JP2000066666A - Automatic music composing device and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce the stored data volume in an automatic music composing device for generating music based on stored music composing data. SOLUTION: Pattern data for expressing passage patterns A-A',-B-C-D and melody generating data for passages A, B, C are stored as music composing data in a data base. The melody generating data for the passage A' are generated with the melody generating data for the passage A changed partially by data changing processing 50. The melody generating data for the passage D are read out from a data bank 52 by data reading-out processing 56 based on assignment of a style or the like, to be generated. A music is generated in music generating processing 58 using the melody generating data for the passages A, A', B, C, D as the music generating data. The melody generating data are generated in the generating processing such as the processings 50, 56 in response to user's indication, or in random.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an automatic music composition apparatus and a recording medium for performing music composition based on stored music composition data, and particularly stores section music composition data for a partial section of a music composition to be generated. At the same time, for other sections of the tune, data for generation of section tunes is generated to reduce the storage data amount.

[0002]

2. Description of the Related Art Conventionally, as an automatic music composition apparatus, melody generation data is stored in a memory for each of all the phrases constituting the music, and the melody is generated based on the melody generation data read from the memory. A melody for one song has been proposed.

[0003]

According to the above-mentioned prior art, the melody generation data of all the passages constituting the music is stored in the memory, so that the storage data amount increases.
There is a disadvantage that a large-capacity memory is required as a memory.

An object of the present invention is to provide a new automatic music composition device capable of reducing the amount of stored data.

[0005]

An automatic music composition apparatus according to the present invention has a storage means for storing first section music generation data for generating a music piece of a partial section among a plurality of sections constituting a music piece. Generating means for generating data for generating a second section music for generating music in a section of the plurality of sections other than the partial section; and generating the first section music read from the storage means Music generating means for generating a music based on the music data and the second section music generating data generated by the generating means.

According to the configuration of the present invention, the storage means stores section music generation data (for example, data for generating a melody section) regarding a partial section of a music to be generated, and generates data for other sections of the music. Generates section music data. Then, music generation is performed based on the section music generation data read from the storage means and the section music generation data generated by the generation means. Since the section music generation data generated by the generation means does not need to be stored in the storage means, the storage data amount can be reduced accordingly.

[0007]

FIG. 1 shows a circuit configuration of an electronic musical instrument provided with an automatic music composition apparatus according to an embodiment of the present invention. This electronic musical instrument generates a musical sound by a small computer such as a personal computer. Music generation and the like are controlled.

The bus 10 has a CPU (central processing unit) 1
2, ROM (Read Only Memory) 14, RAM
(Random access memory) 16, detection circuit 18,
20, display circuit 22, sound source circuit 24, effect circuit 26, external storage device 28, MIDI (Musical Instrument Digi
tal Interface), a communication interface 32, a timer 34, and the like.

The CPU 12 executes various processes for generating music according to a program stored in the ROM 14, and these processes will be described later with reference to FIGS.

The ROM 14 stores a large number of music composition data as a database in addition to programs.
As shown in FIG. 2A, an example of each composition data is A-
This includes pattern data representing a phrase pattern such as A'-BCD and melody generation data for generating a melody of some phrases such as A, B and C in the phrase pattern. Here, the melody generation data of other phrases such as A 'and D in the phrase pattern are not stored in the database, but are generated by a generation process such as a data change process 50 and a data read process 56 described later. Therefore, the amount of data stored in the database can be reduced.

As the melody generation data for one phrase, for example, data including pitch pattern data representing a pitch pattern (pitch change) in a phrase is used. 1
As the melody generation data for a section, rhythm pattern data representing a rhythm pattern (length arrangement) in a section, rhythm coarse / dense data representing a state of notes in a section, melody data representing a melody itself, and the like can be used. is there.

The RAM 16 includes various storage units used for various processes by the CPU 12. The main storage units include a music composition data storage unit 16A, a music generation data storage unit 16B, and a music data storage unit 16C. Etc. are included.

The detection circuit 18 detects key operation information from the keyboard 36. The detection circuit 20 includes the switch group 3
8 to detect the operation information of various switches.
The switch group 38 includes, for example, a keyboard capable of inputting characters and numerical values.

The display circuit 22 enables various displays by controlling the display operation of the display device 40.

