CN117636904A - Singing scoring method, device and storage medium based on continuous curve fitting - Google Patents
Singing scoring method, device and storage medium based on continuous curve fitting Download PDFInfo
- Publication number
- CN117636904A CN117636904A CN202210988036.XA CN202210988036A CN117636904A CN 117636904 A CN117636904 A CN 117636904A CN 202210988036 A CN202210988036 A CN 202210988036A CN 117636904 A CN117636904 A CN 117636904A
- Authority
- CN
- China
- Prior art keywords
- audio
- singing
- scored
- continuous curve
- standard
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013077 scoring method Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 47
- 230000008859 change Effects 0.000 claims description 26
- 238000001514 detection method Methods 0.000 claims description 12
- 239000012634 fragment Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 12
- 230000009466 transformation Effects 0.000 abstract description 2
- 238000006243 chemical reaction Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Reverberation, Karaoke And Other Acoustics (AREA)
Abstract
The invention relates to the technical field of audio, and particularly provides a singing scoring method, device and storage medium based on continuous curve fitting. The singing scoring method based on continuous curve fitting comprises the following steps: acquiring singing audio to be scored and standard singing audio corresponding to the singing audio to be scored; fitting the singing audio to be scored and the standard singing audio respectively by adopting a continuous curve fitting method to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio; obtaining a 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; the singing audio to be scored is scored based at least on the first singing score. The method can solve or at least partially solve the problem that detail fitting in the treble-bass transformation process can not be guaranteed in the scoring process of the existing singing software, and improves the accuracy of scoring singing audio to be scored.
Description
Technical Field
The invention relates to the technical field of audio, and particularly provides a singing scoring method, device and storage medium based on continuous curve fitting.
Background
The singing software on the market generally carries out comparison scoring on singing voice frequency to be scored and standard singing voice frequency directly on the acquired voice signals, the directly acquired voice signals are generally ladder-shaped curves, and the scoring method has the limitation that detail fitting in the high-low sound conversion process cannot be ensured, tiny changes of tones cannot be refined, and the detail fitting is a key index of singing skills, so that the scoring accuracy is influenced.
Accordingly, there is a need in the art for a singing scoring method based on continuous curve fitting to solve the above-mentioned problems.
Disclosure of Invention
In order to overcome the defects, the invention provides a method for solving or at least partially solving the problems that the detail fitting in the treble-bass conversion process can not be ensured in the scoring process of the existing singing software.
In a first aspect, the present invention provides a singing scoring method based on continuous curve fitting, the method comprising the steps of:
acquiring singing audio to be scored and standard singing audio corresponding to the singing audio to be scored;
fitting the singing audio to be scored and the standard singing audio by adopting a continuous curve fitting method to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio;
obtaining a 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;
and scoring the singing audio to be scored based on at least the first singing score.
In some embodiments, the fitting the singing audio to be scored and the standard singing audio by using the continuous curve fitting method to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio includes:
dividing the singing audio to be scored and the standard singing audio into a plurality of audio fragments according to the time dimension;
collecting discrete pitch values y for the singing audio to be scored and the plurality of audio fragments of the standard singing audio respectively, and recording the time corresponding to the discrete pitch values y as x to obtain a plurality of (x, y) discrete points;
fitting the singing audio to be scored and the (x, y) discrete points of the standard singing audio respectively by adopting a polynomial or Fourier series mode, and obtaining an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio respectively.
In some embodiments, the obtaining the first singing score based on the audio continuous curve of the singing audio to be scored and based on the audio continuous curve of the standard singing audio comprises:
and comparing the audio continuous curve of the singing audio to be scored with the audio continuous curve of the standard singing audio, and determining the first singing score based on the curve comparison result.
In some embodiments, the comparing the audio continuous curve of the singing audio to be scored with the audio continuous curve of the standard singing audio, and determining the first singing score based on the comparison result of the curves includes:
comparing the continuous audio curves of the singing audio to be scored with the continuous audio curves of the standard singing audio in a curve overlap ratio mode to obtain an overlap ratio value of the two curves;
the first singing score is determined based on the coincidence degree value of the two curves.
