KR101975193B1 - Automatic composition apparatus and computer-executable automatic composition method - Google Patents

Abstract

The present invention relates to an automatic composition apparatus and a computer-executable automatic composition method. The automatic composition apparatus comprises: a sound source reception unit receiving sound source including accompaniment and a user song; a melody analysis unit separating the user song from the sound source and analyzing a melody; and an automatic composition unit performing at least one of modification of the accompaniment, modification of the user song, and instrument playing generation of the melody based on the melody. Therefore, the automatic composition apparatus and the computer-executable automatic composition method may provide a sound source composed based on the inputted user song with the accompaniment.

Description

TECHNICAL FIELD [0001] The present invention relates to an automatic composing apparatus and a computer-executable automatic composing method,

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to automatic composing techniques, and more particularly, to an automatic composing apparatus and a computer-executable automatic composing method capable of providing a music composition based on a user song inputted together with accompaniment.

Auto-composing technology automatically records the emerging rogues for music composition, which can help people with low ability to write easily. The conventional automatic composition techniques merely combine simple music fragments rather than actual composition, and it is difficult to provide high-quality results.

Korean Patent No. 10-1191907 (Oct. 10, 2012) relates to an automatic composing system, an automatic composing method using the same, and a recording medium on which the method is recorded. Specifically, the automatic composing system includes a PCM a sound source library unit for extracting the sound source from the sound source library unit and generating a material sound source by compressing the sound source for each genre according to the genre, and a track of the musical instrument set according to the genre on the basis of the material sound source provided by the sound source library unit, And a complex coding unit for encrypting or decrypting the completed sound source.

Korean Patent Laid-Open No. 10-2016-0076775 (2016.07.01) relates to an automatic composition program and system based on input song information. Even if human mental activity on creation is completely excluded, It is possible to provide an automatic composition program capable of generating an output in which the ambience of the song is not exactly a copy of the input original song but is faithfully expressed by applying the Markov chain model theory .

Korea Patent No. 10-1191907 (Oct. 10, 2012) Korean Patent Publication No. 10-2016-0076775 (2016.07.01)

An embodiment of the present invention is to provide an automatic composing apparatus and a computer-executable automatic composing method capable of providing a music composition based on a user song input together with accompaniment accompaniment.

An embodiment of the present invention is to provide an automatic composition device and a computer-executable automatic composition method capable of analyzing a melody by separating a user song from a sound source including an accompaniment and a user song.

An embodiment of the present invention provides an automatic composition device capable of performing at least one of synthesis of a recommended accompaniment based on a melody separated from a sound source, correction of a user's voice, and generation of a musical instrument performance corresponding to a melody, And to provide a composition method.

In an embodiment of the present invention, the automatic composing apparatus includes a sound source receiving unit for receiving a sound source including an accompaniment and a user song, a melody analyzing unit for analyzing the melody by separating the user song from the sound source, And an automatic composition unit for performing at least one of modification of a user song and generation of musical instrument performance of the melody.

The sound source receiving unit may select the accompaniment through user control and receive the user song while the selected accompaniment is being reproduced to synthesize the selected accompaniment and the user song.

The sound source receiver may learn the accompaniment selection history of the user and automatically select or recommend the accompaniment by reflecting at least one of date, time, and environment.

The sound source receiving unit may select or recommend at least one of the style, atmosphere, and genre of the accompaniment by reflecting at least one of an accompaniment selection general trend, a region, a country, and an event for a specific period.

The melody analyzing unit may determine whether a user voice is input from the sound source and an input part of the user voice.

The melody analyzing unit may determine whether or not it is a chorus including solo, duo, and trio from the sound source.

The melody analyzer may perform at least one of pitch extraction, beats per minute (BPM) estimation, composition estimation, user gender estimation, user atmosphere estimation, and user style estimation for the user song.

The automatic composer may create a new accompaniment based on at least one of a pitch, a BPM, a composition, a user gender, a user atmosphere, and a user style for the user song to recommend the new accompaniment as a modification of the accompaniment.

