CN113096624A - Method, device, equipment and storage medium for automatically creating symphony music - Google Patents
Method, device, equipment and storage medium for automatically creating symphony music Download PDFInfo
- Publication number
- CN113096624A CN113096624A CN202110311421.6A CN202110311421A CN113096624A CN 113096624 A CN113096624 A CN 113096624A CN 202110311421 A CN202110311421 A CN 202110311421A CN 113096624 A CN113096624 A CN 113096624A
- Authority
- CN
- China
- Prior art keywords
- music
- fragment
- symphony
- melody
- rhythm
- 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.)
- Granted
Links
Images
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
- G10H7/00—Instruments in which the tones are synthesised from a data store, e.g. computer organs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- 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
- G10H2210/341—Rhythm pattern selection, synthesis or composition
-
- 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
- G10H2250/00—Aspects of algorithms or signal processing methods without intrinsic musical character, yet specifically adapted for or used in electrophonic musical processing
- G10H2250/311—Neural networks for electrophonic musical instruments or musical processing, e.g. for musical recognition or control, automatic composition or improvisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Auxiliary Devices For Music (AREA)
- Electrophonic Musical Instruments (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to an automatic symphony music creation method, device, equipment and storage medium, which are used for realizing the automatic creation of symphony music. The automatic composition method of the symphony music comprises the following steps: acquiring initial information of a symphony melody to be created, generating a plurality of corresponding fragment units of the symphony melody by using a preset melody fragment generation algorithm according to the initial information, and combining the fragment units to obtain a plurality of melody fragments; and calculating the splicing integrity among different types of fragments in the plurality of music fragments according to a fragment recommendation algorithm in the sound effect feedback system, selecting N music fragments with higher splicing integrity from each type of fragments and pushing the N music fragments to a user, determining a music fragment from each type of fragments according to the selection of the user, and performing conversion processing on the determined music fragment to obtain the symphony music. Therefore, the automatic composition of the symphony music with the complete structure meeting the requirements of the user is realized.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an automatic making method, device, equipment and storage medium of a symphony melody.
Background
Music is an indispensable part of people's life, all has its usage in the aspect of life. In recent years, with the development of life, a harmony music piece has uses such as games and movie and television soundtracks in addition to being played at a concert.
However, for a large orchestral music piece containing a plurality of music chapters, such as a symphony music piece, because the music type structure is rigorous and the number of sound parts is large, energy is consumed during manual creation, and the selection of musical instruments is complicated during creation. Most of the existing automatic composition technologies are automatic composition of single melody or generation of second sound part, and there is no automatic composition method which can generate complete melody type symphony music according to the composition requirement.
Disclosure of Invention
The invention mainly aims to solve the technical problems that the music created by the existing automatic music creation technology is difficult to automatically create according to the requirements of users and the creation integrity is low.
The invention provides a method for automatically creating a symphony music in a first aspect, which comprises the following steps:
acquiring initial information of a symphony melody to be created, wherein the initial information comprises a melody structure of the symphony melody and basic parameters of the symphony melody, and the melody structure is determined based on the type of the symphony melody;
generating a plurality of corresponding segment units of the reverberation music by using a preset music segment generation algorithm according to the basic parameters, and combining the segment units to obtain a plurality of music segments, wherein the segment units comprise a plurality of note sequences with tones;
calculating splicing integrity among different types of fragments in the plurality of music fragments according to a fragment recommendation algorithm in a sound effect feedback system, and selecting N music fragments with higher splicing integrity from each type of fragments based on the splicing integrity and pushing the N music fragments to a client used by a user;
and determining a music fragment from each type of fragment according to the selection of the user, and performing transformation processing on the determined music fragment to obtain the reverberation music.
Optionally, in a first implementation manner of the first aspect of the present invention, the basic parameters include rhythm design data and a pitch span range, and the generating, according to the basic parameters, a plurality of corresponding fragment units of the reverberation music by using a preset music fragment generation algorithm, and combining the fragment units to obtain a plurality of music fragments includes:
generating a rhythm section by utilizing a rhythm generation algorithm in the music section generation algorithm according to the rhythm design data, wherein the rhythm section comprises a plurality of note sequences;
and adjusting the tone of the rhythm fragment by utilizing a tone generation algorithm in the music fragment generation algorithm according to the pitch span range to obtain a fragment unit.
Optionally, in a second implementation manner of the first aspect of the present invention, the generating, according to the rhythm design data, a rhythm section by using a rhythm generation algorithm in the music section generation algorithm includes:
and according to the rhythm cell design parameters of the single rhythm in the rhythm design data, carrying out combined processing on notes to obtain a plurality of rhythm cells, wherein the rhythm cells at least comprise the following four types of cells: first beat cells, second beat cells, third beat cells and fourth beat cells;
and selecting at least two cells from the four types of cells to be randomly combined according to the single-rhythm duration value in the rhythm design data to generate rhythm segments.
Optionally, in a third implementation manner of the first aspect of the present invention, the performing, according to the pitch span range, a tone adjustment process on the rhythm segment by using a tone generation algorithm in the music segment generation algorithm to obtain a segment unit includes:
and adjusting the tone of each note sequence in the rhythm fragment by decomposing chords, continuously grading, roundabout up and down and turning back up and down according to the pitch span range to obtain a fragment unit.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the generating, according to the basic parameter, a plurality of corresponding fragment units of the reverberation music by using a preset music fragment generation algorithm, and combining the fragment units to obtain a plurality of music fragments includes:
according to the basic parameters, overlapping the plurality of segment units to obtain segment units of multiple sound parts;
and splicing the multi-part fragment units to obtain a plurality of music fragments.