In some embodiments, the comparing the continuous audio curves of the singing audio to be scored with the continuous audio curves of the standard singing audio to obtain the overlap ratio value score of the two curves includes obtaining the overlap ratio value score based on the following formula:
score＝100-area1/area2*100，
wherein area1 is the area of the package 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 represented by Max [ |y max -y A |,|y A |]And corresponding integral of time, where y max For a preset maximum pitch value, y A Pitch values in an audio continuum for standard singing audio.
In some embodiments, the method further comprises scoring the singing skill of the singing audio to be scored, wherein scoring the singing skill of the singing audio to be scored comprises:
detecting whether the change of a pitch value in an audio continuous curve of the singing audio to be scored within a first preset duration is larger than a first preset threshold or not;
and scoring the singing skills of the singing audio to be scored based on the detection result.
In some embodiments, the scoring the singing skill of the singing audio to be scored based on the detection result includes:
if the change of the pitch value in the audio continuous curve of the singing audio to be scored within a first preset time period is larger than a first preset threshold value, judging that the singing audio to be scored obtains singing skill score, and determining the singing skill score of the singing audio to be scored based on a threshold value interval within which the change of the pitch value in the audio continuous curve of the singing audio to be scored within the first preset time period in the detection result is located;
otherwise, judging that the singing skill score is not obtained by the singing audio to be scored.
In some embodiments, the scoring the singing audio to be scored based at least on the first singing score includes:
scoring the singing audio to be scored based on the first singing score;
or scoring the singing audio to be scored based on the first singing score and the singing skill score.
In a second aspect, the present invention provides a singing scoring apparatus based on continuous curve fitting, comprising a processor and a memory adapted to store a plurality of program code 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 the preceding claims.
In a third aspect, the present invention provides a computer readable storage medium having stored therein a plurality of program codes adapted to be loaded and executed by a processor to perform the singing scoring method based on continuous curve fitting of any one of the above.
Under the condition of adopting the technical scheme, the invention can provide the singing scoring method based on the continuous curve fitting, which comprises the steps of obtaining singing audio to be scored and standard singing audio corresponding to the singing audio to be scored; fitting the singing audio to be scored and the standard singing audio by adopting a continuous curve fitting method to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio; obtaining a 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; and scoring the singing audio to be scored based on at least the first singing score. According to the method, the continuous curve fitting method is used for obtaining the continuous curve of the audio of the standard singing audio and the continuous curve of the audio of the singing audio to be scored, and the continuous curve of the audio of the standard singing audio and the continuous curve of the audio of the singing audio to be scored are compared to obtain the singing score, so that the problem that detail fitting in the high-low tone conversion process can not be guaranteed in the singing software scoring process can be effectively solved, and the accuracy of singing software scoring is improved.
Drawings
The present disclosure will become more readily understood with reference to the accompanying drawings. As will be readily appreciated by those skilled in the art: the drawings are for illustrative purposes only and are not intended to limit the scope of the present invention. Moreover, like numerals in the figures are used to designate like parts, wherein:
FIG. 1 is a schematic flow chart of main steps of a singing scoring method based on continuous curve fitting according to an embodiment of the present invention;
FIG. 2 is a schematic illustration of audio curve changes before and after fitting using a continuous fitting method according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an audio continuous curve of a standard singing audio after fitting and an audio continuous curve of a singing audio to be scored after fitting according to an embodiment of the present invention;
fig. 4 is a schematic block diagram of a singing scoring device based on continuous curve fitting according to an embodiment of the present invention.
Detailed Description
Some embodiments of the invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
In the description of the present invention, a "module," "processor" may include hardware, software, or a combination of both. A module may comprise hardware circuitry, various suitable sensors, communication ports, memory, or software components, such as program code, or a combination of software and hardware. The processor may be a central processor, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and/or signal processing functions. The processor may be implemented in software, hardware, or a combination of both. Non-transitory computer readable storage media include any suitable medium that can store program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, and the like. The term "a and/or B" means all possible combinations of a and B, such as a alone, B alone or a and B. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and/or B" and may include A alone, B alone or A and B. The singular forms "a", "an" and "the" include plural referents.