The automatic composition unit may correct at least one of a pitch, a pitch, and a pitch of the user song.

The automatic composition unit may perform the correction of the user song through a voice transformation filter.

The automatic composition unit may determine an instrument corresponding to the sound related to the user song and synthesize the melody to the accompaniment by playing the melody with the determined instrument.

The automatic composing apparatus may further include an automatic composition completion unit for automatically completing a composition of the sound source by selecting one of modification of the accompaniment, modification of the user song, and creation of musical instrument performance of the melody according to user's selection .

Among the embodiments, a computer-executable automatic composition method includes a sound source receiving step of receiving a sound source including an accompaniment and a user song, a melody analysis step of analyzing the melody by separating the user song from the sound source, A modification of the user song, and a musical instrument performance creation of the melody.

The melody analyzing step may include analyzing the melody of the accompaniment based on at least one of a time difference, an intensity difference between the speaker output signal and the microphone receiving signal related to the accompaniment, a size, a distribution, a tendency, And the user song.

The disclosed technique may have the following effects. It is to be understood, however, that the scope of the disclosed technology is not to be construed as limited thereby, as it is not meant to imply that a particular embodiment should include all of the following effects or only the following effects.

The automatic composing apparatus and the computer-executable automatic composing method according to an embodiment of the present invention can analyze a melody by separating a user song from a sound source including an accompaniment and a user song.

The automatic composing apparatus and the computer-executable automatic composing method according to an embodiment of the present invention can perform at least one of synthesizing a recommendation accompaniment based on a melody separated from a sound source, correcting a user's voice, and generating a melody musical instrument performance .

1 is a view for explaining an automatic composition system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating the automatic composer of FIG. 1. FIG.
FIG. 3 is a flowchart illustrating a process of performing automatic composition in the automatic composition apparatus shown in FIG. 1. FIG.
FIG. 4 is a diagram illustrating a process of receiving an accompaniment and a user song on the user terminal of FIG. 1;
5 is a diagram for explaining a process of performing automatic composition in the automatic composition apparatus shown in FIG.
FIG. 6 is an exemplary diagram illustrating an embodiment of an accompaniment selection interface provided to a user terminal in the tone generator receiving unit shown in FIG. 2. FIG.

The description of the present invention is merely an example for structural or functional explanation, and the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, the embodiments are to be construed as being variously embodied and having various forms, so that the scope of the present invention should be understood to include equivalents capable of realizing technical ideas. Also, the purpose or effect of the present invention should not be construed as limiting the scope of the present invention, since it does not mean that a specific embodiment should include all or only such effect.

Meanwhile, the meaning of the terms described in the present application should be understood as follows.

The terms " first ", " second ", and the like are intended to distinguish one element from another, and the scope of the right should not be limited by these terms. For example, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

It is to be understood that when an element is referred to as being "connected" to another element, it may be directly connected to the other element, but there may be other elements in between. On the other hand, when an element is referred to as being "directly connected" to another element, it should be understood that there are no other elements in between. On the other hand, other expressions that describe the relationship between components, such as "between" and "between" or "neighboring to" and "directly adjacent to" should be interpreted as well.

It is to be understood that the singular " include " or " have " are to be construed as including the stated feature, number, step, operation, It is to be understood that the combination is intended to specify that it does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

In each step, the identification code (e.g., a, b, c, etc.) is used for convenience of explanation, the identification code does not describe the order of each step, Unless otherwise stated, it may occur differently from the stated order. That is, each step may occur in the same order as described, may be performed substantially concurrently, or may be performed in reverse order.

The present invention can be embodied as computer-readable code on a computer-readable recording medium, and the computer-readable recording medium includes all kinds of recording devices for storing data that can be read by a computer system . Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like. In addition, the computer-readable recording medium may be distributed over network-connected computer systems so that computer readable codes can be stored and executed in a distributed manner.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Commonly used predefined terms should be interpreted to be consistent with the meanings in the context of the related art and can not be interpreted as having ideal or overly formal meaning unless explicitly defined in the present application.

