Singing score method and device based on continuity curve fitting and storage medium

Abstract

The present application relates to the field of audio technology, and specifically provides a singing scoring method and device based on continuity curve fitting and a storage medium. The singing scoring method based on continuity curve fitting comprises: obtaining a to-be-scored singing audio and a standard singing audio corresponding to the to-be-scored singing audio; using a continuity curve fitting method to fit the to-be-scored singing audio and the standard singing audio respectively to obtain an audio continuity curve of the to-be-scored singing audio and an audio continuity curve of the standard singing audio; obtaining a first singing score based on the audio continuity curve of the to-be-scored singing audio and the audio continuity curve of the standard singing audio; and scoring the to-be-scored singing audio based on at least the first singing score. The method can solve or at least partially solve the problem that existing singing software scoring processes cannot guarantee the fitting of details in the process of high and low pitch conversion, and improves the accuracy of scoring the to-be-scored singing audio.

Description

Technical Field

[0001] This invention relates to the field of audio technology, specifically providing a singing scoring method, apparatus, and storage medium based on continuous curve fitting. Background Technology

[0002] Currently, most singing software on the market directly compares the singing audio to be scored with a standard singing audio on the acquired sound signal. The directly acquired sound signal is usually a stepped curve. The limitation of this scoring method is that it cannot guarantee the detailed fitting of the high and low pitch transition process, nor can it refine the subtle changes in pitch, which are key indicators of singing skills, thus affecting the accuracy of the score.

[0003] Accordingly, there is a need in this field for a singing scoring method based on continuous curve fitting to solve the above problems. Summary of the Invention

[0004] To overcome the above-mentioned shortcomings, this invention is proposed to provide a method for solving, or at least partially solving, the problem that existing singing software scoring processes cannot guarantee detailed fitting during high and low pitch transitions.

[0005] In a first aspect, the present invention provides a singing scoring method based on continuous curve fitting, the method comprising the following steps:

[0006] Obtain the singing audio to be scored and the standard singing audio corresponding to the singing audio to be scored;

[0007] The continuous curve fitting method is used to fit the singing audio to be scored and the standard singing audio to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio, respectively.

[0008] A first singing score is obtained based on the audio continuity curve of the singing audio to be scored and the audio continuity curve based on the standard singing audio;

[0009] The singing audio to be scored is scored based at least on the first singing score.

[0010] In some embodiments, the method of fitting continuous curves to the singing audio to be scored and the standard singing audio to obtain the audio continuous curves of the singing audio to be scored and the standard singing audio includes:

[0011] The singing audio to be scored and the standard singing audio are each divided into multiple audio segments according to the time dimension;

[0012] Discrete pitch values ​​y are collected for each of the multiple audio segments of the singing audio to be scored and the standard singing audio, and the time corresponding to the discrete pitch value y is recorded as x, thus obtaining multiple (x,y) discrete points;

[0013] The multiple (x,y) discrete points of the singing audio to be scored and the standard singing audio are fitted using polynomial or Fourier series methods, respectively, to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio.

[0014] In some embodiments, obtaining a first singing score based on the audio continuity curve of the singing audio to be scored and the audio continuity curve based on the standard singing audio includes:

[0015] The audio continuous curve of the singing audio to be scored is compared with the audio continuous curve of the standard singing audio, and the first singing score is determined based on the curve comparison result.

[0016] In some embodiments, the step of comparing the audio continuity curve of the singing audio to be scored with the audio continuity curve of the standard singing audio, and determining the first singing score based on the curve comparison result, includes:

[0017] The overlap ratio of the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio is compared to obtain the overlap ratio value of the two curves.

[0018] The first singing score is determined based on the degree of overlap between the two curves.

[0019] In some embodiments, comparing the overlap between the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio to obtain the overlap value of the two curves includes obtaining the overlap value score based on the following formula:

[0020] score=100-area1 / area2*100,

[0021] Where area1 is the area enclosed between the continuous audio curve of the singing audio to be scored and the continuous audio curve of the standard singing audio, and area2 is defined by Max[|y max -y A |,|y A |] and the integral of the corresponding time, where y max To preset the maximum pitch value, y A The mid-pitch value of the continuous audio curve for standard singing audio.

[0022] In some embodiments, the method further includes scoring the singing audio to be scored in terms of singing skills, wherein scoring the singing audio in terms of singing skills includes:

[0023] At least detect whether the change in pitch value in the continuous audio curve of the singing audio to be scored within a first preset duration is greater than a first preset threshold.