At present, when singing scoring is carried out, the singing audio to be scored and the standard singing audio are generally and directly compared and scored on the collected voice signals of the ladder-type curves, and the method cannot ensure detail fitting in the high-low sound conversion process and cannot refine tiny changes of the tone, so that the accuracy of scoring is affected.
In view of the above, the present invention provides a singing scoring method based on continuous curve fitting, which obtains singing audio to be scored and standard singing audio corresponding to the singing audio to be scored; fitting the singing audio to be scored and the standard singing audio respectively by adopting a continuous curve fitting method to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio; obtaining a 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; the singing audio to be scored is scored based at least on the first singing score. The method can effectively solve the problem that detail fitting in the treble-bass conversion process can not be guaranteed in the scoring process of the existing singing software, and improves the accuracy of scoring singing audio to be scored.
Referring to fig. 1 for describing an embodiment of the present invention, fig. 1 is a schematic flow chart of main steps of a singing scoring method based on continuous curve fitting according to an embodiment of the present invention, and mainly includes the following steps S101 to S104:
step S101: acquiring singing audio to be scored and standard singing audio corresponding to the singing audio to be scored;
step S102: fitting the singing audio to be scored and the standard singing audio respectively by adopting a continuous curve fitting method to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio;
step S103: obtaining a 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;
step S104: the singing audio to be scored is scored based at least on the first singing score.
In one embodiment, the fitting 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 by adopting the continuous curve fitting method in step S102 includes:
dividing singing audio to be scored and standard singing audio into a plurality of audio fragments according to the time dimension;
collecting discrete pitch values y of a plurality of audio fragments of singing audio to be scored and standard singing audio respectively, recording time corresponding to the discrete pitch values y as x, and obtaining a plurality of (x, y) discrete points;
fitting a plurality of (x, y) discrete points of the singing audio to be scored and the standard singing audio respectively by adopting a polynomial or Fourier series mode to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio respectively.
In some application examples, the number of the plurality of audio clips in the above embodiment is selected to be greater than the preset number of audio clips, so that, on the premise of ensuring that the number of audio clips is sufficiently large, when the plurality of (x, y) discrete points are extracted based on the plurality of audio clips, and at least one discrete point is extracted in each audio clip, the total number of the obtained plurality of (x, y) discrete points can be greater than the preset minimum discrete point total number, thereby ensuring that a sufficient number of discrete points can be obtained during curve fitting, so that a continuous curve obtained by fitting considers fine variations such as detail fitting in a high-low tone transformation process.
Further, when the plurality of (x, y) discrete points are obtained based on the plurality of audio segments, whether the pitch value change of the audio segments in the second preset time period is larger than the preset change threshold value or not can be detected respectively, if the pitch value change of the audio segments in the second preset time period is larger than the preset change threshold value, the condition that the high-low sound conversion amplitude exceeds the preset amplitude is indicated in the audio segments, and when the (x, y) discrete points are obtained for the audio segments, the number of the discrete points obtained for the audio segments is selected to be larger than the number of the discrete points of the preset audio segments, so that the number of the discrete points obtained for the audio segments is enough, and the fact that the details of the high-low sound conversion are not lost during curve fitting is guaranteed.
In some application embodiments, the fitting of the N (x, y) discrete points by 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 respectively can be performed based on the following polynomial formula:
wherein y corresponds to the pitch value in the fitted audio continuous curve, x is the time corresponding to the pitch value y, w 0 ～w n Is a coefficient corresponding to a different order x.