1 is a view for explaining an automatic composition system according to an embodiment of the present invention.

Referring to FIG. 1, the automatic composition system 100 may include a user terminal 110, an automatic composer 130, and a database 150.

The user terminal 110 may be a smartphone, a notebook computer, or a computer. The user terminal 110 corresponds to a computing device that receives a user's song and can automatically reproduce the music source, . ≪ / RTI > The user terminal 110 may be connected to the automatic composing device 130 via a network and at least one user terminal 110 including the user terminal 1 10a to the user terminal n 110n may be connected to the automatic composer 130 ). The user terminal 110 may include a microphone capable of receiving a user song, a speaker capable of playing back an accompaniment or a sound source.

The automatic composing device 130 can receive a sound source including an accompaniment and a user song from the user terminal 110 via a network and automatically perform composition based on the received sound source and provide it to the user terminal 110 Or a server corresponding to the program. The automatic composer 130 may be wirelessly connected to the user terminal 110 via Bluetooth, WiFi, or the like, and may exchange data with the user terminal 110 via the network.

The automatic composer 130 may be embodied including a database 150 and may be implemented separately from the database 150. [ When implemented independently of the database 150, the automatic composer 130 may be connected to the database 150 in a wired or wireless manner to transmit and receive data.

The database 150 is a storage device that stores various information that the automatic composing device 130 uses to provide an automatically composed sound source to the user terminal 110. [ For example, the database 150 may store information about various accompaniment, musical scores, musical instruments, and melodies, and may include information such as an accompaniment selection history for each user, a general trend for selecting an accompaniment for a specific period, Statistical information on the atmosphere and style, and information regarding the voice deformation filter, and may store various types of information necessary for performing a music composition by receiving a sound source and providing the music composition.

The database 150 may include at least one independent sub-database that stores information belonging to a specific range, and at least one independent sub-database may be configured as an integrated database integrated into one. In the case of at least one independent sub-database, each of the sub-databases may be wirelessly connected via Bluetooth, WiFi, or the like and may exchange data with each other via the network. In the case of an integrated database, it may include a control unit for integrating each of the sub-databases into one and managing data exchange and control flow between the sub-databases.

FIG. 2 is a block diagram illustrating the automatic composer of FIG. 1. FIG.

2, the automatic composition device 130 may include a sound source receiving unit 210, a melody analyzing unit 220, an automatic composition unit 230, an automatic composition completion unit 240, and a control unit 250 .

The sound source receiving unit 210 may receive a sound source including an accompaniment and a user song from the user terminal 110. The sound source receiving unit 210 can independently receive an accompaniment and a user song from the user terminal 110, and can directly receive a sound source file in which an accompaniment and a user song are combined. In one embodiment, the tone generator 210 may receive the accompaniment stored in the user terminal 110 and may receive the accompaniment stored in the database 150. [

In one embodiment, the tone generator 210 may select an accompaniment through user control and receive a user song while the selected accompaniment is being reproduced, thereby synthesizing the selected accompaniment and the user song. More specifically, the automatic composing device 130 can reproduce the accompaniment selected by the user via the user terminal 110. [ The sound source receiving unit 210 may receive and store a user song while the accompaniment is being reproduced through the user terminal 110. [ The sound source receiving unit 210 may generate a sound source by synthesizing the stored user song with accompaniment, and may store the sound source in the database 150.

In one embodiment, the sound source receiving unit 210 may receive both the accompaniment and the user song, which are reproduced through the user terminal 110, to generate a sound source. In one embodiment, the sound source receiving unit 210 may receive the humming of the user as a song of the user.

In one embodiment, the tone generator 210 may learn the accompaniment selection history of the user and automatically select or recommend the accompaniment by reflecting at least one of the date, time, and environment. The sound source receiving unit 210 may provide the user terminal 110 with an accompaniment selection interface through which the user can receive a selection of a specific accompaniment.