Optionally, in a fifth implementation manner of the first aspect of the present invention, before the acquiring initial information of a reverberation music to be created, the method further includes:
acquiring music information of the existing symphony music, and forming the music information into a music training set, wherein the music information comprises music scores;
and training a deep learning algorithm by using the music training set to obtain a fragment recommendation algorithm.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the determining a musical composition segment from each type of segment according to the selection of the user, and performing a transformation process on the determined musical composition segment to obtain the reverberation musical composition includes:
directly repeating, distributor changing or polyphonic changing the determined music fragment to obtain a changed music fragment;
and splicing the determined music fragment and the changed music fragment to obtain the symphony music.
A second aspect of the present invention provides an automatic composition apparatus of a symphony melody, comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring initial information of a symphony melody to be created, the initial information comprises a melody structure of the symphony melody and basic parameters of the symphony melody, and the melody structure is determined based on the type of the symphony melody;
the music fragment generating module is used for generating a plurality of corresponding fragment units of the reverberation music by using a preset music fragment generating algorithm according to the basic parameters and combining the fragment units to obtain a plurality of music fragments, wherein the fragment units are a plurality of note sequences with tones;
the feedback module is used for calculating the splicing integrity among different types of fragments in the music fragments according to a fragment recommendation algorithm in a sound effect feedback system, and selecting N music fragments with higher splicing integrity from each type of fragments based on the splicing integrity and pushing the N music fragments to a client used by a user;
and the music output module is used for determining a music fragment from each type of fragment according to the selection of the user and carrying out conversion processing on the determined music fragment to obtain the symphony music.
Optionally, in a first implementation manner of the second aspect of the present invention, the music piece generation module includes:
the rhythm generation unit is used for generating a rhythm segment by utilizing a rhythm generation algorithm in the music segment generation algorithm according to the rhythm design data, wherein the rhythm segment comprises a plurality of note sequences;
and adjusting the tone of the rhythm fragment by utilizing a tone generation algorithm in the music fragment generation algorithm according to the pitch span range to obtain a fragment unit.
Optionally, in a second implementation manner of the second aspect of the present invention, the rhythm generating unit includes:
a rhythm cell combination subunit, configured to combine the notes according to the rhythm cell design parameters of a single rhythm in the rhythm design data to obtain a plurality of rhythm cells, where the rhythm cells at least include the following four types of cells: first beat cells, second beat cells, third beat cells and fourth beat cells;
and the rhythm fragment generating subunit is used for selecting at least two cells from the four types of cells to be randomly combined according to the single-rhythm time value in the rhythm design data to generate the rhythm fragment.
Optionally, in a third implementation manner of the second aspect of the present invention, the tone generating unit is specifically configured to adjust the tone of each note sequence in the rhythm segment according to the pitch span range by processing manners of chord decomposition, continuous progression, detour up and down, and retrace up and down, so as to obtain a segment unit.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the music piece generation module includes:
the sound part generating unit is used for superposing the plurality of segment units according to the basic parameters to obtain segment units of the polyphonic parts;
and the music fragment generating unit is used for splicing the multi-part fragment units to obtain a plurality of music fragments.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the feedback module further includes:
the fragment recommendation algorithm unit is used for acquiring music information of the existing symphony music and forming the music information into a music training set, wherein the music information comprises music scores; training a deep learning algorithm by using the music training set to obtain a fragment recommendation algorithm;
and the feedback unit is used for selecting the N music fragments with higher splicing integrity from each type of fragment to push to the client used by the user based on the splicing integrity calculated by the fragment recommendation algorithm unit.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the music output module includes:
the fragment change unit is used for directly repeating, distributor changing or polyphonic changing the determined music fragment to obtain a changed music fragment;
and the splicing unit is used for splicing the determined music fragment and the changed music fragment to obtain the symphony music.
A third aspect of the present invention provides an automatic composition apparatus of a symphony melody, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor calls the instructions in the memory to cause the automated vocal music composition apparatus to execute the above-described automated vocal music composition method.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions which, when run on a computer, cause the computer to execute the above-described method of automatically composing a symphony melody.
In the technical scheme provided by the invention, the automatic making method of the symphony music comprises the following steps: acquiring initial information of a symphony melody to be created, wherein the initial information comprises a melody structure of the symphony melody and basic parameters of the symphony melody, and the melody structure is determined based on the type of the symphony melody; generating a plurality of corresponding segment units of the symphony melody by utilizing a preset melody segment generation algorithm according to the basic parameters, and combining the segment units to obtain a plurality of melody segments, wherein the segment units are a plurality of note sequences with tones; calculating splicing integrity among different types of fragments in the plurality of music fragments according to a fragment recommendation algorithm in the sound effect feedback system, and selecting N music fragments with higher splicing integrity from each type of fragments based on the splicing integrity and pushing the N music fragments to a client used by a user; and determining a music fragment from each type of fragment according to the selection of the user, and performing transformation processing on the determined music fragment to obtain the reverberation music. The symphony music with complete music structure and according with the psychological expectation of the user can be automatically generated according to the creative demand of the user.
