the chorus scene. No matter how big the gap is between the first singing information and the original audio, compared with the sound of the original audio, other singers with poor singing levels as chorus friends are often more inclined to sing along with the singer who is the source of the first singing information. In addition, in the chorus scene, the accompaniment audio does not serve the singer with the best singing effect alone, but needs to serve the overall chorus effect.

[0039] Based on the above situation, the technical solution of the present invention configures the control module to adjust the output weight of the original singing audio according to the singing beat score and singing pitch score of the first singing information; The control module is used to adjust the output weight of the accompaniment audio according to the singing emotion scores of the first singing information and the second singing information. In this way, the output ratio of the original singing audio and the accompaniment audio can be matched with the overall chorus effect in real time.

[0040] Furthermore, the control module is used to turn off or reduce the output magnification of the original singing audio when the sum of the singing beat score and the singing pitch score of the first singing information is within a first preset score range; When the sum of the singing beat score and the singing pitch score of the first singing information is within the second preset score range, the output magnification of the original singing audio is adjusted to the initial original singing output magnification or increased to the first target magnification; When the sum of the singing beat score and the singing pitch score of the first singing information is within the third preset score range, the output magnification of the original singing audio is increased to the second target magnification.

[0041] Among them, the first target ratio is greater than the initial original singer output ratio and less than the second target ratio; the scores corresponding to the first preset score interval, the second preset score interval, and the third preset score interval decrease in sequence.

[0042] In this embodiment, the first preset score interval, the second preset score interval, and the third preset score interval can be three continuously decreasing score intervals. The control module is used to calculate the sum of the singing beat score and the singing pitch score of the first singing information, and determine in which preset score interval the sum calculation result is.

[0043] If the judgment result is that the sum value calculation result is in the first preset score interval, it means that the level of the singer of the first singing information is extremely high, and the singing effect is close to the original singing. At this time, the output magnification of the original singing audio can be turned off or reduced to reduce the participation of the original singing audio to improve the participation of each singer, and because there are singers of the first singing information with a higher level, it does not affect the chorus effect. If the judgment result is that the sum value calculation result is in the second preset score interval, it means that the level of the singer of the first singing information is high and the singing effect is good. At this time, the output magnification of the original singing audio can be adjusted to the initial magnification, or increased to a lower first target magnification, so as to slightly increase the participation of the original singing audio to improve the participation and chorus effect of each singer. If the judgment result is that the sum value calculation result is in the third preset score interval, it means that the level of the singer of the first singing information is average or poor, and the singing effect is far from the original singing. At this time, the output magnification of the original singing audio can be increased to a higher second target magnification to increase the participation of the original singing audio to improve the participation of each singer.

[0044] In this embodiment, the first target multiplier and the second target multiplier can be a preset multiplier value, or a real-time multiplier value calculated based on relevant parameters (for example, the singing beat score and singing pitch score of the first singing information), which is not limited in this embodiment.

[0045] Further, the control module is used to calculate the average value of the singing emotion scores of the first singing information and the second singing information; When the average value calculation result is within the fourth preset score interval, increasing the output magnification of the accompaniment audio to a third target magnification; When the average value calculation result is within the fifth preset score interval, increasing the output magnification of the accompaniment audio to a fourth target magnification; When the average value calculation result is within the sixth preset score interval, adjusting the output magnification of the accompaniment audio to the initial accompaniment output magnification; Among them, the fourth target ratio is greater than the initial accompaniment output ratio and less than the third target ratio; the scores corresponding to the fourth preset score interval, the fifth preset score interval, and the sixth preset score interval decrease in sequence.

[0046] The control module can add the singing emotion score of the first singing information and the singing emotion scores of each second singing information and divide the sum by N to obtain the average value calculation result. It should be noted that actual tests have shown that the singing emotion score is proportional to the intensity of the singer's willingness to sing, that is, the higher the average value calculation result, the higher the willingness of each singer to actively sing. Based on this, in this embodiment, the fourth preset score interval, the fifth preset score interval, and the sixth preset score interval can also be three continuously decreasing score intervals. After calculating the average value of the singing emotion score, the control module can determine in which preset score interval the average value calculation result is.