[0024] The singing skills of the singing audio to be scored are evaluated based on the test results.

[0025] In some embodiments, the singing skill scoring of the singing audio to be scored based on the detection results includes:

[0026] If the change in pitch value in the continuous audio curve of the singing audio to be scored within a first preset time period is greater than a first preset threshold, then the singing audio to be scored is determined to obtain a singing skill score, and the singing skill score of the singing audio to be scored is determined based on the threshold range in which the change in pitch value in the continuous audio curve of the singing audio to be scored within the first preset time period falls.

[0027] Otherwise, the singing audio to be scored is deemed not to have received a singing skill score.

[0028] In some embodiments, scoring the singing audio to be scored, at least based on the first singing score, includes:

[0029] The singing audio to be scored is scored based on the first singing score;

[0030] Alternatively, the singing audio to be scored can be scored based on the first singing score and the singing skill score.

[0031] In a second aspect, the present invention provides a singing scoring device based on continuous curve fitting, comprising a processor and a memory, the memory being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to perform the singing scoring method based on continuous curve fitting as described above.

[0032] In a third aspect, the present invention provides a computer-readable storage medium storing a plurality of program codes adapted to be loaded and run by a processor to perform the singing scoring method based on continuous curve fitting as described in any of the preceding claims.

[0033] By employing the above technical solution, the present invention provides a singing scoring method based on continuous curve fitting. This method obtains a singing audio to be scored and a corresponding standard singing audio; it uses continuous curve fitting to fit the singing audio to be scored and the standard singing audio to obtain audio continuous curves for the singing audio to be scored and the standard singing audio, respectively; it obtains a first singing score based on the audio continuous curves of the singing audio to be scored and the standard singing audio; and it scores the singing audio to be scored based at least on the first singing score. This method obtains the audio continuous curves of the standard singing audio and the singing audio to be scored through continuous curve fitting, and compares these two curves to obtain a singing score. This effectively solves the problem that singing software scoring cannot guarantee detailed fitting during high and low note transitions, thus improving the accuracy of singing software scoring. Attached Figure Description

[0034] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Furthermore, similar numbers in the drawings are used to denote similar components, wherein:

[0035] Figure 1 This is a schematic diagram of the main steps of a singing scoring method based on continuous curve fitting according to an embodiment of the present invention;

[0036] Figure 2 This is a schematic diagram illustrating the changes in an audio curve before and after fitting using a continuous fitting method, according to an embodiment of the present invention.

[0037] Figure 3 This is a schematic diagram of the audio continuity curve of a fitted standard singing audio and the audio continuity curve of a fitted singing audio to be scored, provided by an embodiment of the present invention.

[0038] Figure 4 This is a schematic diagram of the main structure of a singing scoring device based on continuous curve fitting according to an embodiment of the present invention. Detailed Implementation

[0039] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0040] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0041] Currently, when scoring singing, the method generally involves directly comparing the singing audio to be scored with the standard singing audio on the acquired step-shaped curve sound signal. This method cannot guarantee the detailed fitting of the high and low pitch transitions, nor can it refine the subtle changes in pitch, thus affecting the accuracy of the scoring.

[0042] In view of this, the present invention provides a singing scoring method based on continuous curve fitting. This method obtains the singing audio to be scored and the corresponding standard singing audio; it uses continuous curve fitting to fit the singing audio to be scored and the standard singing audio respectively to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio; it obtains a first singing score based on the audio continuous curve of the singing audio to be scored and the audio continuous curve based on the standard singing audio; and it scores the singing audio to be scored based at least on the first singing score. This method can effectively solve the problem that existing singing software cannot guarantee detailed fitting during high and low note transitions, thus improving the accuracy of scoring the singing audio to be scored.

[0043] See the appendix below. Figure 1 An embodiment of the present invention will be described below. Figure 1 This is a schematic flowchart of the main steps of a singing scoring method based on continuous curve fitting according to an embodiment of the present invention, mainly including the following steps S101-S104:

[0044] Step S101: Obtain the singing audio to be scored and the standard singing audio corresponding to the singing audio to be scored;

[0045] Step S102: Use the continuous curve fitting method to fit the singing audio to be scored and the standard singing audio to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio respectively.