When receiving the accompaniment selection of the user, the sound source receiving unit 210 may learn through a general learning algorithm and store it in the database 150. In one embodiment, the sound source receiving unit 210 can extract a user selection history for a specific period from the database 150, and can perform learning based on the extracted user selection history.

It is possible to automatically select or recommend the accompaniment by reflecting at least one of the date, time, and environment of the current time based on the result of learning the accompaniment selection history of the user of the tone generator 210. The automatic composing device 130 can automatically or manually set items to be reflected in date, time, and environment, and combinations thereof, and is not necessarily limited to this, and can be set by adding reflection items or adding new combinations. When the accompaniment is automatically selected, the sound source receiving unit 210 may provide an interface through which the user may select whether to play the selected accompaniment. If the accompaniment is automatically recommended, the sound source receiving unit 210 may select any one of the at least one recommended accompaniment It can provide an interface that can be.

In one embodiment, the tone generator 210 receives at least one of an accompaniment selection general trend, a region, a country, and an event for a specific period. The tone, the mood, and the genre of the accompaniment, Or at least one of them may be selected or recommended.

Here, the accompaniment selection general trend may mean a tendency or fashion for users of a particular area to select an accompaniment for a certain period of time. The event may correspond to a local or national event, holiday, or anniversary based on the location of the current user terminal 110. The event may correspond to an international event not related to the location, Lt; RTI ID = 0.0 > events. ≪ / RTI >

The sound source receiving unit 210 can receive the current location information of the user terminal 110 using the GPS included in the user terminal 110 and can determine the current location and the country based on the location information. The sound source receiving unit 210 may provide an interface by which the style, atmosphere, and genre of the accompaniment can be independently selected.

In one embodiment, the sound source receiving unit 210 provides an interface for selecting or recommending at least one of the style of accompaniment, accompaniment, atmosphere, and genre to the user terminal 110, The size of the selection button can be dynamically determined according to the order of the highest ranking. For example, the sound source receiving unit 210 may maximize the button size of the most-selected accompaniment based on the accompaniment selection history of the user while recommending the accompaniment, and provide the same to the user terminal 110.

The melody analyzer 220 may analyze the melody by separating the user song from the sound source received through the sound source receiver 210. [ The melody analyzer 220 can separate user songs by removing the accompaniment received from the received music source. The melody analyzer 220 can analyze the melody using the user song without separating the melody when the accompaniment and the user song are independently received through the melody receiving unit 210. [

In one embodiment, the melody analyzer 220 may generate at least one of a time difference, an intensity difference, a frequency-dependent size, a distribution, a tendency, and a signal shape distortion model of a speaker output signal between a speaker output signal and a microphone reception signal concerning an accompaniment Can separate the accompaniment and the user song from the sound source.

In one embodiment, the melody analyzer 220 may determine whether to input a user voice from a sound source and an input portion of a user voice. The melody analyzing unit 220 can receive the accompaniment reproduced through the user terminal 110 together with the user's song, and determine whether the user's voice is input from the corresponding sound source based on the reproduced accompaniment and the received accompaniment, Can be determined.

In one embodiment, the melody analyzer 220 can determine from the sound source whether it is a chorus including solo, duo, and trio. The melody analyzer 220 can separate the user song from the sound source and then analyze the separated user song to determine whether or not to chorus. The melody analyzer 220 can determine whether the chorus includes a specific number of voices, including a duo or a trio, if the chorus is determined through a sound source analysis.

In one embodiment, the melody analyzer 220 may perform at least one of pitch extraction, beats per minute (BPM) estimation, composition estimation, user gender estimation, user mood estimation, and user style estimation for a user song. The melody analyzer 220 can extract the characteristics of the sound source from the sound source, extract the pitch of the sound source based on the extracted features of the sound source, and determine the BPM, the composition, the user's sex, Style can be estimated.

The automatic composition unit 230 may perform at least one of modification of the accompaniment, modification of the user's song, and creation of musical instrument performance of the melody based on the melody analyzed from the sound source through the melody analyzer 220. [ The automatic composer 230 may provide an interface to the user terminal 110 so that the user can be selected for modification of the accompaniment, modification of the user song, and creation of the musical instrument performance of the melody.