[0047] If the judgment result is that the average value calculation result is in the fourth preset score interval, it means that the willingness of each singer to actively sing is extremely high, and a higher accompaniment audio is needed to create a singing atmosphere, so as to increase the participation of the accompaniment audio to cooperate with the overall chorus effect; at this time, the control module can increase the output magnification of the accompaniment audio to a higher third target magnification to meet the demand of the chorus for the accompaniment audio at this time. If the judgment result is that the average value calculation result is in the fifth preset score interval, it means that the willingness of each singer to actively sing is high, and the accompaniment audio can be slightly increased to assist in obtaining a better chorus effect; at this time, the control module can increase the output magnification of the accompaniment audio to a slightly higher fourth target magnification to meet the demand of the chorus for the accompaniment audio at this time. If the judgment result is that the average value calculation result is in the sixth preset score interval, it means that the willingness of each singer to actively sing is average or low, and there is no need to increase the accompaniment audio to assist in obtaining a better chorus effect; at this time, the control module adjusts the output magnification of the accompaniment audio to the initial accompaniment output magnification.

[0048] In this embodiment, the third target multiplier and the fourth target multiplier can be a preset multiplier value, or a real-time multiplier value calculated based on relevant parameters (for example, the singing beat score and singing pitch score of the first singing information), which is not limited in this embodiment.

[0049] In an optional embodiment, the control module may substitute the higher of the singing beat score and the singing pitch score of the first singing information, and the singing beat score and the singing pitch score of each second singing information into the corresponding preset amplification multiple calculation formula to calculate to obtain the first multiple, and the third target multiple may be obtained by multiplying the first multiple by the initial accompaniment output multiple. The control module may also substitute the lower of the singing beat score and the singing pitch score of the first singing information, and the singing beat score and the singing pitch score of each second singing information into the corresponding preset amplification multiple calculation formula to calculate to obtain the second multiple, and the fourth target multiple may be obtained by multiplying the second multiple by the initial accompaniment output multiple. Since the space where commercial karaoke machines are located is generally small, and the echo is more serious when multiple people sing together, it is easy for the microphone to collect the voices of other singers and other sounds, resulting in large errors in the score evaluation results of each singing sound information.

[0050] For the above problems, refer to Figure 2 The multifunctional integrated karaoke machine also includes: A filter module is connected to the N microphones and the control module respectively; for the singing sound information output by any microphone, the filter module is used to filter the singing sound information output by the accompaniment audio, the original audio and the other N-1 microphones and then output it to the control module; Among them, the filtering process is used to filter out the audio components corresponding to the accompaniment audio, the original singer audio, and the singing sound information output by the other N-1 microphones.

[0051] In this way, the singing sound information received by the control module can eliminate the audio components corresponding to the accompaniment audio, the original singing audio, and the singing sound information output by other N-1 microphones, thereby helping to improve the control module's evaluation accuracy of each channel of singing sound information. The above are only optional embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent structural changes made using the contents of the present invention's specification and drawings, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. A multifunctional integrated song requesting machine, characterized in that: Used to connect with N microphones and playback devices, the multifunctional integrated song requesting machine includes: The acquisition module is wirelessly connected to the N microphones to obtain N channels of singing sound information output by the N microphones, where N is greater than or equal to 2. a division module, used to obtain the accompaniment audio and the original singing audio of the current on-demand song, and divide the on-demand song into a plurality of singing intervals according to the accompaniment audio and the original singing audio; and A control module connected to the acquisition module, the division module and the playback device, the control module is used to divide the N channels of singing sound information into first singing information and at least one second singing information in the singing interval, and to adjust the accompaniment audio and the original singing audio according to the first singing information and the second singing information and output them to the playback device; Among them, the singing effect of the first singing information is better than that of the second singing information.

