CN105825844B - Method and device for correcting sound - Google Patents

Abstract

Embodiments of the present invention provide a method and device for revising sound, the method comprising: acquiring the audio of a user's song; converting the audio of the song into a digital musical score; acquiring features of the audio of the song, and obtaining a standard musical score with the same features according to the features; Compare the digital score and the standard score, determine the difference between the digital score and the standard score; correct the digital score according to the difference. The embodiment of the present invention provides a method and device for sound correction, which realizes the correction of the user's singing out of tune on the mobile terminal, and enables convenient and fast sound correction processing in the later stage.

Description

Method and device for correcting sound

technical field

The present invention relates to the technical field of audio processing, and in particular, to a method and device for modifying sound.

Background technique

K-singing is a way of entertainment for people, but because different people have different perceptions of music and melody, out-of-tune or rhythm sometimes happens, which seriously affects the mood of singing.

Now, the only way to solve out-of-tune or not keep up with the rhythm is to find a professional recording studio for post-processing to correct the out-of-tune. Although the studio sound repair is highly professional, under the constraints of a long production cycle and high production costs, it is difficult for ordinary people to accept it, resulting in a decline in people's interest in K songs.

Therefore, a technical problem that needs to be urgently solved by those skilled in the art at present is how to implement a convenient and quick post-editing process when singing.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a sound repair method and device, so as to solve the technical problem that a user can only go to a recording studio to repair the audio in order to correct the out-of-tune.

In order to solve the above problems, an embodiment of the present invention discloses a method for revising a sound, including:

Get the user's song audio;

convert the audio of the song into a digital sheet music;

Acquire the features of the audio of the song, and according to the features, obtain a standard musical score with the same features;

comparing the digital musical score and the standard musical score, and determining the difference between the digital musical score and the standard musical score;

The digital score is revised according to the difference.

Preferably, the comparison of the digital musical score and the standard musical score to determine the difference between the digital musical score and the standard musical score includes:

Comparing at least one of tempo, tempo or pitch frequency of the digital score and the standard score, at least one of tempo difference, tempo difference or pitch frequency difference is obtained.

Preferably, in the step of acquiring the user's song audio, the song audio is dry sound.

Preferably, the step of obtaining the features of the audio of the song, and according to the features, obtaining a standard musical score with the same features includes:

Acquire the song title and the original singer's name of the audio of the song, and obtain a corresponding standard musical score through the song title and the original singer's name, where the standard musical score is a digital musical score.

Preferably, the step of correcting the digital musical score according to the difference includes:

displaying the difference on the staff of the standard score according to the difference in tempo, the difference in beat and the difference in pitch frequency;

The user's modification instruction is received, and the audio of the song is modified.

An embodiment of the present invention provides a sound-modifying device, including:

The song frequency acquisition module is used to acquire the user's song audio;

a conversion module for converting the audio of the song into a digital score;

A standard musical score acquisition module, used to obtain the features of the audio of the song, and according to the features, obtain a standard musical score with the same described features;

Difference comparison module, used to compare the digital musical score and the standard musical score, and determine the difference between the digital musical score and the standard musical score;

A musical score correction module, used for correcting the digital musical score according to the difference.

Preferably, the difference comparison module is specifically configured to compare at least one of tempo, beat or pitch frequency of the digital musical score and the standard musical score, and obtain a tempo difference, beat difference or pitch frequency difference at least one of the differences.

Preferably, in the song frequency acquisition module, the song audio is dry sound.

Preferably, the standard musical score obtaining module is specifically configured to obtain the song title and the original singer's name of the song audio, and obtain the corresponding standard musical score through the song title and the original singer's name, and the standard musical score is a digital musical score .

Preferably, the musical score correction module includes:

a difference value display unit, used for displaying the difference value on the staff of the standard musical score according to the speed difference value, the beat difference value and the pitch frequency difference value;

A correction unit, configured to receive a correction instruction from the user, and correct the audio of the song.