In one embodiment, the automatic composer 230 generates a new accompaniment based on at least one of a pitch, a BPM, a composition, a user gender, a user mood, and a user style for a user song to provide a new accompaniment Recommended. The automatic composer 230 may provide an interface to the user terminal 110 to listen to the new accompaniment and to confirm the modification to the new accompaniment of the existing accompaniment.

In one embodiment, the automatic composition unit 230 may correct at least one of a pitch height, a note length, and a negative pitch of a user song. The automatic composition unit 230 may provide the user terminal 110 with an interface capable of correcting at least one of a pitch height, a sound pitch, and a negative pitch of a user song. The interface may include an input function that includes an estimated value of each of the pitch height, pitch length, and negative pitch with respect to the entire sound source section, and can input a correction value.

In one embodiment, the automatic composition unit 230 can perform correction of a user song through a voice transformation filter. The automatic composer 230 may provide an interface to the user terminal 110 to select a particular voice transformation filter. The interface may include an output function to listen to a song in real time with a particular voice transformation filter applied.

In one embodiment, the automatic composer 230 may determine an instrument corresponding to the notes associated with the user song and play the melody with the determined instrument to synthesize the accompaniment. The automatic composition unit 230 can automatically determine the musical instrument relating to the notes relating to the user song and can receive input through the user terminal 110. [ The automatic composition unit 230 can generate a play sound played according to the analyzed melody through the melody analyzer 220 with the determined musical instrument, and synthesize the generated play sound to the accompaniment. The automatic composition unit 230 can receive a selection of an instrument to be used for generating a play sound from a user and provide an interface for listening to a sound source synthesized with a play sound and an accompaniment generated through the selected musical instrument to the user terminal 110 ).

The automatic composition completion unit 240 may automatically select a musical composition of the melody, modify the accompaniment, modify the user's song, or generate the musical instrument performance of the melody according to the user's selection. The automatic composition completion unit 240 may provide the user terminal 110 with an interface through which the user's selection can be input. The automatic composition completion unit 240 separates the user song from the sound source according to the selection of the user input from the user terminal 110, analyzes the melody, and automatically completes the composition according to the user's selection.

More specifically, the automatic composition completion unit 240 generates a new accompaniment based on at least one of a pitch, a BPM, a composition, a user gender, a user atmosphere, and a user style relating to a user song when the user selects modification of the accompaniment So that a new sound source can be generated by synthesizing with the user's song.

The automatic composition completion unit 240 may generate a new sound source by correcting at least one of a pitch height, a sound length, and a negative shake of the user song and synthesizing it with the accompaniment when the user selects the modification of the user song. In addition, the automatic composition completion unit 240 may generate a new sound source by performing correction of the user's song through the voice distortion filter, and then synthesizing the user song with the accompaniment.

The automatic composition completion unit 240 automatically determines an instrument corresponding to the sound of the user's song when the user selects to produce the instrument performance of the melody, synthesizes the melody to the accompaniment by the determined instrument, A new sound source can be created.

The control unit 250 controls the overall operation of the automatic composing apparatus 130 and controls the control flow and data between the sound source receiving unit 210, the melody analyzing unit 220, the automatic composing unit 230, You can manage the flow.

FIG. 3 is a flowchart illustrating a process of performing automatic composition in the automatic composition apparatus shown in FIG. 1. FIG.

Referring to FIG. 3, the automatic composer 130 may receive a sound source including an accompaniment and a user song through the sound source receiving unit 210 (step S310). The automatic composer 130 can analyze the melody by separating the user song from the sound source through the melody analyzer 220 (step S330). The automatic composer 130 can perform at least one of modification of the accompaniment based on the melody, automatic modification of the user's song, and generation of musical instrument performance of the melody through the automatic composition unit 230 (step S350).

