JP6565529B2 - Automatic arrangement device and program - Google Patents

Description

  The present invention relates to an apparatus and a program for automatically arranging (arranging) music performance information, and in particular, a technique for performing high-quality automatic arrangement based on searching an accompaniment having characteristics and compatibility with original performance information from a database. About.

  Japanese Patent Application Laid-Open No. 2004-228561 shows a technique in which a user selects a desired part from MIDI format automatic performance data of a plurality of parts of a given musical piece, and generates a desired score for the selected part. ing. As an example, the user selects a melody part, automatically generates accompaniment data suitable for the melody of the selected melody part, and the accompaniment part based on the selected melody part and the automatically generated accompaniment data; It is shown to generate a score consisting of As a method for automatically generating accompaniment data suitable for a melody, specifically, a plurality of accompaniment patterns corresponding to performance levels are prepared in advance, and an accompaniment pattern corresponding to the performance level selected by the user is selected. The accompaniment data is automatically generated in consideration of the chord progression in the melody based on the selected accompaniment pattern.

  Japanese Patent Application Laid-Open No. 2004-259561 discloses a technique for searching an accompaniment pattern similar to a rhythm pattern input by a user by a tapping operation or the like from a database. Non-Patent Document 1 below discloses a technique for searching for music having a corresponding melody progression based on the pitch order of the melody performance input by the user.

JP-A-2005-202204 International Publication No. WO2012 / 074070

http://jp.yamaha.com/products/apps/melodysearch/

  It can be said that the automatic generation of accompaniment data in Patent Document 1 described above automatically arranges (arranges) accompaniment based on a given melody. However, the automatic generation of the accompaniment data in Patent Document 1 is only to change the pitch of the musical sound constituting the existing accompaniment pattern (such as chord backing or arpeggio) according to the progress of the chord of the melody. Therefore, it is difficult to generate an accompaniment that matches the melody unless the user appropriately selects an existing accompaniment pattern that is the base. That is, Patent Document 1 does not automatically select an accompaniment pattern that is compatible with a melody. Patent Document 2 is suitable for searching for an accompaniment pattern similar to a rhythm pattern input by a user, but cannot search for an accompaniment pattern suitable for a melody part, chord part, bass part, or the like in a song. Non-Patent Document 1 merely searches for a song having a corresponding melody progression based on the pitch order input by the user, and has no idea of searching for an accompaniment pattern suitable for the melody part.

  The present invention has been made in view of the above points, and an object of the present invention is to provide an automatic arrangement apparatus and program capable of improving the quality of automatic arrangement.

  An automatic arrangement device according to the present invention includes means for acquiring original performance information, means for specifying a performance part, means for extracting performance information of the specified performance part from the acquired original performance information, and the extraction Means for retrieving accompaniment pattern data in accordance with the query from a database storing a plurality of accompaniment pattern data using the played performance information as a query, and at least a part of the original performance information based on the retrieved accompaniment pattern data And means for generating accompaniment data for use in combination.

  According to the present invention, performance information of a specified performance part is extracted from original performance information, and a plurality of accompaniment pattern data is stored as a query using the extracted performance information as a query. Since the data is retrieved and accompaniment data for use in combination with at least a part of the original performance information is generated based on the retrieved accompaniment pattern data, the compatibility with the performance part specified in the original performance information Good accompaniment pattern data can be automatically retrieved, and accompaniment data that is compatible with the original performance information can be easily generated based on the retrieved accompaniment pattern data, improving the quality of automatic arrangement Can be made.

  In one embodiment, the means for searching for the accompaniment pattern data may be configured to search for accompaniment pattern data suitable for combining with the extracted performance information. Thus, in the case where the arranged performance information is provided by combining the accompaniment data generated based on the retrieved accompaniment pattern data with the performance information extracted from the original performance information, the combination is musically compatible. Can provide a good arrangement.

  In another embodiment, the means for searching for accompaniment pattern data may be configured to search for accompaniment pattern data suitable for replacing the extracted performance information. Accordingly, when providing the performance information arranged by combining the accompaniment data generated based on the searched accompaniment pattern data with performance information different from the extracted performance information in the original performance information, The arranged performance information composed of the combination inherits the good compatibility between the extracted performance information and the other performance information of the original performance, thereby easily providing a musically compatible arrangement. can do.

