JP2004333611A - Automatic accompaniment generating device and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To automatically generate an accompaniment on which the climax tendencies of a piece of music are reflected. <P>SOLUTION: According to a variation type allocation rule stored corresponding to an accompaniment style, accompaniment patterns to be allocated to respective sections are determined on the basis of the detected upsurges of the piece of music. The variation type allocation rule is data wherein specified data specification information for specifying a accompaniment pattern to be allocated to a specified section of the piece of music is defined by the tendencies of upsurges of the piece of music. The music structure of acquired musical piece data is analyzed to detect the upsurges of the piece of music by a plurality of divided sections. According to a variation type allocation rule corresponding to a selected accompaniment style, accompaniment patterns to be allocated to the respective sections are determined on the basis of the upsurges of the piece of music. Consequently, even when the number of accompaniment patterns which can be used for the selected accompaniment style is different from the number of kinds of upsurges of the piece of musical, an accompaniment on which the tendencies of upsurges of the piece of music are correctly reflected can automatically be generated. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to an automatic accompaniment generation device and a program for analyzing music data, which is performance information of a music such as a melody, and automatically generating an accompaniment for the music based on the music data. In particular, even when using an accompaniment style in which the number of accompaniment patterns that can be assigned to each section is different, an automatic accompaniment that can automatically generate an accompaniment that correctly reflects the climax of the music in each section. The present invention relates to a generation device and a program.
[0002]
[Prior art]
[Patent Document 1] Japanese Patent No. 3327188
[Patent Document 2] Japanese Patent No. 2806351
In an electronic musical instrument, a sequencer, or the like, when generating automatic accompaniment data required for performing automatic accompaniment, the accompaniment style data is referred to. The accompaniment style data is data defined assuming a performance style (accompaniment style) of a music genre such as rock and pop, and includes a plurality of types of accompaniment patterns (also referred to as section data). Examples of the accompaniment pattern included in the accompaniment style data include, for example, main section data such as “Main A”, “Main B”, and “Main C”, which are mainly played in the music, and introductory music in the music. There are intro section data such as “Intro A” and “Intro B” played in the part, and ending section data such as “Ending A” and “Ending B” played in the ending part of the music. Each accompaniment pattern is composed of, for example, setting information including the name (type) of the section data, the number of measures, and the like, and pattern data including a performance event and a sounding timing that are the source of the actual accompaniment.
[0003]
2. Description of the Related Art Conventionally, there has been known an apparatus that automatically generates, for example, automatic accompaniment data for performing accompaniment corresponding to a music based on analysis of music data that is performance information of the music such as a melody. For example, in the invention described in Patent Literature 1, the music data is analyzed and the chord progression sequence and the section data sequence in the automatic accompaniment data (that is, the section data of the song data such as intro A, main A, ending A, etc.) Line) can be automatically generated. Further, in the invention described in Patent Document 2, when the music data is analyzed and the section data string is automatically generated, the determination of the variation type, which is data designation information for designating section data (accompaniment pattern), is performed. Is performed, and section data defining pattern data corresponding to the climax of the music can be allocated from one or a plurality of section data that can be allocated to each section. For example, in a main section in which two types of section data having variation types of “type A” and “type B” are prepared, as a result of analysis of music data, two types of “central” and “flashy” tend to rise. If it is detected, if it is detected as "Normal", the section data "Main A" of the variation type "Type A" for the main section, and if it is detected as "Fancy", it will be Thus, the section data "main B" of the variation type "type B" is respectively assigned.
[0004]
[Problems to be solved by the invention]
By the way, the number of accompaniment patterns (number of variation types) that can be assigned to each section type constituting the automatic accompaniment data differs for each accompaniment style. However, in the conventional automatic accompaniment generation device, the control is performed on the assumption that the number of accompaniment patterns that can be assigned to each section type constituting the automatic accompaniment data is common to all accompaniment styles. However, when using accompaniment styles in which the number of accompaniment patterns that can be assigned to each section type is different, inconvenience has occurred. That is, when the accompaniment style in which the number of accompaniment patterns that can be assigned to each section is different, an accompaniment pattern corresponding to the variation type automatically assigned to the detected section is detected. There is a possibility that it does not match the trend of music excitement. If an accompaniment pattern of a variation type that does not match the detected song's excitement tendency is assigned, that is, depending on the accompaniment style used, the automatic accompaniment will not match the song's excitement tendency and the sharpness of the automatic accompaniment will change Occurs. In addition, it is inconvenient because the atmosphere of the melody and the automatic accompaniment no longer match. For this reason, conventionally, the user must check the climax of each section of the accompaniment style to be used and perform an operation in consideration of the accompaniment style to be used, or automatically assign a variation type. The user had to perform an operation of individually changing to a variation-type accompaniment pattern that is safe to hear later, but it is troublesome and troublesome for the user to manually perform such an operation. There was a point.