In some application embodiments, when fitting the acquired audio signal, the fitting may be represented as a superposition of a plurality of cosine or sine functions, i.e. the fitting may be performed in the manner of fourier series. The fitting of the N (x, y) discrete points by adopting the fourier series method to obtain the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio respectively can be performed based on the following fourier series formula:
wherein y corresponds to the pitch value in the fitted audio continuous curve, T represents the signal period,for fundamental angular frequency, a 0 As a direct current component, a n For the amplitude of the cosine component, b n For the amplitude of the sinusoidal component, x is the time corresponding to the pitch value y.
Fig. 2 is a schematic diagram of audio curve changes before and after fitting by using a continuous fitting method according to an embodiment of the present invention. Referring to fig. 2, it can be seen that the method of fitting the singing audio to be scored and the standard singing audio by adopting the continuous curve fitting method 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 in the process of high-low pitch conversion, keep the tiny change of the tone in the audio, and score the singing audio to be scored and the standard singing audio on the basis of the method, so that the accuracy of scoring by singing software can be effectively improved.
In one embodiment, obtaining the first singing score based on the audio continuous curve of the singing audio to be scored and based on the audio continuous curve of the standard singing audio in step S103 includes:
and comparing the audio continuous curve of the singing audio to be scored with the audio continuous curve of the standard singing audio, and determining a first singing score based on the curve comparison result.
In some embodiments, the above continuous curve fitting method is adopted to perform curve fitting on the obtained singing audio to be scored and the standard singing audio corresponding to the singing audio to be scored, so as to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio. After the audio continuous curve of the standard singing audio is obtained, the obtained audio continuous curve of the standard singing audio can be stored in an audio fingerprint library.
In some embodiments, when the fitted audio continuous curve of the standard singing audio corresponding to the singing audio to be scored is obtained, the audio continuous curve of the standard singing audio corresponding to the singing audio to be scored may be directly obtained from the audio fingerprint library. By directly obtaining the required audio continuous curve of the standard singing audio from the audio fingerprint library, the calculation time can be saved when the singing audio score to be scored is actually carried out, and the efficiency of scoring the singing audio to be scored is further improved.
Specifically, the audio fingerprint library is used for storing fingerprint features of standard singing audio, and the fingerprint features can include, but are not limited to, frequency parameters and time parameters corresponding to the frequency spectrum of the standard singing audio data, and the audio continuity curve of the standard singing audio obtained by adopting the continuity curve fitting method.
In some embodiments, comparing the audio continuous curve of the singing audio to be scored with the audio continuous curve of the standard singing audio, and determining the first singing score based on the comparison result includes:
comparing the continuous audio curves of the singing audio to be scored with the continuous audio curves of the standard singing audio to obtain the coincidence value of the two curves;
the first singing score is determined based on the coincidence value of the two curves.
In some embodiments, comparing the degree of coincidence of the continuous audio curve of the singing audio to be scored and the continuous audio curve of the standard singing audio to obtain the degree of coincidence value of the two curves comprises obtaining the degree of coincidence value score based on the following formula:
score＝100-area1/area2*100，
wherein area1 is the area wrapped 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 represented by Max [ |y max -y A |,|y A |]And corresponding integral of time, where y max For a preset maximum pitch value, y A Pitch values in an audio continuum for standard singing audio.
And calculating the superposition degree value score of the audio continuous curve of the singing audio to be scored and the audio continuous curve of the standard singing audio according to the formula, and taking the superposition degree value score as a first singing score.
Referring now to FIG. 3, FIG. 3 is a graph of an audio continuum of a fitted standard singing audio and a fitted standard singing audio according to an embodiment of the present inventionWherein curve A is the audio continuous curve of the standard singing audio after fitting, curve B is the audio continuous curve of the singing audio after fitting, the area of the package between curve A and curve B is area1=a1+a2+a3, and Max [ |y ] is taken for the pitch value and the preset maximum pitch value in curve A max -y A |,|y A |]Wherein y is max For a preset maximum pitch value, y A For the ordinate value of curve A, i.e. the pitch value in curve A, the Max [ |y max -y A |,|y A |]And performing curve integration on the value and the corresponding time t value to obtain an area2, and then obtaining a superposition value score of the curve A and the curve B based on a formula score=100-area 1/area2 x 100 according to the calculated area1 and area2 values, and further taking the superposition value score as a first singing score.