Drawings
Fig. 1 is a schematic diagram of an embodiment of an automatic composition method of a reverberation music according to the embodiment of the present invention;
fig. 2 is a schematic diagram of another embodiment of the automatic composition method of a reverberation music in the embodiment of the present invention;
FIG. 3 is a diagram illustrating a rhythm segment generated in an embodiment of the present invention;
fig. 4 is a diagram showing another embodiment of the automatic composition method of a reverberation music in the embodiment of the present invention;
fig. 5 is a schematic diagram of another embodiment of the automatic composition method of a reverberation music in the embodiment of the present invention;
FIG. 6 is a diagram showing the morphological pattern of the rhythmic cells according to the embodiment of the present invention;
fig. 7 is a schematic diagram showing an embodiment of an automatic masker music composition apparatus according to the embodiment of the present invention;
fig. 8 is a schematic view of another embodiment of the automatic composition apparatus of a reverberation music in the embodiment of the present invention;
fig. 9 is a schematic diagram of an embodiment of an automatic masker music composition apparatus according to the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides an automatic symphony music creation method, device, equipment and storage medium, which are used for realizing the automatic creation of symphony music. The symphony music with complete music structure and according with the psychological expectation of the user can be automatically generated according to the creative demand of the user.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, an embodiment of the method for automatically creating a symphony melody in the embodiment of the present invention includes:
101. acquiring a melody structure of a symphony melody in initial information of the symphony melody to be created and basic parameters of the symphony melody;
it is understood that the execution subject of the present invention may be an automatic composition device of a symphony melody, or may be a terminal or a server, and is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
In this step, initial information of a symphony music to be authored is acquired through interaction with a user, the initial information including a melody structure and basic parameters of a symphony melody, wherein the melody structure is determined based on a type of the symphony melody.
The following describes the steps in this embodiment by taking a specific symphony music creation process as an example, and obtains initial information of a symphony music to be created through input or selection by a user, where the initial information includes a music structure of the music and basic parameters of the symphony music, and the basic parameters further include information such as an emotional style of the music, a tempo, and lengths of music structure portions of the symphony music. For example, when the currently desired vocal style is a rhythm style, the user selects a rhythm style from the interface provided in this embodiment, such as software or a web page, and inputs or selects information about the currently desired mood style, tempo, and the like. Wherein, the emotional style comprises generous, relaxing and relaxing, depression and depression, and the like; the tempo includes fast board, middle board, slow board, etc. The length information of each curved structure portion includes the number of small nodes of each curved structure. Since the music score includes three parts, i.e., a presentation part, an expansion part, and a playback part, the user needs to continue to select the length of each of the three parts, i.e., the number of small temples to be created.
102. Generating a plurality of corresponding fragment units of the symphony melody by using a preset melody fragment generation algorithm according to the basic parameters, and combining the fragment units to obtain a plurality of melody fragments;
next, a plurality of segment units of the reverberation music are generated by using a preset music segment generation algorithm according to the basic parameters acquired in the previous step, wherein the segment units comprise a plurality of note sequences with tones.
In the case of a music-on-demand method, first, segment units are generated in a part of the presentation unit, and the music generation algorithm can automatically generate segment units related to basic parameter information such as emotional style and tempo of music from the basic parameter information.
Specifically, the music generation algorithm needs to generate the rhythm and the tone of the segment unit according to the obtained basic parameters. The length of each generated fragment unit can be one section or several sections according to the basic parameter requirement. The segment units comprise rhythm segments with the same rhythm and pitch but different instruments used for playing or rhythm segments with the same rhythm and pitch and changed instruments used for playing. And after obtaining the plurality of the fragment units, combining the plurality of the fragment units, specifically, combining and splicing further comprises overlapping and splicing, and after combining, obtaining a plurality of music fragments generated by the presentation part.
103. Calculating splicing integrity among different types of fragments in the plurality of music fragments according to a fragment recommendation algorithm in the sound effect feedback system, and selecting N music fragments with higher splicing integrity from each type of fragments based on the splicing integrity and pushing the N music fragments to a client used by a user;
after the plurality of music pieces generated by the presentation part obtained in the above step are acquired, the plurality of acquired music pieces are identified by using a pre-trained piece recommendation algorithm, and the splicing integrity between the piece units in each music piece is calculated. The splicing integrity between each fragment unit comprises whether the parts spliced between the fragment units are well spliced or not, and no sudden change of pitch or a distributor and the like exists.
And arranging the music fragments according to the splicing integrity calculated by the fragment recommendation algorithm, generating trial listening audios for the music fragments with the splicing integrity arranged at the front N positions, and pushing the trial listening audios to a client used by a user according to the sequence of the splicing integrity so that the user can select the trial listening audios according to the scores of the splicing integrity.
104. And determining a music fragment from each type of fragment according to the selection of the user, and performing transformation processing on the determined music fragment to obtain the symphony music.
After the user selects a music piece according to the score of the splicing integrity and the trial listening audio, a certain music piece is obtained, that is, the creation for the presentation part is completed at this time.