In one embodiment, the automatic composing device 130 selects one of the modification of the accompaniment, the modification of the user's song, and the creation of the musical instrument performance of the melody in accordance with the user's selection through the automatic composition completion section 240, .

FIG. 4 is a diagram illustrating a process of receiving an accompaniment and a user song on the user terminal of FIG. 1;

Referring to FIG. 4, a user input 450 may be received on the user terminal 410 via an interface for selecting an accompaniment. The automatic composer 130 may automatically select or recommend an accompaniment through the sound source receiving unit 210 (430). A user song can be input through the microphone of the user terminal 410 while the accompaniment is played through the speaker of the user terminal 410 and the accompaniment and the user song can be recorded and stored in the user terminal 410. [ The recorded sound source can be reproduced by the user terminal 410 and confirmed by the user. The automatic composer 130 may receive the recorded sound source from the user terminal 410 through the network through the sound receiving unit 210. [

5 is a diagram for explaining a process of performing automatic composition in the automatic composition apparatus shown in FIG.

Referring to FIG. 5, the automatic composing device 130 can separate the accompaniment and the user song from the sound source through the melody analyzer 510. The melody analyzing unit 510 analyzes the melody of the accompaniment and the microphone reception signal based on at least one of the time difference, the intensity difference, the size, distribution, trend, and signal shape distortion model of the speaker output signal, You can separate your songs. The melody analyzer 510 can analyze the melody based on the separated user songs.

The automatic composer 130 can perform automatic composing through the automatic composer 530. [ More specifically, the automatic composition unit 530 can perform at least one of modification of an accompaniment, modification of a user song, and generation of musical instrument performance of a melody based on a melody separated from the sound source by the melody separation unit 510. [

The automatic composition unit 530 can recommend the accompaniment based on the analyzed melody by correcting the accompaniment, and can perform the automatic composition by synthesizing the recommendation accompaniment with the user song. The automatic composer 530 can correct the user's voice based on the melody analyzed as a modification of the user's song and synthesize the synthesized voice with the accompaniment to perform automatic composing. The automatic composition unit 530 can generate a play sound in which the melody is played on the musical instrument based on the melody analyzed by the musical instrument performance creation of the melody, and can perform automatic composition by combining with the accompaniment. The automatic composing device may provide an interface to the user terminal 110 to reproduce the sound source generated by the automatic composition so that the user can directly confirm the automatically composed sound source.

FIG. 6 is an exemplary diagram illustrating an embodiment of an accompaniment selection interface provided to a user terminal in the tone generator receiving unit shown in FIG. 2. FIG.

Referring to FIG. 6, the sound source receiving unit 210 may provide an interface to the user terminal 110 through which the user can select an accompaniment. The sound source receiving unit 210 may automatically provide buttons 610 and 630 that can select at least one of the recommended accompaniment, accompaniment style, atmosphere, and genre. In one embodiment, the sound source receiving unit 210 may change the design including the shape, color, size, and the like of the button to provide various changes to the user terminal 110. For example, the sound source receiving unit 210 may embody a button shape in a rectangular shape, an area in a lattice pattern, and the like, and the present invention is not limited thereto.

In one embodiment, the sound source receiving unit 210 may change the size of the button based on the priority according to a specific criterion and provide the changed size to the user terminal 110. In FIG. 6, the accompaniment selection button 610 of a genre having a high preference can be displayed larger than the accompaniment selection button of a genre having a low preference. In addition, the accompaniment selection button 630 of the atmosphere having the low preference can be displayed smaller than the accompaniment selection button of the atmosphere having the high preference.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the present invention as defined by the following claims It can be understood that

100: Automatic composition system
110: user terminal 130: automatic composer
150: Database
210: Sound source receiving unit 220: Melody analyzing unit
230: Automatic composer 240: Automatic composer
250:
410: user terminal 430: automatic selection or recommendation of accompaniment
450: user input
510: melody analyzing unit 530: automatic composition unit
610: Select button with high preference
630: Select button with low affinity

Claims (14)