In some embodiments, a singing scoring method based on a continuous curve fit further includes scoring singing skills for the singing audio to be scored, wherein scoring singing skills for the singing audio to be scored includes:
detecting whether the change of a pitch value in an audio continuous curve of singing audio to be scored within a first preset duration is larger than a first preset threshold or not;
and scoring singing skills of the singing audio to be scored based on the detection result.
In some embodiments, scoring singing skills of the singing audio to be scored based on the detection result includes:
if the detection result is that the change of the pitch value in the audio continuous curve of the singing audio to be scored within the first preset time length is larger than a first preset threshold value, judging that the singing audio to be scored obtains singing skill score, and determining the singing skill score of the singing audio to be scored based on a threshold value interval in which the change of the pitch value in the audio continuous curve of the singing audio to be scored within the first preset time length in the detection result is located;
otherwise, judging that the singing voice frequency to be scored does not obtain singing skill score.
Specifically, the pitch value in the audio continuous curve of a piece of audio is detected, and if the change of the pitch value in the audio continuous curve in a first preset time period is greater than a first preset threshold value, that is, the pitch value of the piece of audio changes drastically in a short time period, singing skills like tremolo and transfer can be considered to exist in the piece of audio. Judging whether singing skills exist in the singing audio to be scored or not by detecting the change of the pitch value of the audio continuous curve of the singing audio to be scored within a first preset duration. If singing skills are detected in the singing audios to be scored, the singing audios to be scored can obtain singing skill scores.
In some application embodiments, determining the singing skill score of the singing audio to be scored based on a threshold interval in which a change in pitch value in an audio continuous curve of the singing audio to be scored in the detection result falls within a first preset duration includes:
cy1 is the change value of the pitch value in the audio continuous curve of the singing audio to be scored within a first preset duration;
if the first preset threshold value is not less than Cy1 and not more than the second preset threshold value, the singing audio to be scored obtains a first preset skill score value;
if Cy1 is larger than a second preset threshold value, the singing audio to be scored obtains a second preset skill score value.
It should be noted that the above rule for determining the score of singing skills in the singing audio to be scored is merely illustrative, and the rule for determining the score of singing skills in the singing audio to be scored may be adjusted and set according to actual needs in practical applications.
In some other embodiments, in addition to detecting whether a change in pitch value in the audio continuous curve of the singing audio to be scored is greater than a first preset threshold, detecting whether a change in pitch value in the audio continuous curve of the standard singing audio is greater than the first preset threshold, and determining a singing skill score of the singing audio to be scored based on the pitch value in the audio continuous curve of the standard singing audio and a threshold interval in which the change in pitch value in the audio continuous curve of the singing audio to be scored falls in the first preset period.
Specifically, whether singing skills exist in the standard singing audio is judged by detecting the pitch value change of the audio continuous curve of the standard singing audio within a first preset duration, and whether singing skills exist in the singing audio to be scored is judged by detecting the pitch value change of the audio continuous curve of the singing audio to be scored within the first preset duration. If the singing skills are detected in the standard singing audio and the singing audio to be scored, the singing skill score can be obtained by the singing audio to be scored.
Specifically, determining, based on a pitch value in an audio continuous curve of standard singing audio and a threshold interval in which a change in a pitch value in an audio continuous curve of singing audio to be scored falls within a first preset duration in a detection result, a singing skill score of the singing audio to be scored includes:
cy0 is the change value of the pitch value in the audio continuous curve of the standard singing audio within a first preset time period, and Cy1 is the change value of the pitch value in the audio continuous curve of the singing audio to be scored within the first preset time period;
if the first preset threshold value is less than or equal to Cy0 and less than or equal to the second preset threshold value and the first preset threshold value is less than or equal to Cy1 and less than or equal to the second preset threshold value, the singing audio to be scored obtains a first preset skill score value;
if Cy0 is larger than a second preset threshold value and Cy1 is larger than the second preset threshold value, obtaining a second preset skill score value from singing audio to be scored;
if Cy0 is larger than or equal to a first preset threshold value and Cy1 is larger than or equal to a first preset threshold value, but the numerical values of Cy0 and Cy1 do not meet the scoring condition that the singing audio to be scored obtains the first preset skill score value and the second preset skill score value, the singing audio to be scored obtains a third preset skill score value.