  Each means constituting the automatic arrangement device according to the present invention can be constituted by a dedicated device or a circuit configured to realize each function, or a program module configured to realize each function, and the program module It can also be configured by a combination of processors capable of executing program modules (a general-purpose processor such as a CPU or a dedicated processor such as a DSP).

  In addition, the present invention can be implemented not only as an apparatus invention but also as a computer-implemented method invention comprising steps for realizing the functions of the respective means, and for executing the method. The present invention can also be implemented as an invention of a program comprising a group of instructions that can be executed by a processor, and as an invention of a non-transitory computer-readable storage medium storing the program.

1 is a hardware configuration block diagram showing an embodiment of an automatic arrangement device according to the present invention. The functional block diagram of the process which concerns on one Example of this invention performed under control by CPU.

  FIG. 1 is a hardware configuration block diagram showing an embodiment of an automatic arrangement device according to the present invention. The automatic arrangement device does not necessarily have to be configured as a dedicated device for automatic arrangement, and the automatic arrangement device according to the present invention can be applied to any device or device having a computer function, such as a personal computer, a portable terminal device, and an electronic musical instrument. Any application program may be installed as long as an arrangement application program is installed. The hardware arrangement of this automatic arrangement device is a well-known configuration in a computer, for example, for inputting a CPU (Central Processing Unit) 1, ROM (Read Only Memory) 2, RAM (Random Access Memory) 3, characters and symbols, etc. Input device 4 including keyboard and mouse, display 5, printer 6, hard disk 7 which is a non-volatile large-capacity memory, memory interface (I / F) 9 for portable medium 8 such as USB memory, sound source circuit board 10, a sound system 11 such as a speaker, and a communication interface (I / F) 12 for connecting to an external communication network. In the ROM 2 and / or the hard disk 7, the application program for automatic arrangement according to the present invention, other application programs, and a control program are temporarily stored.

  FIG. 2 is a functional block diagram of processing according to an embodiment of the present invention that is executed under the control of the CPU 1. First, in block 20, music performance information (this is called original performance information) to be arranged is acquired. Any specific configuration for acquiring the original performance information may be used. For example, the data format of the original performance information to be acquired may be data encoded in a predetermined format such as a standard MIDI file (SMF), or may be image information of a musical score drawn on a staff. It may be composed of audible audio waveform data, or may be composed of any other data format as long as it can express a music piece. When original performance information consisting of a score image is acquired, the image is analyzed according to a known score analysis technique, and the pitch, beat position (time position), note value, etc. of each note constituting the original performance information are encoded. In addition, various symbols such as the strength symbol and the accent symbol are encoded together with the time position. Similarly, in the case of audio waveform data, the audio waveform is analyzed according to a known analysis technique such as pitch and volume, and the pitch, beat position (time position), note value of each note constituting the original performance information is analyzed. And the sound volume may be encoded together with the time position. Also, the musical part configuration of the original performance information to be acquired may be substantially one that includes a plurality of performance parts. For example, a right-hand part (melody part) and a left-hand part (accompaniment or chord part) like a piano score. Furthermore, it may consist of a melody part and a plurality of accompaniment parts such as chord backing, arpeggio, bass and rhythm (drum). Further, the configuration or path for acquiring the original performance information is arbitrary. For example, the original performance information may be acquired from the portable medium 8 holding the original performance information via the memory I / F 9, or The desired original performance information may be selectively acquired from an external source or server via the communication I / F 12, or the user performed in real time using a performance device such as a keyboard (not shown). You may make it acquire the information of a music as original performance information. When the CPU 1 executes the process of block 20, it functions as a means for acquiring original performance information.

  In block 21, the chord information indicating the chord progression of the music in the acquired original performance information is acquired. If chord information is included in the acquired original performance information, the chord information may be acquired. If chord information is not included in the acquired original performance information, a chord is detected by analyzing the progress of the melody or accompaniment included in the original performance information using a known chord analysis technique. The chord information may be acquired based on the information. Alternatively, the user may input chord information via the input device 4 or the like, and the chord information may be acquired based on the user input. The acquired chord information is used to shift the pitch of the accompaniment sound indicated by the accompaniment data when generating accompaniment data that becomes harmony.