A sound source receiving unit for receiving a sound source including an accompaniment and a user song;
A melody analyzer for analyzing the melody by separating the user song from the sound source;
An automatic composition unit for performing at least one of modification of the accompaniment based on the melody, modification of the user song, and creation of musical instrument performance of the melody; And
And an automatic composition completion unit for automatically completing a composition of the sound source by selecting at least one of modification of the accompaniment, modification of the user song, and creation of musical instrument performance of the melody according to a user's selection,
The automatic composition completion unit
Synthesizing the modified accompaniment and the user song when the correction of the accompaniment is selected, synthesizing the modified user song and the accompaniment when the modification of the user song is selected, Synthesizing the musical instrument performance of the melody, the accompaniment and the song of the user,
When the plural of the accompaniment is modified, the user song is modified, and the plurality of musical instrument performances of the melody is selected, the modified accompaniment, the modified user song, and the musical instrument performance of the generated melody are synthesized .
The apparatus of claim 1, wherein the sound source receiving unit
Selects the accompaniment through user control and receives the user song while the selected accompaniment is being played back to synthesize the selected accompaniment and the user song.
3. The apparatus of claim 2, wherein the sound source receiving unit
And automatically selects or recommends the accompaniment based on at least one of a date, a time, and an environment by learning the accompaniment selection history of the user.
3. The apparatus of claim 2, wherein the sound source receiving unit
And selecting or recommending at least one of the style, atmosphere, and genre of the accompaniment based on at least one of an accompaniment selection general trend, a region, a country, and an event for a specific period.
The apparatus of claim 1, wherein the melody analyzer
And determining whether to input a user voice from the sound source and an input portion of the user voice.
The apparatus of claim 1, wherein the melody analyzer
And judges whether or not a chorus including solo, duo, and trio is to be chorus from the sound source.
The apparatus of claim 1, wherein the melody analyzer
And performing at least one of pitch extraction, beats per minute (BPM) estimation, composition estimation, user gender estimation, user atmosphere estimation, and user style estimation on the user song.
8. The apparatus of claim 7, wherein the automatic composer
Generating a new accompaniment based on at least one of a pitch, a BPM, a composition, a user gender, a user atmosphere, and a user style for the user song to recommend the new accompaniment as a modification of the accompaniment. .
8. The apparatus of claim 7, wherein the automatic composer
And corrects at least one of a pitch height, a sound length and a negative shake of the user song.
The apparatus of claim 9, wherein the automatic composition unit
And performs a correction of the user song through a voice transformation filter.
8. The apparatus of claim 7, wherein the automatic composer
Determines an instrument corresponding to the sound related to the user song, and synthesizes the melody to the accompaniment by playing the melody with the determined musical instrument.
delete A sound source receiving step of receiving a sound source including an accompaniment and a user song;
A melody analyzing step of analyzing the melody by separating the user song from the sound source;
An automatic composition step of performing at least one of modification of the accompaniment based on the melody, modification of the user song, and generation of musical instrument performance of the melody; And
Selecting at least one of modification of the accompaniment, modification of the user song, and creation of musical instrument performance of the melody according to a user's selection, and automatically completing the composition of the sound source,
The step of automatically composing the music source
Synthesizing the modified accompaniment and the user song when the correction of the accompaniment is selected, synthesizing the modified user song and the accompaniment when the modification of the user song is selected, Synthesizing the musical instrument performance of the melody, the accompaniment and the song of the user,
Synthesizing the accompaniment, the modified user song, and the musical instrument performance of the generated melody in accordance with the selection, when the plurality of the musical instrument performance is generated during the modification of the accompaniment, the modification of the user song, Lt; RTI ID = 0.0 > of: < / RTI >
14. The method of claim 13, wherein the melody analyzing step
The accompaniment and the user song from the sound source based on at least one of a time difference, an intensity difference between the speaker output signal and a microphone receive signal regarding the accompaniment, a size, a distribution, a tendency, and a signal shape distortion model of the speaker output signal, Said method comprising the steps of:

Images