Fitting system and method for original singing audio information, computer storage medium
By generating a safe pitch range and correcting the user's audio, the problem of user pitch deviation is solved, improving the pitch accuracy and singing effect of the karaoke machine.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHENGDU XIAOCHANG TECH CO LTD
- Filing Date
- 2026-03-13
- Publication Date
- 2026-06-05
AI Technical Summary
When users sing with a karaoke machine, insufficient control can cause pitch to be difficult to match the standard pitch, especially in the low or high notes, which affects the singing effect.
By obtaining the standard pitch sequence of the song, a safe pitch range is generated, and the user's original audio is corrected to adjust the pitch value to the upper or lower limit threshold of the safe range, ensuring that the pitch deviation is within a certain range.
It reduces instances of users cracking their voices or dropping to extremely low notes during singing, thus improving the overall presentation of the performance.
Smart Images
Figure CN121838696B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of audio processing technology, specifically to a system and method for fitting original audio information and a computer storage medium. Background Technology
[0002] Since its emergence, karaoke machines have gained increasing popularity. However, for ordinary users, the limited control they have often results in difficulty matching the pitch of the song, especially in the low and high registers. Users require greater control to achieve good results in these areas. In practice, while trying to match the standard pitch in the low and high registers, the lack of control can lead to significant pitch deviations, ultimately resulting in a less than ideal performance. Summary of the Invention
[0003] This application provides a system and method for fitting original audio information, as well as a computer storage medium, which can correct the user's voice and improve the final presentation of the performance.
[0004] The specific technical solution of this embodiment is as follows:
[0005] On the one hand, embodiments of this application provide a method for fitting original audio information, including the following steps:
[0006] S10. Obtain the selected song information and, based on the selected song, obtain the standard pitch sequence of the song;
[0007] S20. Based on the standard pitch sequence, generate a pitch safety range that varies with the standard pitch sequence, wherein the pitch safety range includes an upper limit threshold and a lower limit threshold for the allowable offset determined for each note in the standard pitch sequence.
[0008] S30. Obtain the user's original audio recording and compare the real-time pitch of the original audio recording with the corresponding pitch safety range.
[0009] S40. Correct notes in the original audio that exceed the pitch safety range, including correcting pitch values that exceed the upper limit threshold of the pitch safety range to the upper limit threshold, and correcting pitch values that are below the lower limit threshold of the pitch safety range to the lower limit threshold.
[0010] In some embodiments, generating a pitch safety range that varies with the standard pitch sequence includes the following steps:
[0011] S201. Based on each note in the standard pitch sequence, determine whether the pitch value of the note is above the preset pitch value.
[0012] S202. When it is determined that the pitch value of the note is above the pitch value, the offset of the upper limit threshold of the pitch safety interval corresponding to the note is greater than the offset of the lower limit threshold.
[0013] S203. When it is determined that the pitch value of the note is below the middle pitch value, the offset of the upper limit threshold of the pitch safety interval corresponding to the note is less than the offset of the lower limit threshold.
[0014] In some embodiments, after determining whether the pitch value of the note is above a preset pitch value, the following steps are also included:
[0015] S204. When the pitch value of the note is determined to be equal to the pitch midpoint, the offset of the upper limit threshold of the pitch safety interval corresponding to the note is equal to the offset of the lower limit threshold.
[0016] In some embodiments, generating a pitch safety range that varies with the standard pitch sequence based on the standard pitch sequence includes the following steps: setting an upper limit threshold and a lower limit threshold with the same offset for each note in the standard pitch sequence.
[0017] In some embodiments, the offsets of the upper and lower thresholds are set to at least one specific value based on each note in the standard pitch sequence.
[0018] In some embodiments, the offsets between the upper and lower thresholds are set to specific values based on user selection.
[0019] In some embodiments, after correcting notes in the original vocal audio that exceed the pitch safety range, the following steps are also included:
[0020] S50: Perform secondary corrections on the user's original audio recording.
[0021] In some embodiments, secondary correction of the user's original audio includes the following steps:
[0022] S501. Obtain the first difference between the first pitch value in the standard pitch sequence where the previous note is located and the corresponding second pitch value of the user.
[0023] S502, Obtain the second difference between the third pitch value in the standard pitch sequence where the current note is located and the corresponding fourth pitch value of the user;
[0024] S503. Determine whether the second difference is greater than the first difference;
[0025] S504. When it is determined that the second difference is greater than the first difference, the fourth pitch value is shifted towards the third pitch value by at least a portion.
[0026] S505. When it is determined that the second difference is not greater than the first difference, the process ends.
[0027] On the other hand, embodiments of this application provide a system for fitting original audio information, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method for fitting original audio information in any of the above embodiments.
[0028] This application also provides a computer storage medium storing a computer program, which is driven to execute the original audio information fitting method of any of the above embodiments.