The presentation unit, the expansion unit, and the reproduction unit have the same or similar parts as those of the presentation unit according to the feature of the tempo scheme, so that the selected music piece and the obtained music piece after the conversion processing can be spliced to obtain a complete reverberation music by performing the conversion according to the created presentation unit. Subsequently, the output of the music score and the harmony music audio can be performed by the selection of the user.
According to the embodiment of the invention, the reverberation music which accords with the psychological expectation of the user and has complete music type structure is automatically generated according to the acquired initial information of the reverberation music to be created.
Referring to fig. 2 and 3, another embodiment of the method for automatically creating a symphony melody according to the embodiment of the present invention includes:
201. acquiring a melody structure of a symphony melody in initial information of the symphony melody to be created and basic parameters of the symphony melody;
wherein the melody structure is determined based on a type of the symphony melody; the steps in this embodiment are described by taking a specific symphony music creation process as an example, and initial information of a symphony music to be created is obtained through input or selection of a user, where the initial information includes a music structure of the music and basic parameters of the symphony music, and the basic parameters further include information such as an emotional style of the music, a tempo, and lengths of music structure portions of the symphony music. For example, when the currently desired vocal style is a rhythm style, the user selects a rhythm style from the interface provided in this embodiment, such as software or a web page, and inputs or selects information about the currently desired mood style, tempo, and the like. Wherein, the emotional style comprises generous, relaxing and relaxing, depression and depression, and the like; the tempo includes fast board, middle board, slow board, etc.
The length information of each curved structure portion includes the number of minor segments of each curved structure, and the number of minor segments included in different length information is also different. Since the music score includes three parts, i.e., a presentation part, an expansion part, and a playback part, the user needs to continue to select the length of each of the three parts, i.e., the number of small temples to be created.
Further, the user may input or select rhythm design data and a pitch span range in this step, wherein the pitch span range may be a range of a register in the symphony music to be composed; therefore, the requirement style of the user is better determined, and the generated reverberation music in the embodiment can be closer to the psychological expectation of the user.
202. Generating rhythm fragments by utilizing a rhythm generation algorithm in a music fragment generation algorithm according to the rhythm design data;
firstly, a rhythm generation algorithm is established, wherein the rhythm generation algorithm is an algorithm for generating the rhythm according to the rhythm design data acquired in the step 201. The rhythm design data includes information of rhythm type desired to be generated by the user, and information of duration corresponding to duration of the whole note.
In a specific operation, firstly, the note is subjected to rhythm coding according to different durations, and a specific coding correspondence is shown in the following table 1:
TABLE 1 rhythm coding table
| Kind of note | Corresponding code |
| Whole musical note | 16 |
| Dotted dichotomous note | 12 |
| Dichotomous note | 8 |
| Dotted quarter note | 6 |
| Quarter note | 4 |
| Octant note | 2 |
| Sixteen-minute musical note | 1 |
Taking a rhythm style as an example, firstly, the rhythm section in the section unit is generated for the part of the presentation part according to rhythm design data, and the rhythm generation algorithm generates the rhythm section which is in accordance with the psychological expectation of the user by coding according to the information requirements of the rhythm type to be generated, the duration corresponding to the duration of the whole note and the like, and the length of the rhythm section generated each time can be a small bar or a plurality of small bars. Specifically, if the user needs to generate a section of rhythm with a uniformly-divided sound value, the rhythm is generated by using the rhythm coding according to the acquired rhythm design data, and specifically, a section of rhythm segment whose rhythm coding is [2, 2, 2, 2, 4] as shown in fig. 3 may be generated.
203. Adjusting the tones of the rhythm segments by utilizing a tone generation algorithm in a music segment generation algorithm according to the pitch span range to obtain segment units;
adjusting the tone of the rhythm segment obtained in step 202 according to the pitch span range input by the user, specifically, assigning a pitch value to the notes in the generated rhythm segment, randomly selecting a pitch as an initial pitch within a certain preset range for the first note in the obtained rhythm segment, and then sequentially adjusting the tone of the notes not containing the tone in the note sequence in the rhythm segment according to different tone generation rules until the tone of the current rhythm segment is adjusted, thereby obtaining a segment unit.
204. Combining the plurality of fragment units to obtain a plurality of music fragments;
after obtaining a plurality of the segment units in the previous step, combining the plurality of the segment units, specifically, combining and splicing further includes stacking and splicing;
the superposition in the combined splicing is mainly used for generating polyphonic parts of the symphony music to be generated. Specifically, as can be seen from the foregoing, the multiple fragment units obtained in the above step include multiple fragment units with similar rhythms but different pitches, and the fragment units are superimposed according to the rhythm points, and different instrument orchestrators are used for different fragment units, so as to obtain fragment units of multiple segments of polyphonic parts.
And then splicing the fragment units of the polyphones according to the acquired bar lengths of the presentation parts until a plurality of music fragments generated for the presentation parts are obtained.
205. Calculating splicing integrity among different types of fragments in the plurality of music fragments according to a fragment recommendation algorithm in the sound effect feedback system, and selecting N music fragments with higher splicing integrity from each type of fragments based on the splicing integrity and pushing the N music fragments to a client used by a user;
after the plurality of music pieces generated by the presentation part obtained in the above step are acquired, the plurality of acquired music pieces are identified by using a pre-trained piece recommendation algorithm, and the splicing integrity between the piece units in each music piece is calculated. The splicing integrity between each fragment unit comprises whether the parts spliced between the fragment units are well spliced or not, and no sudden change of pitch or a distributor and the like exists.