A method and device for revising sound provided by an embodiment of the present invention, by acquiring the audio of a user's song, converting the audio of the song into a digital musical score; acquiring the feature of the audio of the song, and obtaining a standard musical score with the same feature according to the feature of the audio of the song ; Compare the digital score and the standard score, determine the difference between the digital score and the standard score; modify the digital score according to the difference, so as to correct the user's singing out of tune on the mobile terminal, which can be convenient and quick for post-editing processing.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a schematic flowchart of a method for revising a sound provided by Embodiment 1 of the present invention;

Fig. 2a is a schematic diagram of a digital musical score provided by Embodiment 1 of the present invention;

Fig. 2b is the schematic diagram of the standard musical score provided by the first embodiment of the present invention;

3 is a schematic flowchart of a method for revising a sound according to Embodiment 2 of the present invention;

FIG. 4 is a schematic structural diagram of a sound-modifying device provided in Embodiment 3 of the present invention;

FIG. 5 is a schematic structural diagram of a sound modification device according to Embodiment 4 of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Example 1

Embodiment 1 of the present invention provides a method for revising sound. As shown in FIG. 1 , the method for revising sound may include the following steps:

Step S101, acquiring the user's song audio.

In this step, the mobile terminal can obtain the user's song audio through the microphone. The song audio can be dry sound, which is also called naked sound, which belongs to the audio term and generally refers to the original person who has not undergone any post-processing and processing after recording. Voice. In this embodiment of the present invention, the mobile terminal may be an electronic device having a recording function, an audio storage function, and an audio playback function, such as a mobile phone and a tablet computer.

Step S102, converting the audio of the song into a digital musical score.

In this step, the audio of the song can be converted into a digital musical score through processing such as spectrum, power, and zero-crossing, and the digital musical score can include information such as song speed, melody pitch, tempo, and dynamic relationship.

In step S103, the characteristics of the song audio are acquired, and according to the characteristics, a standard musical score with the same characteristics is acquired.

In this step, the standard score is a score that is completely sung and/or played in accordance with the score, and in layman's terms is a score that is not out of tune. The audio features of the song may include: song title, original singer name and version, for example, the song name is "Ten Years", the original singer name is "Eason Chan", and the version is a recording studio board. Features of the song audio may also include cover artist names. According to the above features, a standard musical score with the same characteristics can be searched in the local music library of the mobile terminal, and the standard musical score can be the musical score sung by the original singer. The local music library can also store different versions of standard scores sung by a singer, such as studio board, live version, concert version, etc. Generally speaking, the sound quality of the studio version is better than the live version, so , when there are multiple versions of the standard score in the local score, the score with the best sound quality can be selected first, such as the studio score.

Step S104, compare the digital musical score and the standard musical score, and determine the difference between the digital musical score and the standard musical score.

In this step, it can be determined whether the digital musical score is out of tune by comparing the rhythm and pitch of the digital musical score and the standard musical score. Rhythm represents the speed and intensity of music, and the rhythm can include two parts: speed and beat. Therefore, there will be a difference in at least one of tempo, tempo, and pitch between the digital score and the standard score. Specifically, at least one of the tempo, tempo or pitch frequency of the digital musical score and the standard musical score can be compared locally on the mobile terminal to obtain at least one of the tempo difference, tempo difference or pitch frequency difference. If there is no difference between the digital musical score and the standard musical score, or the difference in tempo, tempo, or pitch and frequency is within the allowable difference range, a prompt that tuning is not required may be fed back to the user.

Step S105, correcting the digital musical score according to the difference.

In this step, the digital musical score can be modified locally on the mobile terminal according to the difference, so as to realize that there is no difference between the digital musical score and the standard musical score, that is, the digital musical score that is out of tune is corrected. In the embodiment of the present invention, the difference value can be displayed on the staff of the standard musical score according to the speed difference value, the beat difference value and the pitch frequency difference value; the user's correction instruction is received to correct the audio of the song, and the user's correction instruction can be for all The difference is corrected to achieve one-click sound repair, or it can be repaired to some differences, and some differences are retained to achieve personalized sound repair.