[0005]
The present invention has been made in view of the above points, and even when using an accompaniment style in which the number of accompaniment patterns that can be assigned to each section is different, regardless of the number of types of automatically detected music swelling tendencies. It is an object of the present invention to provide an automatic accompaniment generation device and a program capable of automatically generating an accompaniment suited to the ambience of a tune without having to do so.
[0006]
[Means for Solving the Problems]
The automatic accompaniment generation device according to the present invention analyzes the music structure of the acquired music data, divides the music data into a plurality of sections, and sets at least predetermined data, which is data for automatic accompaniment, for each of the plurality of divided sections. An automatic accompaniment generation device that generates automatic accompaniment data corresponding to the music data by assigning the accompaniment pattern of the music data. Storage means for storing, in accordance with each predetermined accompaniment style, variation type assignment rules defined for each undulation tendency; selecting means for selecting an accompaniment style to be used; and a plurality of sections divided from the acquired music data Detecting means for detecting the undulation of the music every time; and a variation type assignment rule corresponding to the selected accompaniment style. Deciding means for deciding an accompaniment pattern to be assigned to each section in accordance with the ups and downs of the detected music, wherein the number of accompaniment patterns available in the selected accompaniment style and the When the number of types of undulations is different, automatic accompaniment data for performing accompaniment along the undulation of the music is generated based on the accompaniment pattern determined by the accompaniment pattern determination means.
[0007]
According to the present invention, the accompaniment pattern to be assigned to each section is determined according to the undulation of the detected music piece, based on the variation type assignment rules stored corresponding to the predetermined accompaniment style. The variation type assignment rule is data that defines predetermined data specifying information for specifying an accompaniment pattern to be assigned to a predetermined section of a song for each undulation tendency of the song, and is stored so as to correspond to each predetermined accompaniment style. Is done. The music data of the acquired music data is analyzed to divide the music data into a plurality of sections, and the undulation of the music is detected for each of the plurality of divided sections. Then, based on the variation type assignment rule corresponding to the selected accompaniment style, an accompaniment pattern to be assigned to each section is determined according to the undulation of the detected music. In this way, even when the number of available accompaniment patterns in the selected accompaniment style is different from the number of detected undulation types of the music, the automatic accompaniment data for performing the accompaniment along the undulation of the music is generated. . That is, even when using an accompaniment style in which the number of accompaniment patterns that can be assigned to each section is different, it is possible to automatically generate an accompaniment that correctly reflects the climax of the music in each section.
[0008]
The invention can be constructed and implemented not only as a device invention, but also as a method invention. Further, the present invention can be implemented in the form of a program of a computer or a processor such as a DSP, or can be implemented in the form of a storage medium storing such a program.
[0009]
Embodiments of the present invention will be described below in detail with reference to the accompanying drawings.
[0010]
FIG. 1 is a block diagram of a hardware configuration showing an embodiment of the entire configuration of the automatic accompaniment generation device according to the present invention. An example of a hardware configuration of the automatic accompaniment generating apparatus is configured by using a computer, in which predetermined music data is analyzed and accompaniment (in detail, automatic accompaniment data) suitable for a music atmosphere based on the music data is generated. The process of automatic generation is performed by a computer executing software including a predetermined control program for realizing “automatic accompaniment generation process”. In the “automatic accompaniment generation processing” (see FIG. 3), the section configuration of the music is automatically determined by analyzing predetermined music data to generate a section data string and to detect the climax of the music. By determining a variation type of an accompaniment pattern (section data) to be assigned to each section of the automatically determined section data sequence from a variation type determination table (see FIG. 2) based on the detected climax of the music, Automatic accompaniment data necessary for performing automatic accompaniment is generated. At the time of actual accompaniment performance, pattern data of an accompaniment pattern (section data) corresponding to each section arranged in the section data sequence is read from the generated automatic accompaniment data, and the accompaniment is automatically played. In this way, an accompaniment suitable for the atmosphere of the music such as a melody is automatically generated. Of course, such "automatic accompaniment generation processing" is not limited to the form of computer software, but can also be implemented in the form of a microprogram processed by a DSP (Digital Signal Processor), and is not limited to this type of program. The present invention may be implemented in the form of a dedicated hardware device including a discrete circuit or an integrated circuit or a large-scale integrated circuit.