[0029] Compared with the prior art, the embodiments of this application have the following beneficial effects:
[0030] The method for fitting original vocal audio information provided in this application, for each real-time note sung by the user, corrects the pitch value of the note to the upper limit threshold of the pitch safety range when the pitch value is higher than the upper limit threshold, and corrects the pitch value to the lower limit threshold when the pitch value is lower than the lower limit threshold. Through the settings of the above embodiments, the offset of the pitch value of each note in the user's song from the standard pitch sequence can be kept within a certain range. This effectively provides a safety net for the user's singing, reducing instances of the user's voice cracking (extremely high) or falling into a low register (extremely low), thereby improving the final presentation of the performance. Attached Figure Description
[0031] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0032] Figure 1 This is a flowchart illustrating a method for fitting original audio information provided in some embodiments of this application;
[0033] Figure 2 This is a flowchart illustrating a method for fitting original audio information provided in other embodiments of this application. Detailed Implementation
[0034] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0035] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.
[0036] The use of "applies to" or "configured to" in this application implies open and inclusive language, which does not exclude the applicability to or configuration to devices performing additional tasks or steps. Additionally, the use of "based on" implies openness and inclusivity, because processes, steps, calculations, or other actions "based on" one or more of the stated conditions or values may in practice be based on additional conditions or values beyond those stated.
[0037] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.
[0038] On the one hand, please refer to Figure 1 and Figure 2 , Figure 1This is a flowchart illustrating a method for fitting original audio information provided in some embodiments of this application; Figure 2 This is a flowchart illustrating a method for fitting original vocal audio information provided in other embodiments of this application. Embodiments of this application provide a method for fitting original vocal audio information, comprising the following steps:
[0039] S10. Obtain the selected song information and, based on the selected song, obtain the standard pitch sequence of the song.
[0040] In S10, based on the user-selected song, the music library is automatically retrieved to obtain the standard pitch sequence of the original song. This standard pitch sequence may differ depending on the original singer. Pitch refers to the level of a sound's frequency, one of the three main subjective attributes of sound, representing the degree to which a person's hearing can distinguish the high or low pitch of a sound. The standard pitch sequence of a song refers to the set of multiple pitch sequences in the original song.
[0041] S20. Based on the standard pitch sequence, generate a pitch safety range that varies with the standard pitch sequence. The pitch safety range includes an upper and lower threshold for allowed offsets determined for each note in the standard pitch sequence.
[0042] In S20, different upper and lower threshold values can be set for notes of different pitches, or the same upper and lower threshold values can be set; similarly, different upper and lower threshold values can be set for notes of the same pitch, or the same upper and lower threshold values can be set. By setting multiple notes, a safe pitch range is formed. The amount of offset for each note based on the standard pitch can be set as a fixed value or as a fixed proportion. The offset of the upper and lower threshold values can be the same or different.
[0043] S30. Obtain the user's original audio recording and compare the real-time pitch of the original audio recording with the corresponding pitch safety range.
[0044] In S30, the real-time pitch of the original audio refers to the tone of the notes at the current moment when the user is singing the song. The real-time pitch of the original audio is compared with the upper and lower thresholds of the pitch safety range.
[0045] S40. Correct notes in the original audio that exceed the pitch safety range, including correcting pitch values that exceed the upper limit threshold of the pitch safety range to the upper limit threshold, and correcting pitch values that are below the lower limit threshold of the pitch safety range to the lower limit threshold.
[0046] In the above embodiments, for each real-time note sung by the user, when the pitch value of the note is higher than the upper limit threshold of the pitch safety range, the pitch value of the note is corrected to the upper limit threshold of the pitch safety range; when the pitch value of the note is lower than the lower limit threshold of the pitch safety range, the pitch value of the note is corrected to the lower limit threshold of the pitch safety range.
[0047] By setting up the above embodiments, the pitch value of each note in the user's song can be kept within a certain range relative to the standard pitch sequence. This effectively provides a safety net for the user's singing, reducing the chances of the user cracking (very high) or falling into a pit (very low) during the performance, thereby improving the final presentation of the performance.
[0048] In some embodiments, step S20, generating a pitch safety range that varies with the standard pitch sequence based on the standard pitch sequence, includes the following steps:
[0049] S201. Based on each note in the standard pitch sequence, determine whether the pitch value of the note is above the preset pitch value.
[0050] In S201, the preset pitch value is a fixed value that can be set based on a sequence of marked pitch values for common songs, or based on a standard pitch sequence for a specific selected song. In some examples, the pitch value can be a pitch value in the middle, or another pitch value near the middle.
[0051] S202. When it is determined that the pitch value of the note is above the middle pitch value, the offset of the upper limit threshold of the pitch safety interval corresponding to the note is greater than the offset of the lower limit threshold.