[0046] Step S103: Obtain the first singing score based on the audio continuous curve of the singing audio to be scored and the audio continuous curve based on the standard singing audio;

[0047] Step S104: Based at least on the first singing score, score the singing audio to be scored.

[0048] In one embodiment, step S102 involves using a continuous curve fitting method to fit the singing audio to be scored and the standard singing audio to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio, respectively.

[0049] The singing audio to be scored and the standard singing audio are each divided into multiple audio segments according to the time dimension;

[0050] Discrete pitch values ​​y are collected from multiple audio segments of the singing audio to be scored and the standard singing audio, and the time corresponding to the discrete pitch value y is recorded as x, thus obtaining multiple (x,y) discrete points;

[0051] Multiple (x,y) discrete points of the singing audio to be scored and the standard singing audio are fitted using polynomial or Fourier series methods, respectively, to obtain the audio continuity curve of the singing audio to be scored and the audio continuity curve of the standard singing audio.

[0052] In some application embodiments, the number of multiple audio segments in the above embodiments is selected to be greater than the preset number of audio segments. Under the premise that the number of audio segments is sufficient, when multiple (x,y) discrete points are extracted based on the multiple audio segments, and at least one discrete point is extracted from each audio segment, the total number of multiple (x,y) discrete points obtained can be greater than the preset minimum total number of discrete points. This ensures that a sufficient number of discrete points can be obtained during curve fitting, so that the fitted continuous curve can take into account subtle changes such as detail fitting during the high and low frequency transformation process.

[0053] Furthermore, when obtaining multiple (x,y) discrete points based on multiple audio segments, it is also possible to detect whether the pitch value change of the audio segment within a second preset duration is greater than a preset change threshold. If the pitch value change of the audio segment within the second preset duration is greater than the preset change threshold, it indicates that there is a situation where the amplitude of the high and low pitch transitions in the audio segment exceeds a preset amplitude. In this case, when obtaining (x,y) discrete points for the audio segment, the number of discrete points obtained on the audio segment is greater than the preset number of discrete points for the audio segment, so as to ensure that the number of discrete points obtained on the audio segment is sufficient, thereby ensuring that the details of the high and low pitch transitions are not lost during curve fitting.

[0054] In some application embodiments, the above-mentioned method of fitting N discrete points (x,y) using a polynomial to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio can be based on the following polynomial formula:

[0055]

[0056] Where y corresponds to the pitch value in the fitted audio continuous curve, x is the time corresponding to the pitch value y, and w0~w n These are the coefficients corresponding to different orders x.

[0057] In some application embodiments, when fitting the acquired audio signal, it can be represented as a superposition of multiple cosine or sine functions, that is, the Fourier series method described above can be used for fitting. The above-mentioned method of fitting N discrete points (x,y) using Fourier series to obtain the continuous audio curves of the singing audio to be scored and the standard singing audio can be based on the following Fourier series formula:

[0058]

[0059] Where y corresponds to the pitch value in the fitted audio continuous curve, and T represents the signal period. Where is the fundamental angular frequency, a0 is the DC component, and a n b is the amplitude of the cosine component. n y is the amplitude of the sine component, and x is the time corresponding to the pitch value y.

[0060] Appendix Figure 2 This is a schematic diagram illustrating the changes in the audio curve before and after fitting using a continuous fitting method, according to an embodiment of the present invention. (See also...) Figure 2It can be seen that the method of using continuous curve fitting to fit the singing audio to be scored and the standard singing audio to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio can effectively ensure the problem of detail fitting during the high and low pitch transformation and retain the subtle changes in pitch in the audio. On this basis, scoring the singing audio to be scored and the standard singing audio can effectively improve the accuracy of the singing software scoring.

[0061] In one embodiment, obtaining the first singing score in step S103 based on the audio continuity curve of the singing audio to be scored and the audio continuity curve based on the standard singing audio includes:

[0062] The audio continuous curve of the singing audio to be scored is compared with the audio continuous curve of the standard singing audio, and the first singing score is determined based on the curve comparison results.

[0063] In some embodiments, the above-described continuous curve fitting method is used to perform curve fitting on the acquired singing audio to be scored and the corresponding standard singing audio to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio. After obtaining the audio continuous curve of the standard singing audio, it is also possible to optionally store the obtained audio continuous curve of the standard singing audio in an audio fingerprint database.