[0011]
The automatic accompaniment generation apparatus shown in this embodiment is controlled by a microcomputer including a microprocessor unit (CPU) 1, a read-only memory (ROM) 2, and a random access memory (RAM) 3. The CPU 1 controls the operation of the entire automatic accompaniment generation device. The ROM 1, the RAM 3, the communication interface (I / F) 4, the input operation unit 5, the display unit 6, the external storage device 7, and the sound source 8 are transmitted to the CPU 1 via a communication bus 1D (for example, a data and address bus). It is connected. The ROM 2 stores various control programs (for example, an automatic accompaniment generation process (see FIG. 3 described later) and the like) and various data (for example, a variation type determination table (see FIG. 2 described later) and the like) executed or referred to by the CPU 1. Store. The RAM 3 is used as a working memory for temporarily storing various data generated when the CPU 1 executes a predetermined program, or as a memory for temporarily storing a program currently being executed and data related thereto. You. A predetermined address area of the RAM 3 is assigned to each function and used as a register, a flag, a table, a memory, and the like.
[0012]
The communication interface (I / F) 4 is connected to a wired or wireless communication network such as a LAN, the Internet, and a telephone line, and is connected to an external device 4A and the like via the communication network. This is an interface for taking control programs and various data into the main body of the automatic accompaniment generation device. Such a communication interface 4 may comprise both wired or wireless, not both. The input operation unit 5 is used to select a tune (specifically, music data) for which an automatic accompaniment is to be generated, to set a tone color and an accompaniment style to be used for the accompaniment, or to set the number of types of singing tendencies of the automatically detected tune. Switches (operators) for performing various instructions. Of course, the input operation unit 5 also includes various operation devices such as a numeric keypad for inputting numerical data, a keyboard for inputting character data, and a mouse used for operating a predetermined pointing device displayed on the display 6A. You may go out. The display unit 6 displays a list of accompaniment style names, song names attached to song data, variation type determination tables, and the like on a display 6A constituted by, for example, a liquid crystal display panel (LCD), a CRT, or the like. And other information.
[0013]
The external storage device 7 stores a control program, various data, and the like, similarly to the ROM 2 described above. When the control program is not stored in the ROM 2, the control program is stored in the external storage device 7 (for example, a hard disk), and is read into the RAM 3 so that the control program is stored in the ROM 2. Similar operations can be performed by the CPU 1. By doing so, it is possible to easily add a control program or upgrade the version. Note that the external storage device 7 is not limited to a hard disk (HD), and is a removable disk such as a flexible disk (FD), a compact disk (CD-ROM / CD-RAM), a magneto-optical disk (MO), or a DVD (Digital Versatile Disk). It may be a storage device using various types of external recording media. Alternatively, it may be a semiconductor memory or the like.
[0014]
The tone generator 8 is capable of simultaneously generating musical tone signals on a plurality of channels. The tone generator 8 receives various pieces of performance information such as music data and automatic accompaniment data provided via the communication bus 1D, based on the performance information. Generates a tone signal. A tone signal generated from the sound source 8 is generated by a sound system 8A including an amplifier, a speaker, and the like. A predetermined effect may be applied to the tone signal generated from the sound source 8 using an effect circuit or the like (not shown). The format of the music data and the automatic accompaniment data may be a digitally encoded format such as a MIDI format, or may be a waveform sampled data format such as PCM, DPCM, and ADPCM. As the configuration of the sound source 8 and the sound system 8A, any conventional configuration may be used. For example, the sound source 8 may adopt any of various tone synthesis methods such as FM, PCM, physical model, and formant synthesis, may be constituted by dedicated hardware, or may be constituted by software processing by the CPU 1. Is also good.