[0052] In S202, the pitch value of this note refers to the pitch value of the note corresponding to the standard pitch sequence in the original song.
[0053] S203. When it is determined that the pitch value of the note is below the middle pitch value, the offset of the upper limit threshold of the pitch safety interval corresponding to the note is less than the offset of the lower limit threshold.
[0054] When determining that the pitch value of a note is equal to the pitch midpoint, it can be that the offset of the upper threshold of the pitch safety interval corresponding to the note is greater than the offset of the lower threshold, the offset of the upper threshold of the pitch safety interval corresponding to the note is less than the offset of the lower threshold, or the offset of the upper threshold of the pitch safety interval corresponding to the note is equal to the offset of the lower threshold.
[0055] In specific application scenarios, when the pitch value of a note is above the mid-range value, users will try to use higher notes when singing, making it easier to shift to higher pitch values; while when the pitch value of a note is below the mid-range value, users will try to use lower notes when singing, making it easier to shift to lower pitch values.
[0056] Therefore, through the settings of the above embodiments, when the pitch value of a note is above the pitch midpoint, the upper threshold of the pitch safety interval corresponding to the note is set to an offset that is greater than the lower threshold; when the pitch value of a note is below the pitch midpoint, the upper threshold of the pitch safety interval corresponding to the note is set to an offset that is less than the lower threshold. This can reduce the pitch value reduced during the pitch correction process when the pitch value of the user's voice exceeds the pitch safety interval, thereby making the user's voice and the final presented sound more consistent, reducing the situation where the pitch correction effect is too obvious, so that the final presented sound can be more natural.
[0057] In some embodiments, after step S201, determining whether the pitch value of the note is above a preset pitch value, the following steps are also included:
[0058] S204. When the pitch value of the note is determined to be equal to the pitch midpoint, the offset of the upper limit threshold of the pitch safety interval corresponding to the note is equal to the offset of the lower limit threshold.
[0059] The above-described embodiments allow for better adaptation to different user groups, enabling notes with mid-range pitch values to be more stable. Furthermore, with such detailed settings for safe pitch ranges, subsequent processing of the original audio becomes more targeted and scientific.
[0060] In some embodiments, step S20, generating a pitch safety range that varies with the standard pitch sequence based on the standard pitch sequence, includes the following steps:
[0061] For each note in the standard pitch sequence, set an upper and lower threshold with the same offset.
[0062] By using the above-described embodiments and setting the threshold with the same offset, the operation is simpler and the processing efficiency is higher compared to setting the threshold without a fixed offset. At the same time, the amount of data required for automatic processing is less, and the preparation and maintenance costs are lower, resulting in better economic efficiency.
[0063] In some embodiments, in step S20, the offsets of the upper and lower thresholds are set to at least one specific value based on each note in the standard pitch sequence.
[0064] The offsets of the upper and lower thresholds can be the same or different. When they are the same, their offsets are set to a single value. When they are different, their offsets are set to two separate values.
[0065] In some examples, when using steps S201-S203, if the offset of the upper limit threshold and the offset of the lower limit threshold of the target note's pitch value are different, the offsets are set to two specific values.
[0066] The settings described above enable more advanced audio editing for users with a more basic skill level, resulting in more personalized vocal performances.
[0067] In some embodiments, the offsets between the upper and lower thresholds are set to specific values based on user selection.
[0068] In the above embodiments, users can customize the offset of the upper and lower thresholds to obtain a setting effect that better suits their needs.
[0069] In some examples, users can customize the upper and lower thresholds and the lower threshold through a simple setting method, such as directly inputting an offset value. This offset value serves as the offset of the upper and lower thresholds for the entire song or for all musical works within a certain period. This is suitable for users who have some understanding of this pitch correction method but are not familiar with it.
[0070] In other examples, users can enter two offset values: one offset value as the offset of the upper threshold for the entire song or all musical works within a certain period, and the other offset value as the offset of the lower threshold for the entire song or all musical works within a certain period.
[0071] In other examples, users can set the offset of the upper and lower thresholds for each note. This method is more labor-intensive, but the resulting customized performance is more pronounced and more suitable for professionals.
[0072] In some embodiments, after correcting notes in the original vocal audio that exceed the pitch safety range in step S40, the following steps are also included:
[0073] S50: Perform secondary corrections on the user's original audio recording.
[0074] In the above embodiments, secondary correction can be performed in a conventional manner, such as using pitch adjustment algorithms to fine-tune the audio pitch to more accurately match the expected pitch range. Filtering can also be used to optimize the audio timbre, removing unnecessary noise and interference to make the sound purer. Equalization of audio volume is also a common secondary correction method to ensure that the volume of each note and segment remains balanced, avoiding sudden changes in volume.