It should be noted that the above rule for determining the score of singing skills in the singing audio to be scored is merely illustrative, and the rule for determining the score of singing skills in the singing audio to be scored may be adjusted and set according to actual needs in practical applications.
In other embodiments, if the Cy0 is greater than or equal to the first preset threshold, the standard singing audio may be marked with features, which indicates that singing skills exist in the standard singing audio, and the Cy0 value and the first preset duration are stored in the audio fingerprint library as singing skill features of the standard singing audio. When the singing skill scoring is actually performed on the singing voice frequency to be scored, the singing skill characteristics of the standard singing voice frequency corresponding to the singing voice frequency to be scored can be directly obtained from the voice frequency fingerprint library, the singing skill characteristics of the singing voice frequency to be scored and the singing skill characteristics in the standard singing voice frequency are compared, and whether the singing voice frequency to be scored obtains the singing skill score or not is judged. By means of the method, fingerprint characteristic information of standard singing audio in an audio fingerprint library can be enriched, and scoring efficiency of singing audio to be scored can be improved.
In one embodiment, scoring the singing audio to be scored based on at least the first singing score in step S104 includes:
scoring the singing audio to be scored based on the first singing score;
or scoring the singing audio to be scored based on the first singing score and the singing skill score.
In some application embodiments, the scoring of the singing audio to be scored may be performed based on the first singing score, and the scoring of the singing audio to be scored may be performed directly with the acquired first singing score. Based on the first singing score and the singing skill score, the singing audio to be scored is scored, and the score of the final singing audio can be determined in a mode of directly carrying out accumulation summation on the first singing score and the singing skill score. Or determining a score of the final singing audio based on the weight calculation of the first singing score and the singing skill score, wherein the weights corresponding to the first singing score and the singing skill score are respectively greater than or equal to zero, and the sum of the weights corresponding to the first singing score and the singing skill score is equal to 1. Specifically, what mode is adopted to determine the score of the final singing audio based on the first singing score and the singing skill score can be adjusted and selected according to actual needs in practical application, so long as the score of the singing audio to be scored is reasonably and effectively achieved, and details are not repeated here.
By adopting the method, the singing audio to be scored can be scored by directly using the first singing score, or the singing audio to be scored can be scored by comprehensively using the first singing score and the singing skill score. Through the operation, the singing audio to be scored can be evaluated more selectively and comprehensively, and the rationality and the effectiveness of the singing scoring method are improved.
It should be noted that, although the foregoing embodiments describe the steps in a specific order, it will be understood by those skilled in the art that, in order to achieve the effects of the present invention, the steps are not necessarily performed in such an order, and may be performed simultaneously (in parallel) or in other orders, and these variations are within the scope of the present invention.
It will be appreciated by those skilled in the art that the present invention may implement all or part of the above-described methods according to the above-described embodiments, or may be implemented by means of a computer program for instructing relevant hardware, where the computer program may be stored in a computer readable storage medium, and where the computer program may implement the steps of the above-described embodiments of the method when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable storage medium may include: any entity or device, medium, usb disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier wave signals, telecommunications signals, software distribution media, and the like capable of carrying the computer program code. It should be noted that the computer readable storage medium may include content that is subject to appropriate increases and decreases as required by jurisdictions and by jurisdictions in which such computer readable storage medium does not include electrical carrier signals and telecommunications signals.