[0015]
The above-described automatic accompaniment generation apparatus is not limited to the one in which the input operation unit 5, the display 6A, the sound source 8 and the like are built in one apparatus main body, but each is separately configured and has a communication means such as a MIDI interface and various networks. It is needless to say that the apparatus may be configured so as to connect each apparatus by using the apparatus. Furthermore, the apparatus to which the automatic accompaniment generation apparatus according to the present invention is applied can be applied to any form of apparatus / equipment such as an electronic musical instrument, a personal computer, a portable communication terminal such as a PDA or a mobile phone, or a karaoke apparatus or a game apparatus. May be applied. When applied to a portable communication terminal, not only the case where the specified function is completed only with the terminal, but also a part of the function is provided on the server side, and the predetermined function is realized as the whole system consisting of the terminal and the server You may make it.
[0016]
Next, a plurality of data is stored in advance in the ROM 2, the RAM 3, the external storage device 7, or the like, and is referred to when determining a variation type of an accompaniment pattern (section data) to be assigned to each section when generating automatic accompaniment data. A certain variation type determination table will be described. FIG. 2 is a conceptual diagram showing one embodiment of the data structure of the variation type determination table. This variation type determination table is prepared for each number of types of music swelling tendency, such as a preset type or a user-set one. For example, there are two types of song swelling tendencies: "normal" and "flashy", and four types of "weak", "normal", "flashy" and "powerful". A variation type determination table corresponding to the number of types is prepared in advance. In FIG. 2 shown here, a variation type determination table corresponding to the case where the number of types of music swelling tendency is “normal” and “flashy” is shown as an embodiment.
[0017]
As can be understood from FIG. 2, the variation type determination table includes, for each section type (here, intro, main, ending, and fill-in) for each type of song swelling tendency, the available type included in the section type group type. This is data defining a variation type, which is data designation information for designating an accompaniment pattern to be actually assigned from the accompaniment patterns. The section type group type is a combination of accompaniment patterns that can be used in a predetermined accompaniment style. For example, four section type group types from type 1 to type 4 are assigned so as to correspond to each accompaniment style. In this embodiment, the accompaniment patterns included in the section type group type 1 are intro A / B, main A / B, fill-in AA / AB / BA / BB, and ending A / B for each section type. Accompaniment patterns included in type 2 are intro A / B / C, main A / B / C / D, fill-in AA / BB / CC / DD / BA, and ending A / B / C. The accompaniment patterns included are intro A, main A / B, fill-in AB / BA, and ending A, and the accompaniment patterns included in section type group type 4 are intro A, main A, fill-in AA, and ending A. Therefore, for example, when the section type group type corresponding to the accompaniment pattern is the above-described type 3, only intro A for the intro section, any of main A or main B for the main section, Either fill-in AB or fill-in BA can be assigned to the fill-in section, and only ending A can be assigned to the ending section.
[0018]
By the way, as described above, depending on the style of accompaniment, if the variation type automatically assigned to the section detected at the time of automatic accompaniment generation is used as it is, an accompaniment pattern that does not match the climax of the song is assigned. May be lost. Therefore, in the automatic accompaniment generation apparatus shown in FIG. 1, the variation type determination table is referred to based on the combination of the swelling tendency of the tune detected by analyzing the music data and the section type, and the swelling tendency of the tune is determined. It is determined which accompaniment pattern should be assigned from the accompaniment patterns included in each section type group type as the accompaniment pattern along. That is, one of the section type group types is determined from type 1 to type 4 according to the selection of the accompaniment pattern to be used, and the accompaniment pattern included in the determined section type group type is assigned to each section type. You can do it. For example, in the case of the section type group type 2, when the climax tendency is “normal”, “intro B” of intro A / B / C, “main B” of main A / B / C / D, and ending If A / B / C is “ending B”, and the climax is “flashy”, “intro B”, “main C”, and “ending B” are assigned, respectively. On the other hand, in the case of section type group type 3, “intro A”, “main A”, “ending A” when the climax is “normal”, and “intro A” when the climax is “flashy” , "Main B" and "Ending A" are respectively assigned. In this way, by referring to the variation type determination table, it is possible to assign an appropriate accompaniment pattern in each accompaniment style according to the climax of the music.