The tone generator 24 has a plurality of tone generation channels. As the tone generation method, any method such as a waveform memory method, an FM method, a physical model method, a harmonic synthesis method, a formant synthesis method, an analog synthesizer method using VCO, VCF, VCA, or the like can be adopted. Further, the tone generator circuit 24 is not limited to the one using dedicated hardware, but may be a combination of a DSP (digital signal processor) and a microprogram, or a combination of a CPU and software. Further, the plurality of tone generation channels may be constituted by a plurality of corresponding circuits,
It may be formed by using one circuit in a time-division manner.

The effect circuit 26 adds effects such as chorus and reverb to the tone signal generated from the tone generator circuit 24. The tone signal sent from the effect circuit 26 is
The sound is supplied to the sound system 42 and converted into sound.

The external storage device 28 includes HD (hard disk), FD (floppy disk), CD (compact disk), DVD (digital versatile disk), M
One or more types of recording media such as O (magneto-optical disk) can be attached and detached. When a desired recording medium is mounted on the external storage device 28, the RAM 16
Data can be transferred to If the mounted recording medium is a writable medium such as HD or FD, the RAM 1
6 can be transferred to a recording medium.

As a database of composition data, R
Instead of the OM 14, a storage medium of the external storage device 28 (HD, FD, CD, DVD, MO, or the like) may be used.
As the program recording means, a recording medium of the external storage device 28 can be used instead of the ROM 14.
In this case, the program recorded on the recording medium is transferred from the external storage device 28 to the RAM 16. And RAM1
The CPU 12 is operated according to the program stored in the CPU 6. By doing so, it is possible to easily add a program, upgrade a version, and the like.

The MIDI interface 30 is provided for transmitting and receiving performance information and the like to and from another MIDI device 44 such as an automatic performance device.

The communication interface 32 is provided for communicating information with a server computer 48 via a communication network 46 (for example, a LAN (local area network), the Internet, a telephone line, etc.). Programs and various data necessary for implementing the present invention are stored in a RAM from a server computer 48 via a communication network 46 and a communication interface 32.
16 or the external storage device 28 in response to a download request.

The timer 34 receives the given tempo data T
The tempo clock signal TCL is generated at a cycle corresponding to M. The tempo clock signal TCL is supplied to the CPU 12 as an interrupt command. The CPU 12 starts an interrupt process for each clock pulse of the tempo clock signal TCL. By utilizing such an interruption process, an automatic performance can be performed based on the music data in the storage section 16C.

In the electronic musical instrument described above, the CPU 12
Supplies the pitch information and the sounding instruction signal corresponding to the pressed key to the tone generator circuit 24 each time the key is pressed on the keyboard 36. The tone generator 24 generates a tone signal having a pitch. In this way, a manual performance sound can be generated.

Next, a composition method according to the present invention will be described with reference to FIG. First, the keyboard (switch group 38)
Based on the operation, the user inputs composition conditions such as key, beat, and passage pattern. The CPU 12 searches the database for composition data that meets the composition conditions related to the input, and
Write to 6A. As an example, composition data including pattern data representing the phrase pattern AA′-BCD in FIG. 2 [a1] and melody generation data in phrases A, B, and C in FIG. 2 [a2]. Is written in the storage unit 16A.

The CPU 12 reads the melody generation data of the phrase A from the storage unit 16A and loads it into the storage unit 16B, and then performs data change processing 50 on the melody generation data of the phrase A to perform the melody generation of the phrase A '. Data is generated and written into the storage unit 16B. A specific example of the data change processing 50 will be described later with reference to FIGS.

Next, the CPU 12 sequentially reads out the melody generating data of the passages B and C from the storage section 16A and sequentially writes them into the storage section 16B. Thereafter, the CPU 12 generates melody generation data for the phrase D.

The generation of the phrase melody generation data is performed as follows. The data bank 52 stores clause melody generation data corresponding to a style (for example, music style such as jazz style). Data bank 52
For example, the ROM 14 or the external storage device 28 can be used. In the designation process 54, when the user designates a style or the like using the keyboard (switch group 38), designation data for designating the style or the like is generated.
In the data reading process 56, the melody generating data of the passage D is read from the data bank 52 and written into the storage unit 16B in accordance with the specified data generated in the specifying process 54. Section melody generation data corresponding to other styles can also be generated in the same manner as described above.

According to the above processing, the storage section 16B stores a series of phrases A, A ', B,
The melody generation data of C and D is stored as music generation data.