  In block 22, the composition of the performance part in the acquired original performance information is determined. If the original performance information includes part information or identification information equivalent thereto, the performance part configuration in the original performance information may be determined using the part information or identification information. In addition, when the original performance information is composed of a score image, if the score is composed of a melody score (G clef score) and an accompaniment score (H clef score) like a piano score, or by part Can be determined based on the performance part composition of the original performance information. If the original performance information is not previously identified as part-specific note information, or is not composed of a part-specific staff score, block 22 analyzes the notes or the score included in the original performance information, A performance method in the original performance information is determined (estimating which musical part in each original performance information is played, such as a melody, a chord, or a bass).

  An example of the rendition style determination process in block 22 will be described as follows. First, the pitch information of all the notes included in the original performance information to be determined is stored in chronological order. The performance information is determined by analyzing the pitch information thus stored as follows. In the following, “single note” means that only one pitch exists at the same sounding timing, and “compound” means that two or more pitches exist at the same sounding timing. Say.

(1) Performance method consisting only of melody part The ratio of “single tone” in the original performance information is a predetermined high ratio (for example, 90%) or more, and the average pitch in the original performance information is a predetermined middle range or high range If it belongs to the original performance information, it is determined that the original performance information consists only of the melody part.

(2) Performance method comprising only the bass part When the ratio of “single notes” in the original performance information is a predetermined high ratio (for example, 90%) or more, and the average pitch in the original performance information belongs to a predetermined low frequency range The original performance information is determined to consist only of the bass part.

(3) Performance method composed of a melody part and a bass part The ratio of “single notes” in the original performance information is less than a predetermined high ratio (for example, 90%), and the ratio of three or more “compounds” is lower than a predetermined threshold value. If the difference between the lowest pitch and the highest pitch in each “compound” is equal to or greater than a predetermined threshold, it is determined that the original performance information is composed of a melody part and a bass part. That is, it is presumed that the melody part is played on the high pitch side (right hand) and the bass part is played on the low pitch side (left hand).

(4) Performance method composed of chord part and bass part The ratio of “single notes” in the original performance information is less than a predetermined high ratio (for example, 90%), and the ratio of three or more “compounds” is higher than a predetermined threshold. If the average pitch of the “single note” falls below a predetermined low frequency range, it is determined that the original performance information is composed of a chord part and a bass part. That is, it is presumed that the chord part is played on the middle or high-frequency side (right hand) and the bass part is played on the low-frequency side (left hand).

(5) Performance method comprising a melody part and a chord part The ratio of “single notes” in the original performance information is less than a predetermined high ratio (for example, 90%), and the ratio of three or more “compounds” is higher than a predetermined threshold value. If the average pitch of “single note” is higher than the average pitch of “compound”, it is determined that the original performance information is composed of a melody part and a chord part. That is, it is presumed that the melody part is played on the middle or high pitch side (right hand) and the chord part is played on the low pitch side (left hand).

(6) Performance with only one chord part in one hand The ratio of “single notes” in the original performance information is less than a predetermined high ratio (for example, 90%), and the ratio of three or more “compounds” is higher than a predetermined threshold. In addition, the average of the differences (pitch) between adjacent pitches in each “compound” is smaller than a predetermined value, or a relatively narrow range in which all pitches can be played with one hand in each “compound” Are determined to be composed only of chord parts. In this case, it is presumed that the chord composed of “compounds” is played with one hand on the keyboard.

(7) Performance method consisting only of chord parts with both hands The ratio of “single notes” in the original performance information is less than a predetermined high ratio (for example, 90%), and the ratio of three or more “compounds” is higher than a predetermined threshold. When all the pitches of individual “compounds” are within a relatively wide range that can be played with both hands, it is determined that the original performance information consists only of chord parts. In this case, it is presumed that this is a performance method in which a chord composed of “compounds” is played with both hands on the keyboard.

  Next, in block 23, a performance part involved in the arrangement is designated. For example, the performance part configuration of the original performance information determined in the block 22 is presented to the user via the GUI (display 5), and the user is allowed to select a performance part (input part) to be used as a search query to be described later. You can do it. The performance part (input part) may be specified (selected) in association with an arbitrary time section (time range) of the original performance information. The performance part specified here may be any one of the one or more performance parts constituting the original performance information, or one or more of the performance parts constituting the original performance information. All of the performance parts (all parts) may be used. Furthermore, in block 23, the user may select one performance part (output part) that uses the accompaniment data generated as a result of the arrangement. When the CPU 1 executes the processing of block 23, it functions as means for designating a performance part.