[0075] In some embodiments, step S50, the secondary correction of the user's original audio, includes the following steps:
[0076] S501. Obtain the first difference between the first pitch value in the standard pitch sequence where the previous note is located and the second pitch value of the corresponding user.
[0077] In S501, the previous note is relative to the current real-time note. The first pitch value is the pitch value in the standard pitch sequence where the previous note is located, the second pitch value is the pitch value of the audio sung by the user in the previous note, and the first difference is the difference between the two.
[0078] S502. Obtain the second difference between the third pitch value in the standard pitch sequence where the current note is located and the corresponding fourth pitch value of the user.
[0079] In S502, the current fourth pitch value can be understood as the pitch value of the current note to be processed.
[0080] S503. Determine whether the second difference is greater than the first difference.
[0081] S504. When the difference is greater than the first difference, the fourth pitch value is shifted at least partially toward the third pitch value.
[0082] In S504, the third pitch value is a value in the standard pitch sequence, and the offset portion can be offset based on a preset value.
[0083] S505. When it is determined that the second difference is not greater than the first difference, the process ends.
[0084] In the above embodiments, by comparing the pitch of the notes in the user's song with the standard pitch sequence and with the previous note, the user's song can gradually converge, and the pitch correction can be smoother, resulting in a more natural pitch correction effect and a better final display effect.
[0085] On the other hand, embodiments of this application provide a system for fitting original audio information, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method for fitting original audio information in any of the above embodiments.
[0086] This application also provides a computer storage medium storing a computer program, which is driven to execute the original audio information fitting method of any of the above embodiments.
[0087] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for fitting original vocal audio information, characterized in that, include: S10. Obtain the selected song information and, based on the selected song, obtain the standard pitch sequence of the song; S20. Based on the standard pitch sequence, generate a pitch safety range that varies with the standard pitch sequence, wherein the pitch safety range includes an upper limit threshold and a lower limit threshold for allowed offsets determined for each note in the standard pitch sequence; S30. Obtain the user's original audio recording and compare the real-time pitch of the original audio recording with the corresponding pitch safety range; S40. Correcting notes in the original audio that exceed the pitch safety range, including correcting pitch values that exceed the upper threshold of the pitch safety range to the upper threshold, and correcting pitch values that are lower than the lower threshold of the pitch safety range to the lower threshold. Generating a pitch safety range that varies with the standard pitch sequence based on the standard pitch sequence includes the following steps: S201. Based on each note in the standard pitch sequence, determine whether the pitch value of the note is above the preset pitch value. S202. When it is determined that the pitch value of the note is above the pitch value, the offset of the upper limit threshold of the pitch safety interval corresponding to the note is greater than the offset of the lower limit threshold. S203. When it is determined that the pitch value of the note is below the middle pitch value, the offset of the upper limit threshold of the pitch safety interval corresponding to the note is less than the offset of the lower limit threshold.
2. The method for fitting original audio information as described in claim 1, characterized in that, After determining whether the pitch of the note is above the preset pitch value, the following steps are also included: S204. When the pitch value of the note is determined to be equal to the pitch midpoint, the offset of the upper limit threshold of the pitch safety interval corresponding to the note is equal to the offset of the lower limit threshold.
3. The method for fitting original audio information as described in claim 1, characterized in that, Generating a safe pitch range that varies with the standard pitch sequence based on the standard pitch sequence includes the following steps: setting an upper limit threshold and a lower limit threshold with the same offset for each note in the standard pitch sequence.
4. The method for fitting original audio information as described in any one of claims 1-3, characterized in that, For each note in the standard pitch sequence, the offsets of the upper and lower thresholds are set to at least one specific value.
5. The method for fitting original audio information as described in claim 4, characterized in that, The offsets between the upper and lower thresholds are set to specific values based on the user's selection.
6. The method for fitting original audio information as described in claim 1, characterized in that, After correcting the notes in the original vocal audio that exceed the pitch safety range, the method further includes the following steps: S50: Perform secondary corrections on the user's original audio recording.
7. The method for fitting original audio information as described in claim 6, characterized in that, The secondary correction of the user's original audio includes the following steps: S501. Obtain the first difference between the first pitch value in the standard pitch sequence where the previous note is located and the corresponding second pitch value of the user. S502, Obtain the second difference between the third pitch value in the standard pitch sequence where the current note is located and the corresponding fourth pitch value of the user; S503. Determine whether the second difference is greater than the first difference; S504. When it is determined that the second difference is greater than the first difference, the fourth pitch value is shifted towards the third pitch value by at least a portion. S505. When it is determined that the second difference is not greater than the first difference, the process ends.
8. A system for fitting original vocal audio information, characterized in that, The device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method for fitting original audio information as described in any one of claims 1-7.
9. A computer storage medium, characterized in that, It contains a computer program that is driven to perform the fitting method for the original audio information as described in any one of claims 1-7.