In the music generation processing 58, a music (one melody for one music) is generated using the music generation data of FIG. 2B, and music data representing the generated music is written in the storage unit 16C. A specific example of the music generation processing 58 will be described later with reference to FIGS.

According to the data change process 50, it is possible to easily generate melody generation data of a phrase (for example, A ') similar to the melody generation data of a phrase (for example, A). However, the application of the data change processing 50 is not limited to this. For example, the melody generation data of the sections B, C, D, etc. which are not similar to the section A can be generated by the data change processing 50. For this purpose, for example, the coarse / fine state of notes in the first and second halves of the passage is reversed (coarse and dense in the first half of the passage, dense / coarse in the first half of the passage if it is dense in the second half), and pitch in the passage. You can make a smooth progress a leap.

According to the data reading process 56, FIG.
The unique melody generation data can be generated without being restricted by the melody generation data of 2).
However, the use of the data reading process 56 is not limited to this. For example, the melody generation data of the phrase A ′ similar to the phrase A can be generated by the data reading process 56.

Data change processing 50, data read processing 56
In the data generation processing such as the above, data for phrase melody generation may be randomly generated. As another generation method, the phrase melody generation data once generated may be corrected according to a user's instruction in the switch group 38. As still another generation method, a plurality of phrase melody generation data are generated based on one original phrase melody generation data (for example, the melody generation data of the phrase A or the phrase melody generation data read from the data bank 52). May be generated and displayed on the display 40 or the like, and any of the phrase melody generating data being displayed may be selected in accordance with a user's instruction in the switch group 38. When the phrase melody generation data is generated in accordance with the user's instruction in this manner, the variations of the generated music become rich.

FIG. 3 shows a first example of the data change processing. In this example, it is assumed that the phrase melody generating data includes pitch pattern data.

In step 60, the melody generating data of the phrase A is read from the storage section 16A, and pitch pattern data is specified in the read data. Pitch pattern data sentence A according to the specification is intended to represent the pitch curve such as P ₁ in FIG. 4, for example, as a pitch pattern. 4, the vertical axis represents the frequency from the reference sound I, and the horizontal axis represents the number of clocks corresponding to the count value of the tempo clock signal TCL. Frequency I, II, III
Are converted to pitch names C ₃ , D ₃ , E _3, ... When, for example, a C major key is given as a key.

Next, in step 62, to change the amplitude of the pitch curve of passage A as P ₂ curve shape same while FIG. 4, a pitch curve of passage A 'pitch curve of the change. That is, written into the storage unit 16B melody generation data of passage A that received the change of pitch curve as P ₂ in FIG. 4 as melody generation data of sentence A '.

FIG. 5 shows a second example of the data change processing. In this example, the data for generating a passage melody includes rhythm coarse / dense data, and this rhythm coarse / fine data is the first and second half of the passage. Shall consist of

At step 70, the melody generating data of the phrase A is read from the storage section 16A, and the first half of the phrase A is specified in the read data. The coarse / dense data represents the coarse / dense state of the note in the first half of the phrase A as, for example, coarse / dense.

Next, at step 72, the phrase A related to the designation
Of the first half of the phrase A 'is left unchanged as it is as the first half of the phrase A'. Then, the routine goes to step 74.

At step 74, the second half of the phrase A is specified in the melody generation data of the data phrase A to be read. The coarse / dense data represents the coarse / dense state of the note in the latter half of the phrase A as, for example, coarse / dense.

Thereafter, in step 76, the coarse / fine data is reversed (fine / coarse) in the coarse / fine data of the second half of the phrase A specified.
Then, the coarse / dense data relating to the reverse is defined as the coarse / dense data in the latter half of the passage A '. That is, the melody generation data of the phrase A that has undergone the processing of steps 72 and 76 is written to the storage unit 16B as the melody generation data of the phrase A '. The coarse / dense data of the phrase A 'is data in which the first half is made dense in step 72 and the second half is made dense in step 76.

FIG. 6 shows a third example of the data change process. In this example, the phrase melody generating data includes melody data representing the melody itself, and the melody data is used in the first half and the second half of the phrase. It shall consist of melody data.

In step 80, the melody generating data of the phrase A is read from the storage unit 16A, and the first half of the melody data of the phrase A is specified in the read data. Then, the process proceeds to step 82, where the melody data of the first half of the phrase A specified is not changed and is left as it is as the melody data of the first half of the phrase A '.