[0019]
Note that the number and types of section type group types, accompaniment patterns (variation types) included in each section type group type, and the tendency of music to rise, are not limited to those in the above-described embodiment. Also, it goes without saying that the number and type of section type group types, variation types, and climaxes of songs may be defined differently for each variation type determination table.
The variation type determination table may be prepared for each section type group type.
[0020]
The automatic accompaniment generation device shown in FIG. 1 analyzes music data selected by the user, automatically generates a section data string of the automatic accompaniment data based on the analysis result, and outputs the section data sequence during an actual accompaniment performance. By referring to the accompaniment patterns of each section according to the columns, it is possible to automatically play the accompaniment that matches the atmosphere of the music of the selected music data. The automatic accompaniment generation processing for generating the automatic accompaniment data necessary for performing the automatic accompaniment according to the atmosphere of the music is performed by a predetermined program (the CPU 1 of the automatic accompaniment generation apparatus shown in FIG. 1) that implements the automatic accompaniment generation processing. Software). Therefore, the processing operation of the "automatic accompaniment generation processing" will be described with reference to FIG. FIG. 3 is a flowchart showing one embodiment of the "automatic accompaniment generation process". Hereinafter, the processing operation of this processing will be described with reference to the flowchart shown in FIG.
[0021]
In step S1, user settings are made. The user settings performed here include, for example, designation of a tone color to be used for accompaniment, setting of an accompaniment style to be used, and selection of music data to which an automatic accompaniment is added. In addition to the user setting, there may be an appropriate setting such as a change of data content of the variation type determination table or addition of data (for example, setting of the number of types of climax tendency) by the user. In step S2, a section type group type is detected from the accompaniment style to be used. That is, one section type group type corresponding to the accompaniment style used in step S1 is determined. For example, when "jazz" is set as the accompaniment style, section type group type 2 is used, and when "drum" is set as the accompaniment style, section type group type 4 is used. The section type group type corresponding to the accompaniment style to be performed is determined.
[0022]
In step S3, the section information sequence is automatically detected by analyzing the music data selected as the target to which the automatic accompaniment is added in step S1, and the generation of the automatic accompaniment data is started. The automatic detection of the section information sequence based on the analysis of the music data may be performed by any known method, and a description thereof will be omitted. The section information sequence automatically detected here includes position information on the section arrangement position (start position / end position), section type (intro section, main section, ending section, fill-in section, etc.), song swelling tendency, etc. Various information is included. In step S4, it is determined whether or not the variation type determination table corresponds to the section type group type detected in step S2. In other words, by automatically detecting the number of types of music swelling tendencies in step S3, a plurality of variation type determination tables prepared in advance corresponding to the number of types of music swelling tendencies are obtained. One variation type determination table corresponding to the number of types of automatically detected music swelling tendency is determined. Then, it is determined whether or not the section type group type detected in step S2 is included in the determined section type group type in the variation type determination table.
[0023]
If it is determined that the variation type determination table does not correspond to the section type group type (NO in step S4), a section type group type that can be substituted from among the section type group types supported by the variation type determination table Is detected (step S5). For example, when the detected section type group type is type 5 and the section type group type included in the variation type determination table is type 1 to type 4 and does not include type 5, A type that can be substituted for the type 5 among the types 1 to 4 included in the variation type determination table is determined as the section type group type.
[0024]
Automatic accompaniment data is completed by determining an accompaniment pattern to be assigned to each section based on each information determined as described above. The processes of steps S6 and S7, which are performed subsequent to steps S1 to S5, are processes performed for each section information. In step S6, with reference to the section type group type in the variation type determination table, the variation type of the accompaniment pattern to be assigned to the section is determined according to the section type in the section information and the tendency of the automatically detected music to rise. In step S7, the accompaniment style, section type, and accompaniment pattern of the determined variation type are arranged at predetermined positions based on the position information in the section information, thereby completing the automatic accompaniment data.