FIG. 2a is a schematic diagram of a digital musical score provided by Embodiment 1 of the present invention, and FIG. 2b is a schematic diagram of a standard musical score provided by Embodiment 1 of the present invention. After comparison, it can be found that the notes in the circle in FIG. 2a are different from the notes in the corresponding positions in FIG. 2b , that is, the place where the digital score is out of tune. Therefore, it is necessary to modify the notes in the circle in Figure 2a, and modify the notes in the circle to be the same as the notes in the corresponding position in Figure 2b, so as to modify the out-of-tune notes. In the first embodiment of the present invention, the digital music score can be automatically modified according to the difference value, and the difference value can also be displayed to the user, allowing the user to manually modify the voice. In the process of manual tuning, users can manually adjust individual notes in the melody. Compared with the melody rhythm of the standard score, users can manually adjust the rhythm and pitch individually according to their individual needs. The way of manual tuning can be achieved by adjusting the note positions in the staff. You can adjust the notes that are different from the standard score, and you can also adjust the notes of the standard score to achieve a variation melody song based on the original song.

By means of the voice modification method provided in the first embodiment of the present invention, it is possible to correct the situation that the user sings out of tune on the mobile terminal, and it is possible to perform convenient and quick post-modification processing on the audio.

Embodiment 2

Since the local memory of the mobile terminal is small and the number of standard audios stored is small, it is possible that the standard audio cannot be found. In order to solve this technical problem, the second embodiment of the present invention provides a method for audio modification, such as As shown in Figure 3, the following steps may be included:

Step S301, the mobile terminal acquires the user's singing audio.

In step S302, the mobile terminal acquires the characteristics of the audio of the song, and converts the audio of the song into a digital musical score.

Step S303, the mobile terminal uploads the feature and the digital musical score to the cloud.

Step S304, the cloud receives the digital musical score and the features, compares the digital musical score and the standard musical score, and determines the difference between the digital musical score and the standard musical score.

In this step, the cloud receives the digital musical score, obtains a standard musical score with the same characteristics according to the features; compares the digital musical score and the standard musical score, determines the difference between the digital musical score and the standard musical score; and feeds back the difference to the mobile terminal. Therefore, there is no need to cache standard scores locally, freeing up local storage space.

Step S305, the cloud feeds back the difference to the mobile terminal.

Step S306, the mobile terminal receives the difference and corrects the digital musical score according to the difference.

With the method for revising sound provided by the second embodiment of the present invention, the standard musical score can be stored in the cloud without occupying the local resources of the mobile terminal, ensuring that the standard musical score can be found, so as to realize the melding of the digital musical score.

Embodiment 3

An embodiment of the present invention provides a sound-modifying mobile terminal, which can execute the sound-modifying method in the first embodiment. As shown in FIG. 4 , the sound-modifying mobile terminal may include the following modules: a song frequency acquisition module 41, a conversion Module 42 , standard score acquisition module 43 , difference comparison module 44 and score correction module 45 .

The song frequency acquisition module 41 is used to acquire the user's song audio; the conversion module 42 is used to convert the song audio into a digital musical score; the standard musical score acquisition module 43 is used to acquire the characteristics of the song audio, and according to the characteristics, obtain the same characteristics. Standard musical score; the difference comparison module 44 is used to compare the digital musical score and the standard musical score to determine the difference between the digital musical score and the standard musical score; the musical score correction module 45 is used to correct the digital musical score according to the difference.

In the song frequency acquisition module 41, the mobile terminal can acquire the user's song audio through the microphone. The song audio can be dry sound, which is also called naked sound. original vocals. In this embodiment of the present invention, the mobile terminal may be an electronic device having a recording function, an audio storage function, and an audio playback function, such as a mobile phone and a tablet computer.

In the conversion module 42, the audio of the song can be converted into a digital musical score by processing spectrum, power, zero crossing, etc., and the digital musical score can include information such as song speed, melody pitch, tempo, and dynamic relationship.