Next, in step 84, the second half melody data of the phrase A is specified in the melody generation data of the phrase A to be read. Then, the process proceeds to step 86, where the melody data of the latter half of the phrase A specified is corrected by, for example, increasing or decreasing the musical notes, changing the pitch, etc., and the melody data relating to this correction is used as the melody data of the latter half of the phrase A '. That is, the melody generation data of the phrase A that has undergone the processing of steps 82 and 86 is written into the storage unit 16B as the melody generation data of the phrase A '.

According to the data change processing of FIGS. 3, 5, and 6, the melody generation data of the phrase A 'similar to the melody generation data of the phrase A can be easily obtained. The similarity between the passage A and the passage A 'is that the shape of the pitch curve is the same and the amplitude of the pitch curve is different in the processing of FIG. 3, and the rhythm is the same in the first half and different in the second half in the processing of FIG. 6 is that the melody is the same in the first half and different in the second half.

FIG. 7 shows a first example of the music generation processing. In this example, it is assumed that the phrase melody generation data includes pitch pattern data.

At step 90, 1 is set in the register n as a passage number. RAM as the register n
A predetermined storage area in 16 is used.

Next, in step 92, the pitch pattern data having the phrase number of the register n is specified in the music generation data (the data stored in the storage section 16B) of FIG. 2B. In the music generation data of FIG. 2B, it is assumed that the phrase numbers 1, 2, 3, 4, and 5 are predetermined corresponding to the phrases A, A ', B, C, and D, respectively. . Therefore, when the process reaches step 92 for the first time after step 90, the phrase number in register n is 1, and the pitch pattern data in the melody generation data of phrase A is designated.

Next, at step 94, pitch and duration are randomly generated. Then, the process proceeds to step 96, where it is determined whether or not the pitch to be generated is a chromatic note of a given key. The given key is a key input as one of the composition conditions, for example, a C major key.

If the decision result in the step 96 is negative (N), the process returns to the step 94, and a pitch is generated again. If the determination result of step 96 is affirmative (Y), the process proceeds to step 98.

In step 98, it is determined whether or not the generated pitch matches the given pitch pattern. The given pitch pattern, the pitch pattern representing pitch pattern data designated in step 92, for example, a pitch curve such as P ₁ in FIG. 4. It should be noted that the determination of suitability is not limited to the case where the pitch is the same as the pitch on the pitch pattern, and the suitability may be determined even if the pitch is within a predetermined pitch (for example, twice) from the pitch on the pitch pattern. .

If the decision result in the step 98 is negative (N), the process returns to the step 94, and the steps 94 and 96 are repeated. When the determination result of step 98 is affirmative (Y),
Move to step 100.

In step 100, the pitch related to the generation is adopted as the melody sound. This melody sound is a chromatic sound of the key given through steps 96 and 98, and conforms to the given pitch pattern. The tone length of the melody tone is the tone length generated in step 94.

Next, in step 102, the length of the melody sound is added to the total length of the melody sound immediately before. Since there is no pitch immediately before the first melody tone, the duration of the first melody tone is stored for the next addition. After step 102, the process proceeds to step 104.

In step 104, the total of the sound lengths obtained in step 102 is "beats per measure x number of measures in a measure".
Is determined. As an example, if the number of beats per measure is 4 (4 beats), and the number of measures in passage A is 4, 4 × 4 = 16 beats. For the first melody sound, the determination result of step 104 is negative (N), and the process returns to step 94. Then, the processing after step 94 is executed for the second melody sound of phrase A. By repeating such processing, when the total sound length in step 102 reaches 16 beats, the determination result in step 104 becomes affirmative (Y), and the process proceeds to step 106.

At step 106, it is determined whether or not the phrase number of the register n is equal to the last phrase number k. FIG.
In the example of (b), k = 5, and n = 1 in step 90.
When the procedure first comes to step 106 after the above, the determination result of step 106 is negative (N), and
Move to 8.

In step 108, the value of the register n is set to 1
Only increase. Then, the process returns to step 92. n = 1
When it comes to step 108 in the state of, n = 2,
The processing after step 92 is executed for the phrase A 'of the phrase number 2 in the same manner as described above. When n = 5 in step 106 by repeating such processing, the determination result in step 106 becomes affirmative (Y), and the processing ends. That is, the generation of one music based on the music generation data of FIG. 2B is completed. Music data representing one melody generated based on the melody generating data of the phrases A, A ', B, C, and D in FIG.