Furthermore, the invention also provides a singing scoring device based on continuous curve fitting. Referring to fig. 4, fig. 4 is a schematic block diagram of a singing scoring device based on continuous curve fitting according to an embodiment of the present invention. In one continuous curve fitting-based singing scoring device embodiment according to the present invention, the continuous curve fitting-based singing scoring device 400 includes a processor 401 and a memory 402, the memory 402 may be configured to store a program for executing the continuous curve fitting-based singing scoring method of the above method embodiment, and the processor 401 may be configured to execute the program in the memory 402, including, but not limited to, the program for executing the continuous curve fitting-based singing scoring method of the above method embodiment. For convenience of explanation, only those portions of the embodiments of the present invention that are relevant to the embodiments of the present invention are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present invention. The apparatus may be a control apparatus device formed of various electronic devices.
Further, the invention also provides a computer readable storage medium. In one computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium may be configured to store a program for performing the continuous curve fitting-based singing scoring method of the above-described method embodiment, which may be loaded and executed by a processor to implement the continuous curve fitting-based singing scoring method described above. For convenience of explanation, only those portions of the embodiments of the present invention that are relevant to the embodiments of the present invention are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present invention. The computer readable storage medium may be a storage device including various electronic devices, and optionally, the computer readable storage medium in the embodiments of the present invention is a non-transitory computer readable storage medium.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will fall within the scope of the present invention.
Claims (10)
1. A singing scoring method based on continuous curve fitting, the method comprising the steps of:
acquiring singing audio to be scored and standard singing audio corresponding to the singing audio to be scored;
fitting the singing audio to be scored and the standard singing audio by adopting a continuous curve fitting method to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio;
obtaining a 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;
and scoring the singing audio to be scored based on at least the first singing score.
2. The singing scoring method based on continuous curve fitting according to claim 1, wherein the fitting the singing audio to be scored and the standard singing audio to obtain an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio by adopting the continuous curve fitting method includes:
dividing the singing audio to be scored and the standard singing audio into a plurality of audio fragments according to the time dimension;
collecting discrete pitch values y for the singing audio to be scored and the plurality of audio fragments of the standard singing audio respectively, and recording the time corresponding to the discrete pitch values y as x to obtain a plurality of (x, y) discrete points;
fitting the singing audio to be scored and the (x, y) discrete points of the standard singing audio respectively by adopting a polynomial or Fourier series mode, and obtaining an audio continuous curve of the singing audio to be scored and an audio continuous curve of the standard singing audio respectively.
3. The singing scoring method based on continuous curve fitting of claim 1, wherein the obtaining a first singing score based on the audio continuous curve of the singing audio to be scored and based on the audio continuous curve of the standard singing audio comprises:
and comparing the audio continuous curve of the singing audio to be scored with the audio continuous curve of the standard singing audio, and determining the first singing score based on the curve comparison result.
4. The singing scoring method based on continuous curve fitting of claim 3, wherein the comparing the audio continuous curve of the singing audio to be scored with the audio continuous curve of the standard singing audio and determining the first singing score based on the curve comparison result comprises:
comparing the continuous audio curves of the singing audio to be scored with the continuous audio curves of the standard singing audio in a curve overlap ratio mode to obtain an overlap ratio value of the two curves;
the first singing score is determined based on the coincidence degree value of the two curves.
5. The singing scoring method based on continuous curve fitting of claim 4, wherein comparing the continuous audio curves of the singing audio to be scored and the continuous audio curves of the standard singing audio to obtain the overlap ratio value of the two curves comprises obtaining the overlap ratio value score based on the following formula:
score＝100-area1/area2*100，
wherein area1 is the area of the package 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 represented by Max [ |y max -y A |,|y A |]And corresponding integral of time, where y max For a preset maximum pitch value, y A Pitch values in an audio continuum for standard singing audio.
6. The singing scoring method based on continuous curve fitting of claim 1, further comprising singing skill scoring the singing audio to be scored, wherein scoring the singing skill scoring the singing audio to be scored comprises:
detecting whether the change of a pitch value in an audio continuous curve of the singing audio to be scored within a first preset duration is larger than a first preset threshold or not;
and scoring the singing skills of the singing audio to be scored based on the detection result.