  Next, in block 24, the performance information of the performance part (one part or all parts) designated in block 23 is extracted from the original performance information. This extraction is performed for each time interval corresponding to the designated performance part. If the original performance information includes part information or identification information equivalent thereto, the performance information of the designated performance part may be extracted from the original performance information using the part information or identification information. On the other hand, if the original performance information does not include part information or identification information equivalent thereto, the specified performance part is determined from the original performance information according to an appropriate method in consideration of the musical properties of the specified performance part. It is sufficient to analyze and extract the performance information. When the CPU 1 executes the processing of block 24, it functions as means for extracting performance information of the designated performance part from the acquired original performance information.

  A specific example of the technique for extracting performance information of the designated performance part in consideration of the musical properties of the designated performance part performed in block 24 will be described below. In this case, first, all notes (pitch and note value information) included in the original performance information to be determined are stored in chronological order. By analyzing the stored notes (pitch and note value information) as follows, performance information of necessary performance parts is extracted.

(A) Extraction example of melody part Time-series notes in the original performance information are grouped together at the same sounding timing for each sounding timing, and the highest sound in each group (sounding timing) is selected as a melody part candidate. And This is because a melody performance is usually performed in a higher range than a bass or chord. Then, from these candidates, those that are not suitable for constituting a series of melody parts are excluded, and the remaining candidate notes are extracted as performance information of the melody parts. As the exclusion condition, for example, a candidate note having a pitch that is lower than the average value of the pitches of a plurality of surrounding candidate notes by a predetermined threshold or more is excluded, and / or the pitch of a candidate note at the preceding pronunciation timing Is higher than the candidate note at the next pronunciation timing and the note length at the preceding pronunciation timing is maintained at the next pronunciation timing, the candidate note at the next pronunciation timing is excluded. ,and so on.

(B) Bass part extraction example Time-series notes in the original performance information are grouped together at the same sounding timing for each successive sounding timing, and the lowest sound in each group (sounding timing) is the base part candidate. And This is because the bass performance is usually performed in a lower range than the melody or chord. Then, from these candidates, those that are not suitable to be regarded as constituting a series of bass parts are excluded, and the remaining candidate notes are extracted as performance information of the bass part. As the exclusion condition, for example, a candidate note having a pitch higher than the average value of the pitches of a plurality of surrounding candidate notes by a predetermined threshold or more is excluded, and / or the pitch of a candidate note at a preceding pronunciation timing Is lower than the candidate note at the next pronunciation timing and the note length at the preceding pronunciation timing is maintained at the next pronunciation timing, the candidate note at the next pronunciation timing is excluded. ,and so on.

(C) Example of chord part extraction Time-series notes in the original performance information are grouped together for each sequential sounding timing, and notes belonging to the same sounding timing are grouped. Candidate. Then, in each group, a plurality of notes suitable to be regarded as constituting a chord played with one hand are extracted as performance information of the chord part. For example, if the number of notes in the group is 3 or less and the pitches are within the range that can be played with one hand, all the notes in the group are extracted as performance information of the chord part. Alternatively, if the number of notes in the group is 4 or more, only the pitches that fall within the range that can be played with one hand are selected, and the notes with the selected pitch are extracted as the performance information of the chord part.

  Next, in block 25, using the performance information extracted in block 24 as a query, accompaniment pattern data corresponding to the query is retrieved from a database storing a plurality of accompaniment pattern data. The database storing a plurality of accompaniment pattern data may be either an internal database (for example, the hard disk 7 or the portable medium 8) or an external database (for example, a server on the Internet).