FIG. 8 shows a second example of the music generation processing. In this example, it is assumed that the phrase melody generation data includes melody data representing the melody itself.

In step 110, a process of designating a melody change section (a section in which the melody is desired to be changed) in the music generation data of FIG. 2B is performed. For example, FIG.
Is displayed on the display 40, and the switch group 38 allows the user to designate a melody change section.

Next, at step 112, a melody change process is performed for the melody change section specified. Melody change processing includes (a) inversion of melody,
(B) reverse reading of the melody, (c) changing the sounding timing, (d) compression or expansion on the time axis, (e) compression or expansion on the pitch axis, (f) replacement of some pitches , (G)
For example, there is replacement of the pitch while the pitch change tendency is stored. As an example of the melody inversion, when a melody of CDEG is given, by inverting around D, E
Changed to DCA melody.

The melody data in the melody change section that has undergone the processing in step 112 is written to the storage section 16C. The melody data outside the melody change section is written to the storage unit 16C without any change.
Therefore, the music data in the storage unit 16C includes the melody data in the melody change section that has been processed in step 112,
It consists of melody data outside the melody change section.

FIG. 9 shows a third example of the music generation processing. In this example, the phrase melody generation data includes melody characteristic data in addition to the melody data, and the melody characteristic data is "melody change". Later, the first and last sounds will be chord constituent sounds. "

Steps 110 and 112 in FIG. 9 are the same as steps 110 and 112 in FIG.
Description is omitted for simplicity. As shown in the above example, when the melody of the CDEG is changed to the melody of the EDCA by the melody inversion, the CDEG has the sensation of the chord C major, whereas the EDCA has the sensation of the chord A minor. There is an inconvenience.

The above-mentioned melody feature data and step 114 are added in order to eliminate such inconvenience and enhance the musicality. That is, in step 114, the melody after the change is corrected according to the melody feature data, thereby normalizing the sense of chord. When the melody is changed to the melody of EDCA in step 112 as in the above-described example, the last sound A is changed to G which is a sound constituting the chord C major and closest to A according to the instruction of the melody feature data. As a result, the melody of EDCG is obtained.

The melody data in the melody change section that has undergone the processing of steps 112 and 114 is written into the storage section 16C. The melody data outside the melody change section is written to the storage unit 16C without any change. Therefore, the music data in the storage unit 16C is stored in step 1
It consists of melody data in the melody change section that has undergone the processing of steps 12 and 114, and melody data outside the melody change section.

The present invention is not limited to the above embodiment, but can be implemented in various modified forms. For example, the following changes are possible.

(1) The melody generation data is not limited to the illustrated one. For example, only the rhythm pattern may be stored, and the pitch may be determined randomly or according to a separately specified pitch pattern. Alternatively, the pitch pattern and the rhythm pattern may be stored together, and the pitch and the pitch may be determined according to the pitch pattern and the rhythm pattern related to the storage, respectively.

(2) The section for generating the melody generating data may be configured so that the user can arbitrarily select whether to generate the melody generating data with reference to another section or independently of the other section. Alternatively, it may be determined at random.

(3) The present invention is not limited to the case where a large number of melody generating data are stored in a database, but can also be applied to a case where a user creates melody generating data using the switch group 38 and the display 40. . In this case, melody generation data can be easily created because there are fewer sections to be created than when melody generation data is created for all sections. Also, the melody generation data created by the user in this way may be registered in the database.

(4) The present invention can be applied not only to the generation of melody music but also to the generation of accompaniment music such as rhythm and bass.

(5) The present invention is not limited to the form of an electronic musical instrument, but can also be implemented in the form of a combination of a personal computer and application software. The application software may be stored in a recording medium such as a magnetic disk, a magneto-optical disk, or a semiconductor memory and supplied to the personal computer, or may be supplied to the personal computer via a communication network.

(6) The present invention can be applied not only to electronic musical instruments but also to the creation of music data used in karaoke apparatuses and the like.

(7) The present invention can be applied not only to keyboard-type electronic musical instruments but also to electronic musical instruments of stringed instrument type, wind instrument type, percussion instrument type, and the like.