[0064] In some embodiments, when obtaining the fitted audio continuity curve of the standard singing audio corresponding to the singing audio to be scored, the audio continuity curve of the standard singing audio corresponding to the singing audio to be scored can be directly obtained from the audio fingerprint database. By directly obtaining the required audio continuity curve of the standard singing audio from the audio fingerprint database, computation time can be saved during the actual scoring of the singing audio to be scored, thereby improving the efficiency of scoring the singing audio to be scored.

[0065] Specifically, the aforementioned audio fingerprint database is used to store the fingerprint features of standard singing audio. The fingerprint features may include, but are not limited to, the frequency parameters and time parameters corresponding to the spectrum of the standard singing audio data, and the audio continuity curve of the standard singing audio obtained by the aforementioned continuity curve fitting method.

[0066] In some implementations, the audio continuity curve of the singing audio to be scored is compared with the audio continuity curve of the standard singing audio, and the first singing score is determined based on the curve comparison result, including:

[0067] The overlap between the continuous audio curve of the singing audio to be scored and the continuous audio curve of the standard singing audio is compared to obtain the overlap value of the two curves.

[0068] The first singing score is determined based on the degree of overlap between the two curves.

[0069] In some embodiments, the overlap between the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio is compared to obtain the overlap value of the two curves, including obtaining the overlap value score based on the following formula:

[0070] score=100-area1 / area2*100,

[0071] Where area1 is the area enclosed between the continuous audio curve of the singing audio to be scored and the continuous audio curve of the standard singing audio, and area2 is defined by Max[|y max -y A |,|y A |] and the integral of the corresponding time, where y max To preset the maximum pitch value, y A The mid-pitch value of the continuous audio curve for standard singing audio.

[0072] After calculating the overlap score between the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio according to the above formula, the overlap score is used as the first singing score.

[0073] See the appendix below. Figure 3 To further explain, Figure 3 This is a schematic diagram of a fitted standard singing audio continuous curve and a fitted singing audio to be scored, provided by an embodiment of the present invention. Curve A is the fitted standard singing audio continuous curve, and curve B is the fitted singing audio to be scored continuous curve. The area enclosed between curves A and B is area1 = a1 + a2 + a3. Max[|y] is taken as the pitch value and the preset maximum pitch value in curve A. max -y A |,|y A |], where y max To preset the maximum pitch value, y A Let the ordinate of curve A be the pitch value, i.e., the pitch value in curve A. Then, set Max[|y]... max -y A |,|y A |] value and the corresponding time t value are integrally obtained to obtain area2. Then, based on the previously calculated area1 and area2 values, the overlap value of curve A and curve B can be obtained according to the formula score=100-area1 / area2*100. This overlap value score is then used as the first singing score.

[0074] In some implementations, a singing assessment method based on continuous curve fitting further includes scoring the singing technique of the audio to be scored, wherein scoring the singing technique of the audio to be scored includes:

[0075] At least detect whether the change in pitch value in the continuous audio curve of the singing audio to be scored within a first preset duration is greater than a first preset threshold.

[0076] Based on the test results, the singing skills of the singing audio to be scored are evaluated.

[0077] In some embodiments, the above-mentioned scoring of singing skills based on the detection results of the singing audio to be scored includes:

[0078] If the detection result shows that the change in pitch value in the continuous audio curve of the singing audio to be scored is greater than the first preset threshold within the first preset time period, then the singing audio to be scored is determined to obtain a singing skill score, and the singing skill score of the singing audio to be scored is determined based on the threshold range in which the change in pitch value in the continuous audio curve of the singing audio to be scored within the first preset time period falls.

[0079] Otherwise, the singing audio to be scored will be deemed not to have received a singing skill score.

[0080] Specifically, the pitch values ​​in the continuous audio curve of an audio segment are detected. If the change in pitch values ​​within a first preset duration exceeds a first preset threshold, indicating drastic pitch changes in a short period, it can be assumed that the audio segment contains singing techniques such as vibrato or trills. The presence of singing techniques in the audio segment is determined by detecting the pitch value changes in the continuous audio curve within the first preset duration. If singing techniques are detected, the audio segment receives a singing technique score.

[0081] In some application embodiments, the singing skill score of the singing audio to be scored is determined based on the threshold range in which the pitch value in the continuous audio curve of the singing audio to be scored falls within a first preset duration.