In the standard musical score obtaining module 43, the standard musical score is a musical score that is completely sung and/or played according to the musical score, which is a musical score that is not out of tune in layman's terms. The audio features of the song may include: song title, original singer name and version, for example, the song name is "Ten Years", the original singer name is "Eason Chan", and the version is a recording studio board. Features of the song audio may also include cover artist names. According to the above features, a standard musical score with the same characteristics can be searched in the local music library of the mobile terminal, and the standard musical score can be the musical score sung by the original singer. The local music library can also store different versions of standard scores sung by a singer, such as studio board, live version, concert version, etc. Generally speaking, the sound quality of the studio version is better than the live version, so , when there are multiple versions of the standard score in the local score, the score with the best sound quality can be selected first, such as the studio score.

In the difference comparison module 44, it can be determined whether the digital musical score is out of tune by comparing the rhythm and pitch of the digital musical score and the standard musical score. Rhythm represents the speed and intensity of music, and the rhythm can include two parts: speed and beat. Therefore, there will be a difference in at least one of tempo, tempo, and pitch between the digital score and the standard score. Specifically, at least one of the tempo, tempo or pitch frequency of the digital musical score and the standard musical score can be compared locally on the mobile terminal to obtain at least one of the tempo difference, tempo difference or pitch frequency difference. If there is no difference between the digital score and the standard score, or the difference in tempo, tempo, or pitch frequency is within the allowable difference range, the user can be fed back a prompt that tuning is not required

In the musical score correction module 45, the digital musical score can be modified locally on the mobile terminal according to the difference, so that there is no difference between the digital musical score and the standard musical score, that is, the out-of-tune digital musical score is corrected. In the embodiment of the present invention, the difference value can be displayed on the staff of the standard musical score according to the speed difference value, the beat difference value and the pitch frequency difference value; the user's correction instruction is received to correct the audio of the song, and the user's correction instruction can be for all The difference is corrected to achieve one-click sound repair, or it can be repaired to some differences, and some differences are retained to achieve personalized sound repair.

With the mobile terminal for voice modification provided by the third embodiment of the present invention, it is possible to correct the situation that the user sings out of tune on the mobile terminal, and it is possible to perform convenient and quick post-modification processing on the audio.

Embodiment 4

Since the local memory of the mobile terminal is small and the number of stored standard audios is small, it is possible that the standard audio cannot be found. To solve this technical problem, as shown in FIG. 5 , the fourth embodiment of the present invention provides a The mobile device for audio modification may include the following:

The mobile terminal 51 and the cloud 52; the mobile terminal 51 includes: a song frequency acquisition module 511, a conversion module 512, a digital music score uploading module 513, and a music score correction module 514;

The cloud 52 includes: a difference comparison module 521 and a difference feedback module 522 .

The song frequency acquisition module 511 is used to acquire the user's singing audio; the conversion module 512 is used to acquire the characteristics of the song audio and convert the song audio into a digital musical score; the digital musical score uploading module 513 is used to upload the features and digital musical scores to the cloud Difference comparison module 521, for receiving digital musical scores and features in the cloud, and comparing the digital musical scores and standard musical scores to determine the difference between the digital musical scores and the standard musical scores; Difference feedback module 522, for feeding back the differences to the mobile terminal; Music score correction module 514 , which receives the differences and corrects the digital score according to the differences.

In the difference comparison module 521, the cloud receives the digital musical score, obtains a standard musical score with the same characteristics according to the features; compares the digital musical score and the standard musical score, determines the difference between the digital musical score and the standard musical score; and feeds back the difference to the mobile terminal. Therefore, there is no need to cache standard scores locally, freeing up local storage space.

In the score correction module 514, a difference value display unit and a correction unit may be included.

The difference value display unit is used to display the difference value on the staff of the standard score according to the speed difference value, the beat difference value and the pitch frequency difference value;

The correction unit is used to receive the correction instruction from the user and correct the audio of the song.