2. The multifunctional integrated song requesting machine as claimed in claim 1, characterized in that: Each of the singing intervals includes a collection interval and an adjustment interval that are performed in sequence; For each of the singing intervals, the control module is used to perform a score evaluation on each of the singing sound information based on multiple evaluation dimensions, and determine the first singing information and the second singing information according to the score evaluation result of each of the singing sound information; The control module is also used to adjust the accompaniment audio and the original singing audio according to the first singing information and the second singing information in the adjustment interval and output them to the playback device; Among them, the ratio of the duration of the collection interval to the duration of the singing interval does not exceed 20%.

3. The multifunctional integrated song requesting machine as claimed in claim 2, characterized in that: The control module is also used to adjust the accompaniment audio and the original singing audio according to the first singing information and each second singing information in the previous singing interval in the Mth collection interval, and output them to the playback device; Among them, M≥2.

4. The multifunctional integrated song requesting machine as claimed in claim 2, characterized in that: The multiple evaluation dimensions are singing rhythm, singing emotion and singing pitch; The control module is used to perform weighted calculation on the evaluation score of the singing beat, the evaluation score of the singing emotion and the evaluation score of the singing pitch to obtain the score evaluation result of the singing sound information.

5. The multifunctional integrated song requesting machine as claimed in claim 4, characterized in that: The control module is used to determine the singing sound information with the highest evaluation score among the N channels of singing sound information as the first singing information in the singing interval, and to determine the remaining singing sound information as the second singing information.

6. The multifunctional integrated song requesting machine as claimed in claim 5, characterized in that: The control module is also used to, when the score evaluation results of multiple channels of the singing sound information are the highest and the same, determine the singing sound information with the highest sum of the evaluation scores of the preset evaluation dimensions as the first singing sound information, and determine the remaining singing sound information as the second singing sound information; Among them, the preset evaluation dimensions are the singing beat and the singing pitch.

7. The multifunctional integrated song requesting machine as claimed in claim 4, characterized in that: The control module is used to adjust the output weight of the original singing audio according to the singing beat score and singing pitch score of the first singing information; The control module is used to adjust the output proportion of the accompaniment audio according to the singing emotion scores of the first singing information and the second singing information.

8. The multifunctional integrated song requesting machine as claimed in claim 7, characterized in that: The control module is used to turn off or reduce the output magnification of the original singing audio when the sum of the singing beat score and the singing pitch score of the first singing information is within a first preset score range; When the sum of the singing beat score and the singing pitch score of the first singing information is within the second preset score range, the output magnification of the original singing audio is adjusted to the initial original singing output magnification or increased to the first target magnification; When the sum of the singing beat score and the singing pitch score of the first singing information is within a third preset score range, increasing the output magnification of the original singing audio to a second target magnification; Among them, the first target ratio is greater than the initial original singer output ratio and less than the second target ratio; the scores corresponding to the first preset score interval, the second preset score interval, and the third preset score interval decrease in sequence.

9. The multifunctional integrated song requesting machine as claimed in claim 7, characterized in that: The control module is used to calculate the average value of the singing emotion scores of the first singing information and the second singing information; When the average value calculation result is within a fourth preset score interval, increasing the output magnification of the accompaniment audio to a third target magnification; When the average value calculation result is within the fifth preset score interval, increasing the output magnification of the accompaniment audio to a fourth target magnification; When the average value calculation result is within the sixth preset score interval, adjusting the output magnification of the accompaniment audio to the initial accompaniment output magnification; Among them, the fourth target magnification is greater than the initial accompaniment output magnification and less than the third target magnification; the scores corresponding to the fourth preset score interval, the fifth preset score interval, and the sixth preset score interval decrease in sequence.

10. The multifunctional integrated song requesting machine according to any one of claims 1 to 9, characterized in that: The multifunctional integrated song requesting machine also includes: A filtering module is connected to the N microphones and the control module respectively; for the singing sound information output by any microphone, the filtering module is used to filter the singing sound information output by the accompaniment audio, the original singing audio and the other N-1 microphones and then output it to the control module; Among them, the filtering process is used to filter out the audio components corresponding to the accompaniment audio, the original singing audio, and the singing sound information output by the other N-1 microphones.

Images