(8) The present invention is not limited to an electronic musical instrument having a built-in tone generator, an automatic musical instrument, and the like, but is also applicable to an electronic musical instrument in which a keyboard, a tone generator, an automatic musical instrument, etc. are connected by communication means such as MIDI or various networks. Can also be applied.

(9) The format of performance data such as melodies and chords is not limited to the “event + relative time” system in which the event occurrence time is represented by a relative time from the immediately preceding event. "Event + Absolute time" method that expresses the absolute time within a bar or bar, "Pitch (rest) + note length" method that expresses the content of a song by the pitch and note length of a note, and the rest and rest length, and an event An arbitrary method such as a method of securing a storage area for each minimum time unit of occurrence and storing the event in a storage area corresponding to the time of occurrence of the event can be used.

(10) When creating music data for a plurality of channels, data for a plurality of channels may be mixed and recorded, or a recording track may be separately recorded for each channel.

(11) When music data is recorded, it may be recorded in a continuous area in the memory in a time-series manner, or may be dispersedly recorded in discrete areas in the memory and managed as continuous data. You may do so.

[0076]

As described above, according to the present invention, the storage means stores the first section music generation data relating to a partial section of the music to be generated, and the generation means relates to other sections of the music. The second section music generation data is generated, and the first
In addition, since the music is generated based on the second section music generation data, the amount of storage data can be reduced, and the storage capacity of the storage unit can be reduced.

When the second section music piece generation data is generated based on the first section piece music generation data stored in the storage means, the data is similar to the first section music piece generation data. There is an effect that the data for generating the second section music can be easily generated.

Further, when the second section music piece generation data is generated independently of the first section piece music generation data stored in the storage means, the first section music piece generation data is restricted. Instead, there is an effect that unique second section music generation data can be generated.

Furthermore, when the second section music piece generation data is generated in accordance with the user's instruction, there is an effect that the variety of generated music pieces is increased.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a circuit configuration of an electronic musical instrument including an automatic music composition device according to an embodiment of the present invention.

FIG. 2 is an explanatory diagram for explaining a composition method according to the present invention.

FIG. 3 is a flowchart illustrating a first example of a data change process.

FIG. 4 is a diagram showing a modified example of a pitch curve.

FIG. 5 is a flowchart illustrating a second example of the data change process.

FIG. 6 is a flowchart illustrating a third example of the data change process.

FIG. 7 is a flowchart illustrating a first example of a music generation process.

FIG. 8 is a flowchart showing a second example of the music generation processing.

FIG. 9 is a flowchart showing a third example of the music generation processing.

[Explanation of symbols]

10: bus, 12: CPU, 14: ROM, 16: RA
M, 16A: music composition data storage unit, 16B: music generation data storage unit, 16C: music data storage unit, 18, 20: detection circuit, 22: display circuit, 24: tone generator circuit, 26: effect circuit, 28: External storage device, 30: MIDI interface, 32: communication interface, 34: timer,
36: keyboard, 38: switch group, 40: display, 42:
Sound system, 44: MIDI equipment, 46: Communication network, 48: Server computer.

Claims (5)

[Claims] 1. A storage means for storing first section music generation data for generating music of a partial section of a plurality of sections constituting a music, and a section other than the partial section of the plurality of sections. Generating means for generating second section music generation data for generating music in the section of the first section; first section music generation data read from the storage means; and second data generated by the generating means. An automatic music composition device comprising: music generation means for generating music on the basis of section music generation data. 2. The automatic music composition according to claim 1, wherein said generation means generates said second music piece generation data based on the first music piece generation data stored in said storage means. apparatus. 3. The automatic generating apparatus according to claim 1, wherein said generating means generates said second section music generating data independently of said first section music generating data stored in said storage means. Composer. 4. An apparatus according to claim 1, further comprising an instruction unit configured to generate instruction information in response to an instruction operation relating to generation of the second section music generation data, wherein the generation unit is configured to generate the second section music data in response to the instruction information from the instruction unit. The automatic music composition device according to any one of claims 1 to 3, wherein the automatic music composition device generates section music data for generation of section 2. 5. A recording medium used in an automatic music composition device having a storage means for storing first section music generation data for generating music of a partial section of a plurality of sections constituting a music piece. A generating step of generating data for generating a second section music for generating music in a section of the plurality of sections other than the partial section; and a first section music read from the storage unit. A recording medium recording a program including a step of generating a music piece based on the generation data and the second section music piece generation data generated in the generation step.