By means of the sound repairing device provided in the fourth embodiment of the present invention, the standard musical score can be stored in the cloud, without occupying the local resources of the mobile terminal, ensuring that the standard musical score can be found, so as to realize the sound repairing of the digital musical score.

The method and device for revising a sound provided by the present invention have been described above in detail. The principles and implementations of the present invention are described with specific examples in this paper. The descriptions of the above embodiments are only used to help understand the present invention. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation and application scope. In summary, the content of this description should not be construed as Limitations of the present invention.

Claims (6)

1. A method of modifying a tone, comprising:

acquiring song audio of a user;

converting the song audio into a digital music score;

acquiring the characteristics of the song audio, and acquiring a standard music score with the same characteristics according to the characteristics;

comparing the digital score with the standard score to determine the difference between the digital score and the standard score;

correcting the digital music score according to the difference;

wherein said modifying said digital score in accordance with said difference comprises:

modifying the digital score to achieve that there is no difference between the digital score and the standard score;

wherein said comparing said digital score to said standard score, determining a difference between said digital score and said standard score, comprises:

comparing at least one of the speed, the beat or the pitch frequency of the digital music score and the standard music score to obtain at least one of a speed difference value, a beat difference value or a pitch frequency difference value;

the step of modifying the digital score in dependence on the difference comprises:

displaying the difference value on a staff of the standard music score according to the speed difference value, the beat difference value and the pitch frequency difference value;

receiving a correction instruction of a user, correcting the song audio, and comprising: receiving an instruction of the user for correcting all the difference values, correcting all the difference values in the digital music score, or receiving manual adjustment of notes displayed on the staff by the user, and correcting the difference values of the notes adjusted by the user;

wherein said receiving manual adjustments by the user to notes displayed on the staff comprises: receiving a manual adjustment by the user of a position of a single note displayed on the staff.

2. The method of claim 1, wherein in the step of obtaining the song audio of the user, the song audio is dry sound.

3. The method of claim 1, wherein said step of obtaining characteristics of said song audio and, depending on said characteristics, obtaining a standard score having the same said characteristics comprises:

and acquiring the name of the song audio and the name of the original singer, and acquiring a corresponding standard music score through the name of the song and the name of the original singer, wherein the standard music score is a digital music score.

4. An apparatus for modifying sound, comprising:

the song frequency acquisition module is used for acquiring song audio of a user;

the conversion module is used for converting the song audio into a digital music score;

the standard music score acquisition module is used for acquiring the characteristics of the song audio and acquiring a standard music score with the same characteristics according to the characteristics;

the difference comparison module is used for comparing the digital music score with the standard music score and determining the difference between the digital music score and the standard music score;

the music score correction module is used for correcting the digital music score according to the difference;

the score correction module is specifically configured to: modifying the digital score to achieve that there is no difference between the digital score and the standard score;

the difference comparison module is specifically configured to compare at least one of speeds, beats or pitch frequencies of the digital music score and the standard music score to obtain at least one of a speed difference, a beat difference or a pitch frequency difference;

the score correcting module comprises:

a difference display unit for displaying the difference on the staff of the standard music score according to the speed difference, the beat difference and the pitch frequency difference;

the correcting unit is used for receiving a correcting instruction of a user and correcting the song audio, and comprises: receiving an instruction of the user for correcting all the difference values, correcting all the difference values in the digital music score, or receiving manual adjustment of notes displayed on the staff by the user, and correcting the difference values of the notes adjusted by the user;

wherein the modifying unit is specifically configured to receive a manual adjustment by the user of a position of a single note displayed on the staff.

5. The apparatus of claim 4, wherein in the song frequency acquisition module, the song audio is dry sound.

6. The apparatus of claim 4, wherein the standard score obtaining module is specifically configured to obtain a song name and an original singer name of the song audio, and obtain a corresponding standard score through the song name and the original singer name, wherein the standard score is a digital score.

Images