[0025]
In the embodiment described above, the variation type determination table is prepared. However, the present invention is not limited to this, and the variation type may be determined by an algorithm. In the case where the algorithm decides, for example, if the song has two kinds of climax tendency and the number of variation types of the accompaniment style to be used is four, it is classified into two kinds of quiet performance and two kinds of lively performance. Of the two types of quiet performances, the lively one is assigned to "normal", and the quieter one of the two types of lively performance is assigned to "flashy". The discrimination of a quiet performance or a lively performance may be performed based on the variation type, or may be analyzed based on timbre information or note information in an accompaniment pattern assigned to each section. On the other hand, if the number of types of the climax tendency of the music is greater than the number of the variation types, the variation type of the surplus tendency section may be determined as the default type.
In the above-described embodiment, the types of sections automatically detected include the intro section, the main section, the ending section, and the fill-in section, but are not limited thereto. The intro section, the ending section, the main section only, or an arbitrary section may be used. Alternatively, automatic detection may be performed.
Although the position information is included in the automatically detected section information in the above-described embodiment, the position of each section may be determined in advance. For example, the music data may be divided into predetermined sections in advance, and the section type and the variation type may be automatically determined when one section is arranged for each section.
[0026]
The format of music data and automatic accompaniment data is expressed as “event + relative time”, which indicates the time of occurrence of each event as the time from the immediately preceding event, and the time of occurrence of the event is expressed as the absolute time within the song or bar. "Event + absolute time", "pitch (rest) + note length" expressed by note pitch and note length or rest and rest length, secure memory area for each minimum resolution of performance, It may be in any form, such as a “solid method” in which the event is stored in a memory area corresponding to the time when the event occurs.
[0027]
【The invention's effect】
According to the present invention, a variation type determination table is stored in which accompaniment patterns to be assigned from available accompaniment patterns in advance are stored for each music excitement tendency, and based on a table corresponding to the selected accompaniment style, Since the accompaniment patterns (variation types) are assigned to the sections, even when using different accompaniment styles in which the number of accompaniment patterns that can be assigned to each section is different, the number of types of tune-up tendencies of the music automatically detected. This makes it possible to automatically generate an accompaniment suited to the atmosphere of the music regardless of the music.
[Brief description of the drawings]
FIG. 1 is a block diagram of a hardware configuration showing an embodiment of an overall configuration of an automatic accompaniment generation device according to the present invention.
FIG. 2 is a conceptual diagram illustrating an example of a data structure of a variation type determination table.
FIG. 3 is a flowchart showing an embodiment of an automatic accompaniment generation process.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... CPU, 2 ... ROM, 3 ... RAM, 4 ... Communication interface, 4A ... External equipment, 5 ... Input operation part, 6 ... Display part, 6A ... Display, 7 ... External storage device, 8 ... Sound source, 8A ... Sound System, 1D ... communication bus

Claims (3)

The song data is divided into a plurality of sections by analyzing the song structure of the acquired song data, and at least a predetermined accompaniment pattern, which is data for automatic accompaniment, is assigned to each of the divided sections. An automatic accompaniment generator for generating automatic accompaniment data corresponding to the data,
Storage means for storing, in accordance with each predetermined accompaniment style, variation type allocation rules in which predetermined data specification information for specifying an accompaniment pattern to be allocated to a predetermined section of the music is defined for each undulation tendency of the music;
Selecting means for selecting an accompaniment style to be used;
Detecting means for detecting the undulation of the music for each of a plurality of sections divided from the acquired music data,
Determining means for determining an accompaniment pattern to be assigned to each section according to the undulation of the detected music, based on an assignment rule of a variation type corresponding to the selected accompaniment style,
When the number of available accompaniment patterns in the selected accompaniment style is different from the number of types of undulations of the detected music, automatic accompaniment along the undulations of the music based on the accompaniment pattern determined by the accompaniment pattern determination unit is performed. An automatic accompaniment generation device for generating accompaniment data. 2. The automatic accompaniment generation apparatus according to claim 1, further comprising a change unit that can appropriately change the assignment rule of the variation type. On the computer,
A procedure of storing, in accordance with each predetermined accompaniment style, variation type allocation rules in which predetermined data specification information specifying an accompaniment pattern to be allocated to a predetermined section of the music is defined for each undulation tendency of the music;
Steps to select the accompaniment style to use,
A procedure for detecting undulations of a song for each of a plurality of sections divided from the acquired song data;
Determining an accompaniment pattern to be assigned to each section in accordance with the undulation of the detected music piece, based on a variation type assignment rule corresponding to the selected accompaniment style.

Images