  In one embodiment, a bank of known accompaniment style data (automatic accompaniment data) may be used as a source of existing accompaniment pattern data. In a bank of known accompaniment style data (automatic accompaniment data), multiple sets of accompaniment style data are stored for each category (Pop & Rock, Country & Blues, Standard & Jazz, etc.), and each set of accompaniment style data is an intro section. , Main section, fill-in section, ending section, etc. each accompaniment data set is included, one section accompaniment data set is rhythm 1, rhythm 2, bass, rhythmic chord 1, rhythmic chord 2, phrase 1, It includes accompaniment pattern data (template) of multiple parts such as phrase 2. The accompaniment pattern data (template) for each part of the lowest layer in the bank of such known accompaniment style data (automatic accompaniment data) is the accompaniment pattern data acquired in the block 25. In the block 25, accompaniment pattern data of only one part in an accompaniment data set for a certain section may be acquired, or accompaniment pattern data of all parts or a part of plural parts may be acquired in combination. Good. As is well known, in accompaniment pattern data (template) of parts including pitch elements such as rhythmic chord 1, rhythmic chord 2, phrase 1, phrase 2, etc., information indicating a reference chord name (for example, C major chord) In addition, information for defining a pitch conversion rule is additionally included. The entity of the accompaniment pattern data (template) may be data encoded in a distributed manner according to the MIDI standard or the like, or may be data along the time axis such as audio waveform data.

  There are roughly two types of search algorithms performed in the block 25. One is to search for accompaniment pattern data suitable for combining with performance information as a query (Example 1). The other is to search for accompaniment pattern data suitable for substituting the performance information used as a query (example 2). The former (example 1) search algorithm is employed, for example, when the input part specified in the block 23 is different from the output part. For example, a melody part is designated as the input part and a drum part is designated as the output part. This is because, when the performance information of the drum part is not included in the original performance information, the accompaniment pattern data of the drum part having good compatibility with the performance information of the melody part in the original performance information is retrieved, and the retrieved accompaniment pattern data This is advantageous when the accompaniment data of the drum part is generated based on the above. The latter (example 2) search algorithm is employed, for example, when the input part specified in the block 23 and the output part are the same. For example, a chord part is designated as an input part and a chord part is designated as an output part. In order to replace the performance information of the chord part in the original performance information with another performance information, the accompaniment pattern data of the chord part having good compatibility with the performance information of the chord part in the original performance information is searched and the search is performed. This is advantageous when accompaniment data for chord parts is generated based on the accompaniment pattern data.

  When searching according to Example 1 or Example 2 in the block 25, for example, among the many accompaniment pattern data stored in the database, the accompaniment pattern data group of the performance part designated as the output part is targeted. Using the performance information of the performance part designated as the input part (performance information extracted in the block 24) as a query, one or more accompaniment pattern data having a good compatibility with the query performance information is retrieved. As a specific search method for that purpose, a known appropriate method may be adopted. For example, the musical tone elements such as the pitch, note value, and pronunciation timing of each note constituting the query performance information are compared with the musical tone elements of each accompaniment pattern data in the search target accompaniment pattern data group. The degree of similarity is digitized and evaluated, and the overall evaluation value is calculated by the sum or average or weighted addition of the similarity of each musical tone element, and one or more accompaniment pattern data having the highest overall evaluation value is searched. Good. In this case, the total evaluation value (section evaluation value) is calculated for each predetermined number (one or more) of bars, and the total evaluation value is calculated by summing or averaging or weighted addition of the calculated section evaluation values. One or more accompaniment pattern data having the highest overall evaluation value may be searched. When a plurality of accompaniment pattern data is obtained by the search, the retrieved plurality of accompaniment pattern data is presented to the user via the display 5 and any one of them is selected by the user. It's okay.

  Note that the time section (temporal range) of the performance information that is the query consists of N bars (N is an arbitrary plural number), whereas the accompaniment pattern data to be searched consists of k bars less than N. (K is 1 or more, and k <N or k << N) creates search target accompaniment pattern data for N measures by repeating the search target accompaniment pattern data for k measures a plurality of times, The created N-bar search target accompaniment pattern data and the N-bar query performance information may be compared. In this case, it is preferable to employ a method for obtaining the overall evaluation value based on a plurality of the interval evaluation values. In this case, the predetermined number for calculating the comprehensive evaluation value (section evaluation value) may be set to k, for example.

  When the CPU 1 executes the processing of block 25, the CPU 1 functions as a means for retrieving the accompaniment pattern data corresponding to the query from a database storing a plurality of accompaniment pattern data using the extracted performance information as a query.

  Next, in block 26, accompaniment data is generated based on the accompaniment pattern data acquired by the search in block 25. For example, accompaniment data having a time length corresponding to the time range of the query performance information is generated by repeating one or a plurality of accompaniment pattern data including one or more measures obtained by the search. If necessary, a part of the accompaniment data formed by repeating the retrieved accompaniment pattern data once or a plurality of times may be appropriately changed by a user operation.

  The block 27 is a process performed when the accompaniment pattern data acquired by the search in the block 25 includes an accompaniment sound having a pitch element such as chord backing or arpeggio. When the accompaniment data is generated in the block 26 In addition, the pitch of the accompaniment data to be generated is shifted according to the chord information acquired in the block 21. When the accompaniment pattern data acquired by the search in the block 25 is composed of a rhythm pattern such as a drum part, the processing in this block 27 is omitted.

  In block 28, the accompaniment data generated in block 26 is provided to the user as arranged performance information in combination with at least a part of the original performance information. The part in which the accompaniment data generated in the block 26 is combined with which part of the original performance information may be determined according to the designation of the input part and the output part in the block 23, for example. You may make it select. For example, when all the parts are specified as the input part and the drum part is specified as the output part in the block 23, the accompaniment data of the drum part generated in the block 26 is combined with all the original performance information. May be provided as arranged performance information. Alternatively, when a melody part is designated as an input part and a chord part is designated as an output part in the block 23, the accompaniment data of the chord part generated in the block 26 is used as the melody part in the original performance information. The performance information may be provided in combination with the performance information. For example, when the same part (for example, a chord part) is designated as the input part and the output part in the block 23, the accompaniment data generated in the block 26 is used as substitute performance information. Arranged performance information may be provided by replacing performance information of a part (for example, a chord part) designated as an input part in the original performance information. That is, instead of the chord part performance information in the original performance information, the accompaniment data generated in the block 26 is used as the chord part performance information, and is arranged together with the remaining performance information in the original performance information. Provide performance information.

  The format in which the arranged performance information is provided may be arbitrarily selected in terms of design. For example, it is provided in the state of electronic data encoded according to a predetermined format such as the MIDI standard, or is displayed on the display 5 as a specific musical score image, printed on paper by the printer 6, or an electronic image. It may be provided as data or as audio waveform data.

  When the CPU 1 executes the processing of block 26, it functions as means for generating accompaniment data for use in combination with at least a part of the original performance information based on the retrieved accompaniment pattern data.

  As described above, according to the above embodiment, the performance information of the designated performance part is extracted from the original performance information, and the extracted performance information is used as a query from the database storing a plurality of accompaniment pattern data. Accompaniment pattern data corresponding to the query is retrieved, and accompaniment data for use in combination with at least a part of the original performance information is generated based on the retrieved accompaniment pattern data. Accompaniment pattern data having good compatibility with the performance part can be automatically retrieved. Therefore, accompaniment data having good compatibility with the original performance information can be easily generated based on the retrieved accompaniment pattern data, and the quality of automatic arrangement can be improved.

1 CPU (Central Processing Unit)
2 ROM (Read Only Memory)
3 RAM (Random Access Memory)
4 Input device 5 Display 6 Printer 7 Hard disk 8 Portable medium 9 Memory interface 10 Sound source circuit board 11 Sound system 12 Communication interface

Claims (5)

Means for obtaining original performance information;
Means to specify the performance part;
Means for extracting performance information of the designated performance part from the acquired original performance information;
Means for retrieving accompaniment pattern data in accordance with the query from a database storing a plurality of accompaniment pattern data using the extracted performance information as a query;
An automatic arrangement apparatus comprising: means for generating accompaniment data for use in combination with at least a part of the original performance information based on the retrieved accompaniment pattern data.   The automatic arrangement device according to claim 1, wherein the means for searching for the accompaniment pattern data searches for accompaniment pattern data suitable for combining with the extracted performance information.   The automatic arrangement device according to claim 1, wherein the means for searching for the accompaniment pattern data searches for accompaniment pattern data suitable for substituting for the extracted performance information. Means for obtaining a chord of the original performance information;
The means for generating the accompaniment data generates the accompaniment data by controlling a pitch element of each sound in the retrieved accompaniment pattern data according to the acquired chord. The automatic arrangement device according to crab. The procedure to get the original performance information,
To specify the performance part,
A procedure for extracting performance information of the designated performance part from the acquired original performance information;
A procedure for searching for accompaniment pattern data according to the query from a database storing a plurality of accompaniment pattern data using the extracted performance information as a query;
A program for causing a computer to execute a procedure for generating accompaniment data for use in combination with at least a part of the original performance information based on the retrieved accompaniment pattern data.

Images