7. The singing scoring method based on continuous curve fitting of claim 6, wherein scoring the singing skill of the singing audio to be scored based on the detection result comprises:
if the change of the pitch value in the audio continuous curve of the singing audio to be scored within a first preset time period is larger than a first preset threshold value, judging that the singing audio to be scored obtains singing skill score, and determining the singing skill score of the singing audio to be scored based on a threshold value interval within which the change of the pitch value in the audio continuous curve of the singing audio to be scored within the first preset time period in the detection result is located;
otherwise, judging that the singing skill score is not obtained by the singing audio to be scored.
8. A singing scoring method based on a continuous curve fit as claimed in claim 6 or 7, wherein said scoring the singing audio to be scored based on at least the first singing score comprises:
scoring the singing audio to be scored based on the first singing score;
or scoring the singing audio to be scored based on the first singing score and the singing skill score.
9. A singing scoring device based on continuous curve fitting, comprising a processor and a memory adapted to store a plurality of program code adapted to be loaded and executed by the processor to perform the singing scoring method based on continuous curve fitting of any one of claims 1 to 8.
10. A computer readable storage medium having stored therein a plurality of program codes, wherein the program codes are adapted to be loaded and executed by a processor to perform the continuous curve fitting based singing scoring method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210988036.XA CN117636904A (en) | 2022-08-17 | 2022-08-17 | Singing scoring method, device and storage medium based on continuous curve fitting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210988036.XA CN117636904A (en) | 2022-08-17 | 2022-08-17 | Singing scoring method, device and storage medium based on continuous curve fitting |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117636904A true CN117636904A (en) | 2024-03-01 |
Family
ID=90016945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210988036.XA Pending CN117636904A (en) | 2022-08-17 | 2022-08-17 | Singing scoring method, device and storage medium based on continuous curve fitting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117636904A (en) |
-
2022
- 2022-08-17 CN CN202210988036.XA patent/CN117636904A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11657798B2 (en) | Methods and apparatus to segment audio and determine audio segment similarities | |
| CN110265064B (en) | Audio frequency crackle detection method, device and storage medium | |
| US10366121B2 (en) | Apparatus, method, and computer-readable medium for cue point generation | |
| CN110797031A (en) | Voice change detection method, system, mobile terminal and storage medium | |
| CN111739542B (en) | Method, device and equipment for detecting characteristic sound | |
| JP2005227782A (en) | Apparatus and method for detecting voiced sound and unvoiced sound | |
| CN112015347A (en) | Data migration method and device and related equipment | |
| CN111854888B (en) | Water level detection method and device, storage medium and kettle | |
| TW202127376A (en) | Method, device for evaluating fingerprint quality based on images and electronic device | |
| WO2009074871A2 (en) | System and method for the characterization, selection and recommendation of digital music and media content | |
| CN107210029B (en) | Method and apparatus for processing a series of signals for polyphonic note recognition | |
| WO2010015145A1 (en) | Method and system for filtering and monitoring program behaviors | |
| CN111400542A (en) | Audio fingerprint generation method, device, equipment and storage medium | |
| CN117636904A (en) | Singing scoring method, device and storage medium based on continuous curve fitting | |
| CN116706876A (en) | Broadband oscillation identification method, device and equipment for dual-high power system | |
| CN112416709B (en) | Chip dynamic power consumption estimation method and device, processor chip and server | |
| CN109086984B (en) | Method and device for evaluating life cycle of platform, computer equipment and storage medium | |
| CN113656043B (en) | Code verification method and device, electronic equipment and storage medium | |
| CN109870621A (en) | Run judgment method and device | |
| CN117591784B (en) | FPGA-based twiddle factor calculation method and FPGA chip | |
| JP6257537B2 (en) | Saliency estimation method, saliency estimation device, and program | |
| CN116364063B (en) | Phoneme alignment method, apparatus, driving apparatus, and medium | |
| CN106295026B (en) | Traffic similarity analysis method and device | |
| JP5131172B2 (en) | Period identification device and program | |
| CN117275469A (en) | Voice refusing method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |