WO2020000751A1 - Procédé et appareil de composition automatique, et dispositif informatique et support d'informations - Google Patents

Procédé et appareil de composition automatique, et dispositif informatique et support d'informations Download PDF

Info

Publication number
WO2020000751A1
WO2020000751A1 PCT/CN2018/108851 CN2018108851W WO2020000751A1 WO 2020000751 A1 WO2020000751 A1 WO 2020000751A1 CN 2018108851 W CN2018108851 W CN 2018108851W WO 2020000751 A1 WO2020000751 A1 WO 2020000751A1
Authority
WO
WIPO (PCT)
Prior art keywords
song
arpeggio
intro
user
sequence
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/108851
Other languages
English (en)
Chinese (zh)
Inventor
梅亚琦
刘奡智
王健宗
肖京
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2020000751A1 publication Critical patent/WO2020000751A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H1/00—Details of electrophonic musical instruments
    • G10H1/36—Accompaniment arrangements
    • G10H1/38—Chord
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H7/00—Instruments in which the tones are synthesised from a data store, e.g. computer organs
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/101—Music Composition or musical creation; Tools or processes therefor
    • G10H2210/111—Automatic composing, i.e. using predefined musical rules

Definitions

  • the present invention relates to the field of computer technology, and in particular, to an automatic composition method, device, computer equipment, and storage medium.
  • Algorithmic composition has a history of decades, but no iconic results have appeared so far.
  • the present invention proposes an automatic composition method, device, computer equipment, and storage medium.
  • the song is generated according to a preset composition rule based on a start sound and a song type input by a user, and aims to solve the existing automatic compilation.
  • Music software requires the user to have a certain knowledge of music theory before it can be used smoothly.
  • An automatic composition method includes:
  • a target is selected from the intro, the interlude, the interlude and the endluo, and the target and the main melody are spliced in order to generate a song.
  • the invention also provides an automatic composition device, the device includes:
  • a first acquisition module configured to acquire more than three start sounds input by a user
  • a processing module configured to perform chord decomposition on the three or more start notes input by the user and perform chord inversion after the chord decomposition according to the harmony theory
  • Arpeggio sequence generation module is used to randomly generate four arpeggio sequences corresponding to chords after the chords are transposed;
  • a second acquisition module configured to acquire a song type selected by the user
  • a first obtaining module configured to assign corresponding music elements to the four arpeggio sequences according to the preset composition rule and the song type to obtain an intro, an intro, an interlude, and an ender;
  • a second obtaining module configured to randomly tune a melody corresponding to the song type from the music library to obtain a main melody
  • a song generating module is configured to select the intro, the intro, the interlude, and the end in accordance with the preset composition rule, and splice the target and the main melody in order to generate A song.
  • the present invention also provides a computer device including a memory and a processor.
  • the memory stores computer-readable instructions.
  • the processor executes the computer-readable instructions, the steps of the method according to any one of the foregoing are implemented.
  • the present invention also provides a computer non-volatile readable storage medium on which computer readable instructions are stored, and when the computer readable instructions are executed by a processor, the steps of the method according to any one of the foregoing are implemented.
  • the present invention has the beneficial effect that the song is generated according to a preset composition rule by the user's input starting sound and song type, and does not require the user to have a certain knowledge of music theory, and the user can compose, which aims to solve the current problem.
  • Some automatic arranger software require users to have a certain knowledge of music theory before they can use it smoothly.
  • FIG. 1 is a flowchart of an automatic composition method provided by an embodiment of the present invention
  • FIG. 2 is a functional block diagram of an automatic composition device provided by an embodiment of the present invention.
  • FIG. 3 is a schematic block diagram of a structure of a computer device provided by an embodiment of the present invention.
  • an embodiment of the present invention provides an automatic composition method.
  • the method includes the following steps:
  • Step S101 Acquire more than three start sounds input by a user.
  • More than three start sounds input by the user are obtained.
  • three start sounds input by the user are obtained.
  • composition UI interface the user clicks to create a new song, and enters more than three of the multiple notes.
  • step S101 includes:
  • the initial sound is displayed by using a virtual key to simulate a piano keyboard.
  • step S101 the method includes:
  • the automatic composition device is connected to an external device, and the user inputs more than three start sounds through the external device.
  • the external device as an electronic keyboard as an example
  • the electronic keyboard by connecting with the electronic keyboard, when the user plays the electronic keyboard At this time, the electronic keyboard generates and outputs electric signals corresponding to the notes played by the user, and according to the electric signals, three or more starting sounds played by the user can be obtained, which is convenient for the user.
  • step S101 the method includes:
  • the user hums three or more start sounds, receives three or more start sounds from the user, and extracts three or more start sounds, simplifying the acquisition of three or more start sounds, even if he does not understand how to operate Users of piano keyboards can also create music by humming, which is convenient for users to input the initial sound.
  • Step S102 According to the harmony theory, perform chord decomposition on the three or more starting sounds input by the user and perform chord inversion after the chord decomposition.
  • Step S103 After the chords are transposed, randomly generate four arpeggio sequences corresponding to the chords.
  • the three or more starting sounds obtained by the user are processed.
  • the processing method is to perform chord decomposition first, and then perform chord inversion. After the chord inversion is completed, four arpeggio sequences are randomly generated, where the four arpeggio sequences correspond to the chords.
  • chord decomposition of the three start sounds is specifically: adjusting three arbitrary start sounds to all within one octave, and naming the root sounds from low to high, Three and five tones.
  • chord transposition is performed.
  • the chord transposition is specifically: the chord with the lowest note is called the home chord, and the chord inversion is called with the third and fifth notes.
  • the third chord can have For two transpositions, the lowest transposition with three notes is the first transposition (sixth chord), and the transposition with the fifth note is the second transposition (fourth and sixth chords).
  • the arpeggio sequence is specifically: the arpeggio sequence is randomly selected from the corresponding original chords, six chords, four or six chords, and from low to high (up) or from high to low (down) ) Repeat regularly.
  • Step S104 Acquire a song type selected by the user.
  • the user After the user finishes entering more than three start sounds, the user is required to select a song type, and after the user finishes selecting the song type, the song type selected by the user is obtained.
  • the song type includes song style and song emotion.
  • step S104 includes:
  • the song style pops up for the user to choose.
  • the song emotion pops up for the user to choose.
  • the user needs to choose an emotion from the song emotions.
  • the song type selected by the user is obtained. In the case where the user does not have knowledge of music theory, composition is performed by selecting a song type.
  • step S104 the method includes:
  • a song style pops up for the user to select, and after the user selects one of the song styles, the song type selected by the user is obtained.
  • composition is performed by selecting a song type.
  • step S104 the method includes:
  • the song emotion pops up for the user to select, and after the user selects one of the song emotions, the song type selected by the user is obtained.
  • composition is performed by selecting a song type.
  • the above-mentioned song styles include pop, classical, jazz and folk songs; the above-mentioned song emotions include happiness, sadness, freshness and nostalgia.
  • Step S105 according to the preset composition rules and song types, assign corresponding music elements to the four arpeggio sequences to obtain intros, intros, endoss, and endos;
  • Step S106 Randomly tune a melody corresponding to the song type from the music library to obtain the main melody
  • Step S107 Select among the intro, intro, interlude and ending according to the preset composition rules, splicing the target and the main melody in order to generate a song.
  • the corresponding four elements of the arpeggio sequence are assigned. After completing the four elements of the arpeggio sequence, obtain Intro, Intro, Endo and Endo. After obtaining four pieces of intro, intro, end, and ending, according to the song type selected by the user, randomly select a corresponding melody from the music library to obtain the main melody.
  • the music library contains a large number of Song MIDI format, and classified by song style, song emotional tags.
  • the target is selected according to the preset composition rule. If the structure of the preset composition rule is five-section, the five-section pattern is intro, intro, main melody, end intro, and end intro, the target is selected as intro.
  • Intro, interlude, and ending if the preset composition structure in the composition rules is three-stage, the three-stage is the intro, main melody, and ending, then select the target as intro, ending, if By default, the composition structure in the composition rules is two-stage, and the two-stage composition is the intro and main melody. The target is selected as the intro. Take the five-section style as an example. After obtaining the intro, intro, end, and ending, randomly select a melody corresponding to the type of song from the music library to obtain the main melody. After the five pieces of music, interlude, ending, and main melody, the prelude, interlude, main melody, interlude, and endluo are spliced in order to generate songs and complete the composition. Compose according to the five intro, intro, intro, end, and main melody, making the composition difficult and efficient.
  • the preset composition rules are written according to the music rules, including basic music theory, scales, arpeggios, harmony, polyphony, orchestration, rhythm, and melody structure.
  • the preset composition rules are based on factors such as basic music theory, scales, arpeggios, harmony, polyphony, orchestration, rhythm, tempo, and melody structure, and different parameters are set for specific styles and emotions.
  • the scales use the blues scale
  • the arpeggios and harmonies perform the corresponding changes in the blues scale.
  • the orchestration uses the saxophone template, and the rhythm is mostly split.
  • the main melody is adjusted from the music library compiled by the musician according to the specific parameters of the selected style and emotion, and the existing melody segment is adjusted, and then the melody segment is horizontally, vertically, transposed, shifted, reflected, retrograde, enlarged, and reduced. Transform to increase the degree of freedom of the main theme.
  • the main accompaniment uses the corresponding style and emotion texture template written by the musician.
  • the song type selected by the user is sentimental.
  • the preset composition rules arrange basic music theory, scales, arpeggios, harmony, polyphony, orchestration, rhythm to the four arpeggio sequences, and make the four arpeggio sequences.
  • the obtained intro, intro, interlude, and ending are in a sad type, and the intro, prelude, interlude, and endluo are played to make the user listen. It feels sad.
  • the four arpeggio sequences include the first and second arpeggio sequences, both of which are ascending or descending arpeggios, and the third and fourth arpeggio sequences, which are both ascending or descending arpeggios. In step S105, they include:
  • composition rules and song types arrange the music elements required for the intro to the first arpeggio sequence to obtain the intro;
  • composition rules and song types arrange the music elements required for the prelude to the second arpeggio sequence to obtain the prelude
  • composition rules and song types arrange the music elements required for the interlude to the third arpeggio sequence to obtain the interlude;
  • composition rules and song types arrange the music elements required for the ending of the fourth arpeggio sequence to obtain the ending.
  • the intro and intro are both selected ascending or descending arpeggios, and the intro and ending are both selected ascending or descending arpeggios;
  • the harmony is randomly selected from the corresponding original chords, sixth chords, fourth and sixth chords, each The two beats appear once; the orchestration and rhythm use a large number of templates written by musicians as background tracks.
  • the music elements are arranged by corresponding four arpeggio sequences, including harmony, orchestration, and rhythm.
  • the preset composition rules include basic music theory, scales, arpeggios, harmony, polyphony, Orchestration, rhythm and melody structure, etc., need to correspond to different song styles and song emotions respectively.
  • By analyzing the melody of the arpeggio sequence select the best chord for accompaniment, and then determine the accompaniment sound according to the selected song style and song emotion.
  • Type, orchestration, and rhythm Specifically, the user enters the three starting sounds mi, la, and xi through the simulated piano keyboard on the UI interface, and selects the song style as folk songs and the song emotion as nostalgia.
  • the pattern corresponds to the gentle and beautiful style of the Arpeggio sequence, and chooses a gentle, smooth and beautiful harmony in the music library according to the accompaniment pattern, song style and song emotion, and then presets the composition rules according to the selected song style and song emotion Select the accompaniment instrument as the gourd, and then synthesize the four arpeggio sequences and the harmony played by the gourd to add the accompaniment rhythm and accompaniment of the most suitable user-selected song style and song emotion to the four arpeggio sequences.
  • Musical instruments to enrich the content of the work.
  • the song style selected by the user is rock and the emotion of the song is happy
  • the three start notes of mi, la, and xi are first decomposed into three chords, and then the chords are transposed to generate four arpeggios corresponding to the chords.
  • Sequence then analyze and arrange the melody of the four arpeggio sequences according to the preset composition rules, make the melody of the four arpeggio sequences correspond to the shock and fast-paced style of rock, and determine the four arpeggio sequences.
  • the accompaniment pattern corresponds to the rock style, so select the heavy metal harmony in the music library, and select the accompaniment instrument for the drum and electronic guitar through preset composition rules, and then change the arpeggio sequence and the drum and The accompaniment of the electronic guitar is used to synthesize the harmonies, and finally output the four-segment arpeggio sequence that completes the music elements of the four-segment arpeggio sequence.
  • the three starting sounds of mi, la, and xi are first decomposed and then performed.
  • Chord inversion randomly generate four arpeggio sequences corresponding to the chord.
  • the music library includes all the possibilities for the decomposition of the third chord.
  • the arpeggio sequence is input into the preset composition rule.
  • the preset composition rule analyzes the melody of the four-segment arpeggio sequence, and then re-arranges the four-segment arpeggio sequence melody according to the popular style selected by the user and the fresh mood mode to conform to the popular And fresh style characteristics, and determine the popular and fresh style accompaniment patterns that match the four arpeggio sequences, select the harmony that corresponds to the song style and song emotion from the music library, and the accompaniment instruments are guitars and drums, etc. , And play to generate accompaniment harmonies completed by guitars and drums, and finally synthesize four arpeggio sequences and accompaniment harmonies to output a complete process.
  • step S107 the method includes:
  • the ending of the ending is set to the root of the third chord, and the ending of the ending sound stays at the root of the third chord to make the song officially end.
  • step S107 the method includes:
  • a song corresponding to the song format is generated.
  • a selection box pops up to let the user select the song format.
  • Song formats include MIDI, MP3, and staff notation. The user selects one of MIDI, MP3, and staff notation. After the user makes a selection, according to the song mode selected by the user, Continue to generate songs, users choose the format of the generated songs according to their preferences or habits, in order to better read and understand the song information.
  • step S107 the method includes:
  • the duration of the song adjust the target and the duration of the main melody according to the preset proportions of the total length of the intro, intro, interlude, ending, and main melody;
  • a pop-up selection box for the user to select the song duration is displayed.
  • the song duration includes 30 seconds, 60 seconds, and 90 seconds.
  • the user selects one of 30 seconds, 60 seconds, and 90 seconds.
  • the length of the song selected by the user according to the preset proportions of the intro, intro, interlude, ending, and main melody respectively, adjust the target and main melody duration to generate a song corresponding to the duration of the song. Different, the intro, intro, interlude, ending, and main melody each have different preset proportions for the total duration.
  • the user selects the duration of the song according to their preferences or habits to better adapt to the user's listening habits.
  • the percentage of the total duration of each part is approximately: 20% intro, 10% intro, 40% in melody, 10% in interlude, 20% in end; 30-second songs: Intro 6s, Interlude 3s, Main Melody 12s, Interlude 3s, Endo 6s; Songs of 60 seconds duration: Intro 12s, Prelude 6s, Main Melody 24s, Interlude 6s, Endo 12s.
  • step S107 the method includes:
  • the generated songs are sorted and stored according to the selected song type.
  • Songs are sorted and stored, including pop, classical, jazz, folk, happy, sad, fresh and nostalgic. Specifically, the songs are classified according to the song types selected by the user, so that the songs are labeled with tags corresponding to the selected song types, which facilitates the management of the composed songs.
  • step S107 the method includes:
  • accompaniment tracks By adding accompaniment tracks to songs, such as piano, guitar, bass, and drums, etc., specifically, by obtaining accompaniment files corresponding to the selected song type in the music library and synthesizing multi-track works with the generated songs, the work is made More plump and more contagious.
  • the method After adding the generated song to the accompaniment track and performing a mixing operation to obtain a multi-track work, the method includes:
  • the generated multi-track song is synthesized with a pre-recorded human voice source file to obtain a song audio file.
  • the pre-established preset composition rules and music library are used for composition.
  • the music library contains a large number of songs and is classified according to the song style and song emotional tags.
  • the preset composition rules include substrate music theory, scales, arpeggios, and harmony. , Polyphony, orchestration, rhythm, and melody structure, corresponding to different song styles and song emotional tags.
  • the harmony theory three chords are decomposed by the user and then chord inversion is performed. Randomly generated Four arpeggio sequences corresponding to chords, and then the corresponding music elements of the four arpeggio sequences are arranged according to the preset composition rules and the song style and song emotion selected by the user.
  • the main melody is randomly selected and adjusted in the music library.
  • the ending of the ending is set to the root of the third chord.
  • the five music pieces are stitched in order, and the song is finally output.
  • the songs are created automatically, and the song creation efficiency is high, and the song style and song emotion selected by the user are added to the generated songs, which conforms to the user's preferences and improves the user experience.
  • the song is generated according to the preset composition rules by the user's starting sound and song type. It does not require the user to have a certain knowledge of music theory, and the user can compose. The purpose is to solve the existing automatic arrangement software that requires the user to have a certain Only the knowledge of music theory can be used smoothly.
  • an embodiment of the present invention provides an automatic composition device 1.
  • the device 1 includes a first acquisition module 11, a processing module 12, an arpeggio sequence generation module 13, a second acquisition module 14, a first acquisition module 15, The second obtaining module 16 and the song generating module 17.
  • the first obtaining module 11 is configured to obtain more than three start sounds input by a user.
  • More than three start sounds input by the user are obtained.
  • three start sounds input by the user are obtained.
  • composition UI interface the user clicks to create a new song, and enters more than three of the multiple notes.
  • the first obtaining module 11 includes:
  • the first sub-click acquisition module is used to acquire more than three start sounds input by a user clicking a virtual button.
  • the initial sound is displayed by using a virtual key to simulate a piano keyboard.
  • the first obtaining module 11 includes:
  • the first sub-peripheral acquisition module is configured to acquire more than three start sounds input by a user using a peripheral.
  • the automatic composition device is connected to an external device, and the user inputs more than three start sounds through the external device.
  • the external device as an electronic keyboard as an example
  • the electronic keyboard by connecting with the electronic keyboard, when the user plays the electronic keyboard At this time, the electronic keyboard generates and outputs electric signals corresponding to the notes played by the user, and according to the electric signals, three or more starting sounds played by the user can be obtained, which is convenient for the user.
  • the first obtaining module 11 includes:
  • the first sub-speech acquisition module is configured to acquire more than three start sounds of a voice input.
  • the user hums three or more start sounds, receives three or more start sounds from the user, and extracts three or more start sounds, simplifying the acquisition of three or more start sounds, even if he does not understand how to operate Users of piano keyboards can also create music by humming, which is convenient for users to input the initial sound.
  • the processing module 12 is configured to perform chord decomposition on three or more starting sounds input by the user and perform chord inversion after the chord decomposition according to the harmony theory.
  • the arpeggio sequence generating module 13 is configured to randomly generate four arpeggio sequences corresponding to the chords after the chords are transposed.
  • the three or more starting sounds obtained by the user are processed.
  • the processing method is to perform chord decomposition first, and then perform chord inversion. After the chord inversion is completed, four arpeggio sequences are randomly generated, where the four arpeggio sequences correspond to the chords.
  • chord decomposition of the three start sounds is specifically: adjusting three arbitrary start sounds to all within one octave, and naming the root sounds from low to high, Three and five tones.
  • chord transposition is performed.
  • the chord transposition is specifically: the chord with the lowest note is called the home chord, and the chord inversion is called with the third and fifth notes.
  • the third chord can have For two transpositions, the lowest transposition with three notes is the first transposition (sixth chord), and the transposition with the fifth note is the second transposition (fourth and sixth chords).
  • the arpeggio sequence is specifically: the arpeggio sequence is randomly selected from the corresponding original chords, six chords, four or six chords, and from low to high (up) or from high to low (down) ) Repeat regularly.
  • the second acquisition module 14 is configured to acquire a song type selected by the user.
  • the user After the user finishes entering more than three start sounds, the user is required to select a song type, and after the user finishes selecting the song type, the song type selected by the user is obtained.
  • the song type includes song style and song emotion.
  • the second obtaining module 14 includes:
  • the second sub-obtaining module is used to obtain the song style and song emotion selected by the user.
  • the song style pops up for the user to choose.
  • the song emotion pops up for the user to choose.
  • the user needs to choose an emotion from the song emotions.
  • the song type selected by the user is obtained. In the case where the user does not have knowledge of music theory, composition is performed by selecting a song type.
  • the second obtaining module 14 includes:
  • the second sub-obtaining module is used to obtain the song style selected by the user.
  • a song style pops up for the user to select, and after the user selects one of the song styles, the song type selected by the user is obtained.
  • composition is performed by selecting a song type.
  • the second obtaining module 14 includes:
  • the second sub-obtaining module is used to obtain the song emotion selected by the user.
  • the song emotion pops up for the user to select, and after the user selects one of the song emotions, the song type selected by the user is obtained.
  • composition is performed by selecting a song type.
  • the above-mentioned song styles include pop, classical, jazz and folk songs; the above-mentioned song emotions include happiness, sadness, freshness and nostalgia.
  • the first obtaining module 15 is configured to assign corresponding music elements to four arpeggio sequences according to preset composition rules and song types, and obtain intros, intros, endos, and endos;
  • the second obtaining module 16 is used to randomly tune a melody corresponding to a song type from the music library to obtain a main melody;
  • a song generating module 17 is used for selecting intro, intro, interlude and ending according to preset composition rules, and splicing the target and the main melody in order to generate a song.
  • the corresponding four elements of the arpeggio sequence are assigned. After completing the four elements of the arpeggio sequence, obtain Intro, Intro, Endo and Endo. After obtaining four pieces of intro, intro, end, and ending, according to the song type selected by the user, randomly select a corresponding melody from the music library to obtain the main melody.
  • the music library contains a large number of Song MIDI format, and classified by song style, song emotional tags.
  • the target is selected according to the preset composition rule. If the structure of the preset composition rule is five-section, the five-section pattern is intro, intro, main melody, end intro, and end intro, the target is selected as intro.
  • Intro, interlude, and ending if the preset composition structure in the composition rules is three-stage, the three-stage is the intro, main melody, and ending, then select the target as intro, ending, if By default, the composition structure in the composition rules is two-stage, and the two-stage composition is the intro and main melody. The target is selected as the intro. Take the five-section style as an example. After obtaining the intro, intro, end, and ending, randomly select a melody corresponding to the type of song from the music library to obtain the main melody. After the five pieces of music, interlude, ending, and main melody, the prelude, interlude, main melody, interlude, and endluo are spliced in order to generate songs and complete the composition. Compose according to the five intro, intro, intro, end, and main melody, making the composition difficult and efficient.
  • the preset composition rules are written according to the music rules, including basic music theory, scales, arpeggios, harmony, polyphony, orchestration, rhythm, and melody structure.
  • the preset composition rules are based on factors such as basic music theory, scales, arpeggios, harmony, polyphony, orchestration, rhythm, tempo, and melody structure, and different parameters are set for specific styles and emotions.
  • the scales use the blues scale
  • the arpeggios and harmonies perform the corresponding changes in the blues scale.
  • the orchestration uses the saxophone template, and the rhythm is mostly split.
  • the main melody is adjusted from the music library compiled by the musician according to the specific parameters of the selected style and emotion, and the existing melody segment is adjusted, and then the melody segment is horizontally, vertically, transposed, shifted, reflected, retrograde, enlarged, and reduced. Transform to increase the degree of freedom of the main theme.
  • the main accompaniment uses the corresponding style and emotion texture template written by the musician.
  • the song type selected by the user is sentimental.
  • the preset composition rules arrange basic music theory, scales, arpeggios, harmony, polyphony, orchestration, rhythm to the four arpeggio sequences, and make the four arpeggio sequences.
  • the obtained intro, intro, interlude, and ending are in a sad type, and the intro, prelude, interlude, and endluo are played to make the user listen. It feels sad.
  • the four arpeggio sequences include the first and second arpeggio sequences, both of which are ascending or descending arpeggio, and the third and fourth arpeggio sequences, which are both ascending or descending arpeggio.
  • the first selection module is used to select the first arpeggio sequence and the second arpeggio sequence as the arpeggio and intro arpeggio respectively;
  • the intro module is used to arrange the music elements required for the intro to the first arpeggio sequence according to preset composition rules and song types to obtain the intro;
  • Prelude module which is used to arrange the music elements required for the prelude to the second arpeggio sequence according to the preset composition rules and song types to obtain the prelude;
  • a second selection module configured to select the third arpeggio sequence and the fourth arpeggio sequence as the arpeggio of the interlude and the arpeggio of the ending;
  • the interlude module is used to arrange the music elements required for the interlude to the third arpeggio sequence according to the preset composition rules and song types to obtain the interlude;
  • the ending module is used to arrange the music elements required for the ending of the fourth arpeggio sequence according to the preset composition rules and song types to obtain the ending.
  • the intro and intro are both selected ascending or descending arpeggios, and the intro and ending are both selected ascending or descending arpeggios;
  • the harmony is randomly selected from the corresponding original chords, sixth chords, fourth and sixth chords, each The two beats appear once; the orchestration and rhythm use a large number of templates written by musicians as background tracks.
  • the music elements are arranged by corresponding four arpeggio sequences, including harmony, orchestration, and rhythm.
  • the preset composition rules include basic music theory, scales, arpeggios, harmony, polyphony, Orchestration, rhythm and melody structure, etc., need to correspond to different song styles and song emotions respectively.
  • By analyzing the melody of the arpeggio sequence select the best chord for accompaniment, and then determine the accompaniment sound according to the selected song style and song emotion.
  • Type, orchestration, and rhythm Specifically, the user enters the three starting sounds mi, la, and xi through the simulated piano keyboard on the UI interface, and selects the song style as folk songs and the song emotion as nostalgia.
  • the pattern corresponds to the gentle and beautiful style of the Arpeggio sequence, and chooses a gentle, smooth and beautiful harmony in the music library according to the accompaniment pattern, song style and song emotion, and then presets the composition rules according to the selected song style and song emotion Select the accompaniment instrument as the gourd, and then synthesize the four arpeggio sequences and the harmony played by the gourd to add the accompaniment rhythm and accompaniment of the most suitable user-selected song style and song emotion to the four arpeggio sequences.
  • Musical instruments to enrich the content of the work.
  • the song style selected by the user is rock and the emotion of the song is happy
  • the three start notes of mi, la, and xi are first decomposed into three chords, and then the chords are transposed to generate four arpeggios corresponding to the chords.
  • Sequence then analyze and arrange the melody of the four arpeggio sequences according to the preset composition rules, make the melody of the four arpeggio sequences correspond to the shock and fast-paced style of rock, and determine the four arpeggio sequences.
  • the accompaniment pattern corresponds to the rock style, so select the heavy metal harmony in the music library, and select the accompaniment instrument for the drum and electronic guitar through preset composition rules, and then change the arpeggio sequence and the drum and The accompaniment of the electronic guitar is used to synthesize the harmonies, and finally output the four-segment arpeggio sequence that completes the music elements of the four-segment arpeggio sequence.
  • the three starting sounds of mi, la, and xi are first decomposed and then performed.
  • Chord inversion randomly generate four arpeggio sequences corresponding to the chord.
  • the music library includes all the possibilities for the decomposition of the third chord.
  • the arpeggio sequence is input into the preset composition rule.
  • the preset composition rule analyzes the melody of the four-segment arpeggio sequence, and then re-arranges the four-segment arpeggio sequence melody according to the popular style selected by the user and the fresh mood mode to conform to the popular And fresh style characteristics, and determine the popular and fresh style accompaniment patterns that match the four arpeggio sequences, select the harmony that corresponds to the song style and song emotion from the music library, and the accompaniment instruments are guitars and drums, etc. , And play to generate accompaniment harmonies completed by guitars and drums, and finally synthesize four arpeggio sequences and accompaniment harmonies to output a complete process.
  • the song generation module 17 includes:
  • the ending sound module is used to set the ending sound of the ending to the root of the third chord if the target includes the ending.
  • the ending of the ending is set to the root of the third chord, and the ending of the ending sound stays at the root of the third chord to make the song officially end.
  • the song generation module 17 includes:
  • the first sub-song format obtaining module is used to obtain the song format selected by the user
  • the second sub-generating module is configured to generate a song in a format corresponding to the song format according to the song format.
  • a selection box pops up to let the user select the song format.
  • Song formats include MIDI, MP3, and staff notation. The user selects one of MIDI, MP3, and staff notation. After the user makes a selection, according to the song mode selected by the user, Continue to generate songs, users choose the format of the generated songs according to their preferences or habits, in order to better read and understand the song information.
  • the song generation module 17 includes:
  • the first sub-song duration acquisition module is used to obtain the song duration selected by the user
  • the length adjustment module is used to adjust the duration of the target and the main melody according to the preset proportions of the total length of the intro, intro, interlude, and main melody according to the duration of the song;
  • the third sub-generating module is used to generate a song of a duration corresponding to the duration of the song.
  • a pop-up selection box for the user to select the song duration is displayed.
  • the song duration includes 30 seconds, 60 seconds, and 90 seconds.
  • the user selects one of 30 seconds, 60 seconds, and 90 seconds.
  • the length of the song selected by the user according to the preset proportions of the intro, intro, interlude, ending, and main melody respectively, adjust the target and main melody duration to generate a song corresponding to the duration of the song. Different, the intro, intro, interlude, ending, and main melody each have different preset proportions for the total duration.
  • the user selects the duration of the song according to their preferences or habits to better adapt to the user's listening habits.
  • the percentage of the total duration of each part is approximately: 20% intro, 10% intro, 40% in melody, 10% in interlude, 20% in end; 30-second songs: Intro 6s, Interlude 3s, Main Melody 12s, Interlude 3s, Endo 6s; Songs of 60 seconds duration: Intro 12s, Prelude 6s, Main Melody 24s, Interlude 6s, Endo 12s.
  • Device 1 includes:
  • the first classification storage module is configured to classify and store the generated songs according to the selected song type.
  • Songs are sorted and stored, including pop, classical, jazz, folk, happy, sad, fresh and nostalgic. Specifically, the songs are classified according to the song types selected by the user, so that the songs are labeled with tags corresponding to the selected song types, which facilitates the management of the composed songs.
  • Device 1 includes:
  • the first multi-track generating module is configured to add the accompaniment track to the generated song and perform a mixing operation to obtain a multi-track work.
  • accompaniment tracks By adding accompaniment tracks to songs, such as piano, guitar, bass, and drums, etc., specifically, by obtaining accompaniment files corresponding to the selected song type in the music library and synthesizing multi-track works with the generated songs, the work is made More plump and more contagious.
  • the device 1 further includes:
  • a first synthesizing module is configured to synthesize the generated multi-track song with a pre-recorded human voice source file to obtain a song audio file.
  • the pre-established preset composition rules and music library are used for composition.
  • the music library contains a large number of songs and is classified according to the song style and song emotional tags.
  • the preset composition rules include substrate music theory, scales, arpeggios, and harmony. , Polyphony, orchestration, rhythm, and melody structure, corresponding to different song styles and song emotional tags.
  • the harmony theory three chords are decomposed by the user and then chord inversion is performed. Randomly generated Four arpeggio sequences corresponding to chords, and then the corresponding music elements of the four arpeggio sequences are arranged according to the preset composition rules and the song style and song emotion selected by the user.
  • the main melody is randomly selected and adjusted in the music library.
  • the ending of the ending is set to the root of the third chord.
  • the five music pieces are stitched in order, and the song is finally output.
  • the songs are created automatically, and the song creation efficiency is high, and the song style and song emotion selected by the user are added to the generated songs, which conforms to the user's preferences and improves the user experience.
  • the song is generated according to the preset composition rules by the user's starting sound and song type. It does not require the user to have a certain knowledge of music theory, and the user can compose. The purpose is to solve the existing automatic arrangement software that requires the user to have a certain Only the knowledge of music theory can be used smoothly.
  • a computer device is also provided in the embodiment of the present application.
  • the computer device may be a server, and its internal structure may be as shown in FIG. 3.
  • the computer device includes a processor, a memory, a network interface, and a database connected through a system bus.
  • the computer design processor is used to provide computing and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system, computer-readable instructions, and a database.
  • the memory provides an environment for operating systems and computer-readable instructions in a non-volatile storage medium.
  • the database of the computer equipment is used to store data such as models of the automatic composition method.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection.
  • the computer-readable instructions are executed by a processor to implement an automatic composition method.
  • the above processor executes the steps of the above-mentioned automatic composition method: obtaining more than three start sounds input by a user; performing chord decomposition on the three or more start sounds input by the user according to the harmony theory and performing the chord decomposition Chord inversion; after chord inversion, randomly generate four arpeggio sequences corresponding to the chords; obtain the song type selected by the user; according to the preset composition rule and the song type, the four arpeggios Arrange the corresponding music elements in the sound sequence to obtain the intro, intro, end, and end; randomly select a melody corresponding to the type of song from the music library to obtain the main melody; A target is selected from the intro, the intro, the interlude and the endluo, and the target and the main melody are spliced in order to generate a song.
  • the four arpeggio sequences include the first and second arpeggio sequences, both of which are ascending or descending arpeggios, and the third and fourth arpeggio sequences, which are both ascending or descending arpeggios.
  • the steps of assigning corresponding music elements to the four arpeggio sequences to obtain intro, intro, interlude, and ender include:
  • composition rule and the song type arrange the music elements required for the intro to the first arpeggio sequence to obtain the intro;
  • the fourth arpeggio sequence is arranged with the music elements required for the ending to obtain the ending.
  • a target is selected from among the intro, the intro, the interlude and the end, and the target and the main melody are spliced in order.
  • the steps to generate a song include:
  • the ending of the ending is set to the root of a third chord.
  • the step of obtaining the song type selected by the user includes:
  • the above-mentioned preset composition rules are written according to music rules, including basic music theory, scales, arpeggios, harmony, polyphony, orchestration, rhythm, and melody structure.
  • a target is selected from among the intro, the intro, the interlude and the end, and the target and the main melody are spliced in order.
  • the steps to generate a song include:
  • a song in a format corresponding to the song format is generated.
  • a target is selected from among the intro, the intro, the interlude and the end, and the target and the main melody are spliced in order.
  • the steps to generate a song include:
  • the target and the duration of the main melody are adjusted according to a preset proportion of the total length of the intro, the intro, the interlude, the end and the main melody, respectively.
  • a song of a duration corresponding to the duration of the song is generated.
  • FIG. 3 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied.
  • the computer device generates songs according to preset composition rules based on a start sound and a song type input by a user, and does not require the user to have a certain knowledge of music theory, and the user can compose, which aims to solve the existing automatic Arrangement software requires the user to have a certain knowledge of music theory before it can be used smoothly.
  • An embodiment of the present application further provides a computer non-volatile readable storage medium, which stores computer-readable instructions.
  • a computer non-volatile readable storage medium which stores computer-readable instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Electrophonic Musical Instruments (AREA)
  • Auxiliary Devices For Music (AREA)

Abstract

La présente invention concerne un procédé et un appareil de composition automatique, ainsi qu'un dispositif informatique et un support d'informations. Le procédé consiste à : réaliser une rupture d'accord et une inversion d'accord sur au moins trois notes de départ ; générer de façon aléatoire quatre séquences d'arpège ; orchestrer les quatre séquences d'arpège avec des éléments musicaux pour obtenir un prélude, un interlude, un postlude et une coda ; transférer de façon aléatoire un morceau de mélodie correspondant au type de chanson pour obtenir une mélodie principale ; et sélectionner une cible à partir du prélude, de l'interlude, du postlude et de la coda, et assembler la cible et la mélodie principale en séquence pour produire la chanson.
PCT/CN2018/108851 2018-06-29 2018-09-29 Procédé et appareil de composition automatique, et dispositif informatique et support d'informations Ceased WO2020000751A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810715376.9A CN109036355B (zh) 2018-06-29 2018-06-29 自动作曲方法、装置、计算机设备和存储介质
CN201810715376.9 2018-06-29

Publications (1)

Publication Number Publication Date
WO2020000751A1 true WO2020000751A1 (fr) 2020-01-02

Family

ID=65521361

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/108851 Ceased WO2020000751A1 (fr) 2018-06-29 2018-09-29 Procédé et appareil de composition automatique, et dispositif informatique et support d'informations

Country Status (2)

Country Link
CN (1) CN109036355B (fr)
WO (1) WO2020000751A1 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112435643A (zh) * 2020-11-20 2021-03-02 腾讯音乐娱乐科技（深圳）有限公司 生成电音风格歌曲音频的方法、装置、设备及存储介质
CN112785993A (zh) * 2021-01-15 2021-05-11 杭州网易云音乐科技有限公司 一种乐曲生成方法、装置、介质和计算设备
CN113936629A (zh) * 2021-10-12 2022-01-14 广州艾美网络科技有限公司 音乐文件处理方法和装置、音乐演唱设备
CN115631736A (zh) * 2022-08-31 2023-01-20 杭州网易云音乐科技有限公司 歌曲旋律创作方法、介质、装置和计算设备

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109616090B (zh) * 2018-12-24 2020-12-18 北京达佳互联信息技术有限公司 多音轨序列生成方法、装置、设备及存储介质
CN110136730B (zh) * 2019-04-08 2021-07-20 华南理工大学 一种基于深度学习的钢琴和声自动编配系统及方法
CN110085263B (zh) * 2019-04-28 2021-08-06 东华大学 一种音乐情感分类和机器作曲方法
CN114730550B (zh) * 2019-11-26 2025-10-17 索尼集团公司 信息处理装置、信息处理方法和信息处理程序
CN111046217B (zh) * 2019-12-17 2024-05-31 腾讯科技（深圳）有限公司 组合歌曲生成方法、装置、设备以及存储介质
CN113539215B (zh) * 2020-12-29 2024-01-12 腾讯科技（深圳）有限公司 音乐风格转换方法、装置、设备及存储介质
CN112863465B (zh) * 2021-01-27 2023-05-23 中山大学 基于上下文信息的音乐生成方法、装置及存储介质
CN113140202B (zh) * 2021-04-25 2024-06-18 北京灵动音科技有限公司 信息处理方法、装置、电子设备及存储介质
CN113299255A (zh) * 2021-05-13 2021-08-24 中国科学院声学研究所 基于深度神经网络和音乐元素驱动的情感音乐生成方法
CN114283766A (zh) * 2022-01-14 2022-04-05 天津大学 一种自动完成音乐创作模型的构建方法、系统及应用
CN117690397A (zh) * 2023-12-21 2024-03-12 广州酷狗计算机科技有限公司 旋律处理方法、装置、设备、存储介质及程序产品

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103902642A (zh) * 2012-12-21 2014-07-02 香港科技大学 利用歌词与旋律之间的相关性的音乐作曲系统
CN104391980A (zh) * 2014-12-08 2015-03-04 百度在线网络技术（北京）有限公司 生成歌曲的方法和装置
CN105632480A (zh) * 2014-11-20 2016-06-01 卡西欧计算机株式会社 自动作曲装置、方法
CN106652984A (zh) * 2016-10-11 2017-05-10 张文铂 一种使用计算机自动创作歌曲的方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003058152A (ja) * 2001-08-14 2003-02-28 Uubu Kk 楽曲自動生成装置
CN101800046B (zh) * 2010-01-11 2014-08-20 北京中星微电子有限公司 一种根据音符生成midi音乐的方法和装置
TWM531033U (zh) * 2016-07-01 2016-10-21 南臺科技大學 即時自動作曲播放裝置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103902642A (zh) * 2012-12-21 2014-07-02 香港科技大学 利用歌词与旋律之间的相关性的音乐作曲系统
CN105632480A (zh) * 2014-11-20 2016-06-01 卡西欧计算机株式会社 自动作曲装置、方法
CN104391980A (zh) * 2014-12-08 2015-03-04 百度在线网络技术（北京）有限公司 生成歌曲的方法和装置
CN106652984A (zh) * 2016-10-11 2017-05-10 张文铂 一种使用计算机自动创作歌曲的方法

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112435643A (zh) * 2020-11-20 2021-03-02 腾讯音乐娱乐科技（深圳）有限公司 生成电音风格歌曲音频的方法、装置、设备及存储介质
CN112785993A (zh) * 2021-01-15 2021-05-11 杭州网易云音乐科技有限公司 一种乐曲生成方法、装置、介质和计算设备
CN112785993B (zh) * 2021-01-15 2024-04-12 杭州网易云音乐科技有限公司 一种乐曲生成方法、装置、介质和计算设备
CN113936629A (zh) * 2021-10-12 2022-01-14 广州艾美网络科技有限公司 音乐文件处理方法和装置、音乐演唱设备
CN115631736A (zh) * 2022-08-31 2023-01-20 杭州网易云音乐科技有限公司 歌曲旋律创作方法、介质、装置和计算设备

Also Published As

Publication number Publication date
CN109036355A (zh) 2018-12-18
CN109036355B (zh) 2023-04-25

Similar Documents

Publication Publication Date Title
WO2020000751A1 (fr) Procédé et appareil de composition automatique, et dispositif informatique et support d'informations
US12039959B2 (en) Automated music composition and generation system employing virtual musical instrument libraries for producing notes contained in the digital pieces of automatically composed music
US11037538B2 (en) Method of and system for automated musical arrangement and musical instrument performance style transformation supported within an automated music performance system
US10854180B2 (en) Method of and system for controlling the qualities of musical energy embodied in and expressed by digital music to be automatically composed and generated by an automated music composition and generation engine
US10964299B1 (en) Method of and system for automatically generating digital performances of music compositions using notes selected from virtual musical instruments based on the music-theoretic states of the music compositions
US11024275B2 (en) Method of digitally performing a music composition using virtual musical instruments having performance logic executing within a virtual musical instrument (VMI) library management system
CN115004294B (zh) 编曲生成方法、编曲生成装置以及计算机程序产品
WO2025139724A1 (fr) Procédé et appareil de génération d'accompagnement musical, dispositif, support de stockage et produit programme
CN117789679A (zh) 音频处理方法、计算机设备和存储介质
Winter Interactive music: Compositional techniques for communicating different emotional qualities
Mazzola et al. Software Tools and Hardware Options
Dalmazzo et al. A Computer Application to Explore 53-Tone Equal Temperament Harmonies Through Modal Interchange

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06.04.2021)

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18925018

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 18925018

Country of ref document: EP

Kind code of ref document: A1