[0082] Cy1 is the change in pitch value in the continuous audio curve of the singing audio to be scored within the first preset duration;

[0083] If the first preset threshold ≤ Cy1 ≤ the second preset threshold, then the singing audio to be scored will receive the first preset skill score.

[0084] If Cy1 > the second preset threshold, the singing audio to be scored will receive the second preset skill score.

[0085] It should be noted that the above rules for determining the singing technique score of the singing audio to be scored are only illustrative. The rules for determining the singing technique score of the singing audio to be scored can be adjusted and set according to actual needs in practical applications.

[0086] In other embodiments, in addition to detecting whether the change in pitch value in the continuous audio curve of the singing audio to be scored is greater than a first preset threshold within a first preset duration, it is also detected whether the change in pitch value in the continuous audio curve of the standard singing audio is greater than a first preset threshold within a first preset duration. Based on the threshold range in which the changes in pitch value in the continuous audio curve of the standard singing audio and the continuous audio curve of the singing audio to be scored fall within the first preset duration, the singing skill score of the singing audio to be scored is determined.

[0087] Specifically, the presence of singing techniques in the standard singing audio is determined by detecting the pitch changes of the audio continuity curve within a first preset duration. Similarly, the presence of singing techniques in the singing audio to be scored is determined by detecting the pitch changes of the audio continuity curve within the first preset duration. If singing techniques are detected in both the standard and the singing audio to be scored, the singing audio to be scored receives a singing technique score.

[0088] Specifically, based on the threshold range where the pitch values ​​in the continuous audio curve of the standard singing audio and the pitch values ​​in the continuous audio curve of the singing audio to be scored fall within a first preset duration, the singing technique score of the singing audio to be scored is determined, including:

[0089] Cy0 is the change in pitch value in the continuous audio curve of the standard singing audio within the first preset duration, and Cy1 is the change in pitch value in the continuous audio curve of the singing audio to be scored within the first preset duration.

[0090] If the first preset threshold ≤ Cy0 ≤ the second preset threshold, and the first preset threshold ≤ Cy1 ≤ the second preset threshold, then the singing audio to be scored will receive the first preset skill score.

[0091] If Cy0 > the second preset threshold and Cy1 > the second preset threshold, then the singing audio to be scored will receive the second preset skill score.

[0092] If Cy0 ≥ the first preset threshold and Cy1 ≥ the first preset threshold, but the values ​​of Cy0 and Cy1 do not meet the scoring conditions for the singing audio to be scored to obtain the first preset skill score and the second preset skill score, then the singing audio to be scored will obtain the third preset skill score.

[0093] It should be noted that the above rules for determining the singing technique score of the singing audio to be scored are only illustrative. The rules for determining the singing technique score of the singing audio to be scored can be adjusted and set according to actual needs in practical applications.

[0094] In other application embodiments, if Cy0 ≥ a first preset threshold, the standard singing audio can be characterized, indicating the presence of singing techniques in the standard singing audio. The Cy0 value and the first preset duration are then stored as singing technique features of the standard singing audio in the audio fingerprint database. When actually scoring the singing audio to be scored, the singing technique features of the standard singing audio corresponding to the audio to be scored can be directly obtained from the audio fingerprint database. The singing technique features in the audio to be scored and the standard audio are compared to determine whether the audio to be scored receives a singing technique score. This method enriches the fingerprint feature information of standard singing audio in the audio fingerprint database and improves the efficiency of scoring the audio to be scored.

[0095] In one implementation, in step S104, the scoring of the singing audio to be scored, based at least on the first singing score, includes:

[0096] Based on the first singing score, the audio of the candidate's singing will be scored.

[0097] Alternatively, the singing audio of the candidate can be scored based on the first singing score and the singing technique score.

[0098] In some application embodiments, scoring the audio recording to be scored based on the first singing score can be achieved by directly applying the obtained first singing score. Scoring the audio recording based on both the first singing score and the singing technique score can be achieved by directly summing the first singing score and the singing technique score to determine the final score. Alternatively, the final score can be determined based on a weighted calculation of the first singing score and the singing technique score, where each weight is greater than or equal to zero, and the sum of their respective weights is equal to 1. Specifically, the method used to determine the final score based on the first singing score and the singing technique score can be adjusted and selected according to actual needs in practical applications, as long as it achieves a reasonable and effective score for the audio recording to be scored; further details are omitted here.

[0099] Using the above method, one can choose to directly use the first singing score to evaluate the audio recording, or choose to combine the first singing score and the singing technique score. This allows for a more selective and comprehensive evaluation of the audio recordings, improving the rationality and effectiveness of the singing evaluation method.

[0100] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0101] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0102] Furthermore, the present invention also provides a singing scoring device based on continuous curve fitting. (See appendix) Figure 4 , Figure 4 This is a schematic block diagram of the main structure of a singing scoring device based on continuous curve fitting according to an embodiment of the present invention. In one embodiment of the singing scoring device based on continuous curve fitting according to the present invention, the singing scoring device 400 includes a processor 401 and a memory 402. The memory 402 can be configured to store a program for executing the singing scoring method based on continuous curve fitting described in the above-described method embodiment. The processor 401 can be configured to execute the program in the memory 402, which includes, but is not limited to, the program for executing the singing scoring method based on continuous curve fitting described in the above-described method embodiment. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. This device can be a control device device comprising various electronic devices.

[0103] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program that executes the singing scoring method based on continuous curve fitting of the above-described method embodiments. This program can be loaded and run by a processor to implement the singing scoring method based on continuous curve fitting described above. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0104] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A singing scoring method based on continuous curve fitting, characterized in that, The method includes the following steps: Obtain the singing audio to be scored and the standard singing audio corresponding to the singing audio to be scored; The continuous curve fitting method is used to fit the singing audio to be scored and the standard singing audio to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio, respectively. A first singing score is obtained based on the audio continuity curve of the singing audio to be scored and the audio continuity curve based on the standard singing audio; The singing audio to be scored is scored at least based on the first singing score; The process of obtaining the first singing score based on the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio includes: The overlap ratio of the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio is compared to obtain the overlap ratio value of the two curves. The first singing score is determined based on the overlap value of the two curves. The overlap ratio value is obtained based on the following formula: score = 100 - area1 / area2 * 100 Where, score is the overlap value, area1 is the area enclosed between the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio, and area2 is defined by Max[|y max -y A |,|y A |] and the integral of the corresponding time, where y max To preset the maximum pitch value, y A The mid-pitch value of the continuous audio curve for standard singing audio.

2. The singing scoring method based on continuous curve fitting according to claim 1, characterized in that, The method of using continuous curve fitting to fit the singing audio to be scored and the standard singing audio to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio respectively includes: The singing audio to be scored and the standard singing audio are each divided into multiple audio segments according to the time dimension; Discrete pitch values ​​y are collected for each of the multiple audio segments of the singing audio to be scored and the standard singing audio, and the time corresponding to the discrete pitch value y is recorded as x, thus obtaining multiple (x,y) discrete points; The multiple (x,y) discrete points of the singing audio to be scored and the standard singing audio are fitted using polynomial or Fourier series methods, respectively, to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio.

3. The singing scoring method based on continuous curve fitting according to claim 1, characterized in that, The method further includes scoring the singing technique of the singing audio to be scored, wherein scoring the singing technique of the singing audio to be scored includes: At least detect whether the change in pitch value in the continuous audio curve of the singing audio to be scored within a first preset duration is greater than a first preset threshold. The singing skills of the singing audio to be scored are evaluated based on the test results.

4. The singing scoring method based on continuous curve fitting according to claim 3, characterized in that, The process of scoring the singing technique of the singing audio to be scored based on the detection results includes: If the change in pitch value in the continuous audio curve of the singing audio to be scored within a first preset time period is greater than a first preset threshold, then the singing audio to be scored is determined to obtain a singing skill score, and the singing skill score of the singing audio to be scored is determined based on the threshold range in which the change in pitch value in the continuous audio curve of the singing audio to be scored within the first preset time period falls. Otherwise, the singing audio to be scored is deemed not to have received a singing skill score.

5. A singing scoring method based on continuous curve fitting according to claim 3 or 4, characterized in that, The scoring of the singing audio to be scored, based at least on the first singing score, includes: The singing audio to be scored is scored based on the first singing score; Alternatively, the singing audio to be scored can be scored based on the first singing score and the singing skill score.

6. A singing scoring device based on continuous curve fitting, characterized in that, It includes a processor and a memory, the memory being adapted to store multiple lines of program code, the program code being adapted to be loaded and run by the processor to perform the singing scoring method based on continuous curve fitting as described in any one of claims 1 to 5.

7. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the singing scoring method based on continuous curve fitting as described in any one of claims 1 to 5.

Images