And arranging the music fragments according to the splicing integrity calculated by the fragment recommendation algorithm, generating trial listening audios for the music fragments with the splicing integrity arranged at the front N positions, and pushing the trial listening audios to a client used by a user according to the sequence of the splicing integrity so that the user can select the trial listening audios according to the scores of the splicing integrity.
206. And determining a music fragment from each type of fragment according to the selection of the user, and performing transformation processing on the determined music fragment to obtain the symphony music.
After the user selects a music piece according to the score of the splicing integrity and the trial listening audio, a certain music piece is obtained, that is, the creation for the presentation part is completed at this time. According to the characteristics of the music playing mode, the presentation part comprises a main part, a connecting section, an auxiliary part and a small tail end; there will be segments in the expansion part that present the key (i.e. the key of the main part in the presentation part) at different tonality; the reproduction section includes a section for reproducing the main section in the original tone. Therefore, the selected music fragment can be transformed according to the corresponding part, and the selected music fragment and the obtained transformed music fragment are spliced to obtain the complete reverberation music. Subsequently, the output of the music score and the harmony music audio can be performed by the selection of the user.
According to the embodiment of the invention, the reverberation music which accords with the psychological expectation of the user and has complete music type structure is automatically generated according to the acquired initial information of the reverberation music to be created.
Referring to fig. 4, another embodiment of the method for automatically creating a symphony melody according to the embodiment of the present invention includes:
401. acquiring a melody structure of a symphony melody in initial information of the symphony melody to be created and basic parameters of the symphony melody;
it is understood that the execution subject of the present invention may be an automatic composition device of a symphony melody, or may be a terminal or a server, and is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
In this step, initial information of a symphony music to be authored is acquired through interaction with a user, the initial information including a melody structure and basic parameters of a symphony melody, wherein the melody structure is determined based on a type of the symphony melody.
402. Generating a plurality of corresponding fragment units of the symphony melody by using a preset melody fragment generation algorithm according to the basic parameters, and combining the fragment units to obtain a plurality of melody fragments;
next, a plurality of segment units of the reverberation music are generated by using a preset music segment generation algorithm according to the basic parameters acquired in the previous step, wherein the segment units comprise a plurality of note sequences with tones.
In the case of a music-on-demand method, first, segment units are generated in a part of the presentation unit, and the music generation algorithm can automatically generate segment units related to basic parameter information such as emotional style and tempo of music from the basic parameter information.
Specifically, the music generation algorithm needs to generate the rhythm and the tone of the segment unit according to the obtained basic parameters. The length of each generated fragment unit can be one section or several sections according to the basic parameter requirement. The segment units comprise rhythm segments with the same rhythm and pitch but different instruments used for playing or rhythm segments with the same rhythm and pitch and changed instruments used for playing. And after obtaining the plurality of the fragment units, combining the plurality of the fragment units, specifically, combining and splicing further comprises overlapping and splicing, and after combining, obtaining a plurality of music fragments generated by the presentation part.
403. Acquiring music information of the existing symphony music, forming the music information into a music training set, and training a deep learning algorithm by using the music training set to obtain a fragment recommendation algorithm;
firstly, obtaining a plurality of symphony music samples, wherein the symphony music is labeled by using a manual labeling method to form a symphony training set, wherein the symphony training set comprises the integrity information of music.
The data in the symphony music training set are divided into a training set, a verification set and a test set, the deep learning algorithm is trained by using the information, specifically, the deep neural network is trained in the embodiment, and the trained segment recommendation algorithm is obtained.
404. Calculating the splicing integrity among different types of fragments in the plurality of music fragments according to a fragment recommendation algorithm, and selecting N music fragments with higher splicing integrity from each type of fragments based on the splicing integrity and pushing the N music fragments to a client used by a user;
and acquiring a plurality of music fragments generated by the presentation part and obtained in the previous step by using a trained fragment recommendation algorithm, identifying and calculating the splicing integrity among the fragment units in each music fragment. The splicing integrity between each fragment unit comprises whether the parts spliced between the fragment units are well spliced or not, and no sudden change of pitch or a distributor and the like exists.
And then arranging the music fragments according to the splicing integrity, generating trial listening audios for the music fragments with the splicing integrity arranged at the front N positions, and pushing the trial listening audios to a client used by a user according to the sequence of the splicing integrity so that the user can select the trial listening audios according to the score of the splicing integrity.
405. And determining a music fragment from each type of fragment according to the selection of the user, and performing transformation processing on the determined music fragment to obtain the symphony music.
After the user selects a music piece according to the score of the splicing integrity and the trial listening audio, a certain music piece is obtained, that is, the creation for the presentation part is completed at this time.
The presentation unit, the expansion unit, and the reproduction unit have the same or similar parts as those of the presentation unit according to the feature of the tempo scheme, so that the selected music piece and the obtained music piece after the conversion processing can be spliced to obtain a complete reverberation music by performing the conversion according to the created presentation unit. Subsequently, the output of the music score and the harmony music audio can be performed by the selection of the user.
According to the embodiment of the invention, the reverberation music which accords with the psychological expectation of the user and has complete music type structure is automatically generated according to the acquired initial information of the reverberation music to be created.
Referring to fig. 5 and 6, another embodiment of the method for automatically composing a vocal music according to the embodiment of the present invention includes:
501. acquiring a melody structure of a symphony melody in initial information of the symphony melody to be created and basic parameters of the symphony melody;
wherein the melody structure is determined based on a type of the symphony melody;
the steps in this embodiment are described by taking a specific symphony music creation process as an example, and initial information of a symphony music to be created is obtained through input or selection of a user, where the initial information includes a music structure of the music and basic parameters of the symphony music, and the basic parameters further include information such as an emotional style of the music, a tempo, and lengths of music structure portions of the symphony music. For example, when the currently desired vocal style is a rhythm style, the user selects a rhythm style from the interface provided in this embodiment, such as software or a web page, and inputs or selects information about the currently desired mood style, tempo, and the like. Wherein, the emotional style comprises generous, relaxing and relaxing, depression and depression, and the like; the tempo includes fast board, middle board, slow board, etc. The length information of each curved structure portion includes the number of small nodes of each curved structure. Since the music score includes three parts, i.e., a presentation part, an expansion part, and a playback part, the user needs to continue to select the length of each of the three parts, i.e., the number of small temples to be created.
Further, the user may input or select rhythm design data and a pitch span range in this step, wherein the pitch span range may be a range of a register in the symphony music to be composed; therefore, the requirement style of the user is better determined, and the generated reverberation music in the embodiment can be closer to the psychological expectation of the user.
502. Combining the notes according to the rhythm cell design parameters of the single rhythm in the rhythm design data to obtain a plurality of rhythm cells of four types; selecting at least two cells from the four types of cells to be randomly combined according to a single-rhythm duration value in rhythm design data to generate a rhythm segment;
first, a design parameter of a rhythm cell of a single rhythm included in rhythm data obtained in the previous step, that is, a chronaxie value of the rhythm cell is obtained, and a note is combined to obtain a plurality of rhythm cells, specifically, referring to fig. 6, wherein the rhythm cells are divided into four types, i.e., a first-beat cell, a second-beat cell, a third-beat cell and a fourth-beat cell, according to the length of the chronaxie value of the rhythm cell. And each cell has different sub-cell morphology, such as a beat of cells with a sub-cell composed of one quarter note, a sub-cell composed of two octants, etc.
In the rhythm generation process, according to the single-rhythm time value in the rhythm design data, extracting the daughter cells from the four cells at will for combination to obtain the rhythm segment with the length of the required single-rhythm time value. In a specific operation, the note is also subjected to rhythm coding according to different durations, and the specific coding is as described in the above embodiments and is not described herein again.
503. Adjusting the tone of each note sequence in the rhythm segment by processing modes of chord decomposition, continuous progressive, circuitous up and down, and foldback up and down according to the pitch span range to obtain a segment unit;
adjusting the tone of the rhythm segment obtained in the step 502 according to the pitch span range input by the user, specifically, assigning a pitch value to the notes in the generated rhythm segment, randomly selecting a pitch as an initial pitch within a certain preset range for the first note in the obtained rhythm segment, and then sequentially adjusting the tone of the notes in the note sequence in the rhythm segment according to different tone generation rules until the tone of the current rhythm segment is adjusted, thereby obtaining a segment unit.
The way of adjusting the tone includes decomposing the chord, continuously stepping, winding up and down, and turning back up and down, etc., specifically, the tone generation algorithm is as follows:
(1) if the note index i is 1, the note takes any one of values 55-75 midi;
(2) if the note index i! 1, the relationship between the note i and the note i-1 can be as follows:
firstly, chord decomposition:
the note pitch sequence is expressed as: p [ i ] +3| | p [ i ] + 4;
continuous progressive:
the note pitch sequence is expressed as: p [ i ] ═ p [ i ] + 2;
and (3) roundabout up and down:
the note pitch sequence is expressed as: p [ i ] + randint (2,3) | p [ i ] + -randint (2, 3);
folding back up and down:
the note pitch sequence is expressed as:
If I<＝4:p[i]＝p[i]+randint(2,3)else:p[i]＝p[i]+-randint(2,3)。
after the rhythm and the tone are generated, the rhythm and the tone are subjected to random matching of musical instruments according to the generated music score to generate a plurality of fragment units.
504. Superposing the plurality of segment units according to the basic parameters to obtain segment units of the polyphonic parts; splicing the multi-part fragment units to obtain a plurality of music fragments;
after obtaining a plurality of the segment units, combining the segment units, specifically, combining and splicing further comprises overlapping and splicing;
since a symphony melody generally has a plurality of vocal parts, a plurality of the above-described segment units are obtained, and then the obtained segment units are superimposed to obtain a segment unit having a polyphonic part, and the obtained segment units of the polyphonic part are spliced to obtain a plurality of melody segments generated for the presentation part.
505. Acquiring music information of the existing symphony music, forming the music information into a music training set, and training a deep learning algorithm by using the music training set to obtain a fragment recommendation algorithm;
firstly, obtaining a plurality of symphony music samples, wherein the symphony music is labeled by using a manual labeling method to form a symphony training set, wherein the symphony training set comprises the integrity information of music.
The data in the symphony music training set are divided into a training set, a verification set and a test set, the deep learning algorithm is trained by using the information, specifically, the deep neural network is trained in the embodiment, and the trained segment recommendation algorithm is obtained.
506. Calculating splicing integrity among different types of fragments in the plurality of music fragments according to a fragment recommendation algorithm in the sound effect feedback system, and selecting N music fragments with higher splicing integrity from each type of fragments based on the splicing integrity and pushing the N music fragments to a client used by a user;
and acquiring a plurality of music fragments generated by the presentation part and obtained in the previous step by using a trained fragment recommendation algorithm, identifying and calculating the splicing integrity among the fragment units in each music fragment. The splicing integrity between each fragment unit comprises whether the parts spliced between the fragment units are well spliced or not, and no sudden change of pitch or a distributor and the like exists.
And then arranging the music fragments according to the splicing integrity, generating trial listening audios for the music fragments with the splicing integrity arranged at the front N positions, and pushing the trial listening audios to a client used by a user according to the sequence of the splicing integrity so that the user can select the trial listening audios according to the score of the splicing integrity.
507. Directly repeating, distributor changing or polyphonic changing the determined music fragment to obtain a changed music fragment; and splicing the determined music fragment and the changed music fragment to obtain the reverberation music.
After the user selects a music piece according to the score of the splicing integrity and the trial listening audio, a certain music piece is obtained, that is, the creation for the presentation part is completed at this time. According to the characteristics of the music playing mode, the presentation part comprises a main part, a connecting section, an auxiliary part and a small tail end; there will be segments in the expansion part that present the key (i.e. the key of the main part in the presentation part) at different tonality; the reproduction section includes a section for reproducing the main section in the original tone. Therefore, a preset paragraph variation recommendation system can be adopted, a proper method is adopted through an intelligent algorithm, and different methods such as direct repetition, orchestration variation, polyphonic variation and the like are adopted to transform the selected music fragments according to corresponding parts, so that the music fragments are mutually related but have differences.
And splicing the selected music fragment and the obtained music fragment after the conversion processing to obtain the complete reverberation music. Subsequently, the output of the music score and the harmony music audio can be performed by the selection of the user.
According to the embodiment of the invention, the polyphonic music with complete structure and multiple vocal parts, which meets the psychological expectation of the user, is automatically generated according to the acquired initial information of the polyphonic music to be created.
The above description of the method for automatically creating a symphony melody in the embodiment of the present invention is provided, and referring to fig. 7, an embodiment of the apparatus for automatically creating a symphony melody in the embodiment of the present invention includes:
an obtaining module 701, configured to obtain initial information of a reverberation music to be created, where the initial information includes a melody structure of the reverberation music and basic parameters of the reverberation music, and the melody structure is determined based on a type of the reverberation music;
a music fragment generating module 702, configured to generate, according to the basic parameters, a plurality of fragment units corresponding to the reverberation music by using a preset music fragment generating algorithm, and combine the fragment units to obtain a plurality of music fragments, where the fragment units are a plurality of note sequences with tones;
the feedback module 703 is configured to calculate the splicing integrity between different types of the music clips according to a clip recommendation algorithm in the sound effect feedback system, and select N music clips with higher splicing integrity from each type of the clips based on the splicing integrity to be pushed to a client used by a user;
and the music output module 704 is used for determining a music fragment from each type of fragment according to the selection of the user and carrying out transformation processing on the determined music fragment to obtain the symphony music.
According to the embodiment of the invention, the reverberation music which accords with the psychological expectation of the user and has a complete music type structure can be automatically generated according to the acquired initial information of the reverberation music to be created.
Referring to fig. 8, another embodiment of the automatic composition apparatus of a reverberation music according to the present invention includes:
an obtaining module 701, configured to obtain initial information of a reverberation music to be created, where the initial information includes a melody structure of the reverberation music and basic parameters of the reverberation music, and the melody structure is determined based on a type of the reverberation music;
a music fragment generating module 702, configured to generate, according to the basic parameters, a plurality of fragment units corresponding to the reverberation music by using a preset music fragment generating algorithm, and combine the fragment units to obtain a plurality of music fragments, where the fragment units are a plurality of note sequences with tones;
the feedback module 703 is configured to calculate the splicing integrity between different types of the music clips according to a clip recommendation algorithm in the sound effect feedback system, and select N music clips with higher splicing integrity from each type of the clips based on the splicing integrity to be pushed to a client used by a user;
and the music output module 704 is used for determining a music fragment from each type of fragment according to the selection of the user and carrying out transformation processing on the determined music fragment to obtain the symphony music.
Optionally, the music piece generation module 702 includes:
a rhythm generating unit 7021, configured to generate a rhythm segment according to the basic parameter by using a rhythm generating algorithm in the music segment generating algorithm, where the rhythm segment is a plurality of note sequences;
a tone generating unit 7022, configured to generate a tone of the rhythm segment according to the basic parameter by using a tone generating algorithm in the musical-piece-generating algorithm, so as to obtain a segment unit.
Optionally, the rhythm generation unit 7021 includes:
the rhythm cell classification subunit is used for randomly combining the notes to obtain a plurality of rhythm cells, and dividing the plurality of rhythm cells into four cell types of a first beat cell, a second beat cell, a third beat cell and a fourth beat cell according to the duration of the rhythm cells;
and the rhythm cell combination subunit is used for randomly extracting the rhythm cells from the four cell types according to the basic parameters to be combined to generate the rhythm segment.
Optionally, the tone generating unit 7022 is specifically configured to:
and changing the tone of the note sequence in the rhythm segment by utilizing the tone generation algorithm according to the basic parameters to obtain a segment unit, wherein the tone generation algorithm comprises the steps of performing chord decomposition, continuous progression, upper and lower circuitous and upper and lower foldback processing on the note sequence.
Optionally, the music piece generation module 702 is further configured to:
and superposing the plurality of fragment units according to the basic parameters to obtain the fragment units of the polyphonic parts, and splicing the polyphonic part fragment units to obtain a plurality of music fragments.
Optionally, the feedback module 703 includes:
the segment recommendation algorithm unit 7031 is configured to obtain musical composition information of existing symphony musical compositions, and form the musical composition information into a musical composition training set, where the musical composition information includes musical compositions; training the deep neural network by using the music training set to obtain a fragment recommendation algorithm;
a feedback unit 7032, configured to select, based on the splicing integrity calculated by the segment recommendation algorithm unit 7031, the N music segments with higher splicing integrity from each type of segment to push to a client used by a user.
Optionally, the music output module 704 includes:
a section change unit 7041 configured to perform direct repetition, orchestration change, or polyphonic change on the determined music section to obtain a changed music section;
and the splicing unit 7042 is configured to splice the determined musical composition segments and the changed musical composition segments to obtain the reverberation musical composition.
According to the embodiment of the invention, the reverberation music which accords with the psychological expectation of the user and has a complete music type structure can be automatically generated according to the acquired initial information of the reverberation music to be created.
Fig. 7 and 8 above describe the automated composition apparatus of a symphony melody in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the automated composition apparatus of a symphony melody in the embodiment of the present invention in detail from the perspective of the hardware processing.
Fig. 9 is a schematic structural diagram of an automatic masker apparatus 900 according to an embodiment of the present invention, which may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 910 (e.g., one or more processors) and a memory 920, one or more storage media 930 (e.g., one or more mass storage devices) storing an application 933 or data 932. Memory 920 and storage media 930 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 930 may include one or more modules (not shown), each of which may include a series of instruction operations in the automatic reverberation music composition creation apparatus 900. Still further, the processor 910 may be configured to communicate with the storage medium 930 to execute a series of instruction operations in the storage medium 930 on the symphony melody automatic authoring apparatus 900.
The automated melodic music authoring apparatus 900 may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input-output interfaces 960, and/or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. It will be understood by those skilled in the art that the arrangement of the automated masker music composing apparatus shown in fig. 9 does not constitute a limitation of the automated masker music composing apparatus, and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
The invention also provides an automatic composition device of a symphony melody, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the automatic composition method of the symphony melody in the embodiments.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the method for automatically authoring a symphony melody.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An automatic composition method of a symphony melody, characterized by comprising:
acquiring initial information of a symphony melody to be created, wherein the initial information comprises a melody structure of the symphony melody and basic parameters of the symphony melody, and the melody structure is determined based on the type of the symphony melody;
generating a plurality of corresponding segment units of the reverberation music by using a preset music segment generation algorithm according to the basic parameters, and combining the segment units to obtain a plurality of music segments, wherein the segment units comprise a plurality of note sequences with tones;
calculating splicing integrity among different types of fragments in the plurality of music fragments according to a fragment recommendation algorithm in a sound effect feedback system, and selecting N music fragments with higher splicing integrity from each type of fragments based on the splicing integrity and pushing the N music fragments to a client used by a user;
and determining a music fragment from each type of fragment according to the selection of the user, and performing transformation processing on the determined music fragment to obtain the reverberation music.
2. The method of claim 1, wherein the basic parameters include rhythm design data and pitch span range, and the generating a plurality of fragment units of the reverberation music by using a preset music fragment generation algorithm according to the basic parameters and combining the fragment units to obtain a plurality of music fragments comprises:
generating a rhythm section by utilizing a rhythm generation algorithm in the music section generation algorithm according to the rhythm design data, wherein the rhythm section comprises a plurality of note sequences;
and adjusting the tone of the rhythm fragment by utilizing a tone generation algorithm in the music fragment generation algorithm according to the pitch span range to obtain a fragment unit.
3. The automated composition method of a symphony melody of claim 2, wherein the generating a melody fragment using a melody generation algorithm among the melody fragment generation algorithms according to the rhythm design data includes:
and according to the rhythm cell design parameters of the single rhythm in the rhythm design data, carrying out combined processing on notes to obtain a plurality of rhythm cells, wherein the rhythm cells at least comprise the following four types of cells: first beat cells, second beat cells, third beat cells and fourth beat cells;
and selecting at least two cells from the four types of cells to be randomly combined according to the single-rhythm duration value in the rhythm design data to generate rhythm segments.
4. The method of claim 3, wherein the adjusting the tones of the rhythm section according to the pitch span range by using a tone generation algorithm of the music section generation algorithms to obtain a section unit comprises:
and adjusting the tone of each note sequence in the rhythm fragment by decomposing chords, continuously grading, roundabout up and down and turning back up and down according to the pitch span range to obtain a fragment unit.
5. The method of claim 4, wherein the generating a plurality of corresponding fragment units of the reverberation music by using a preset music fragment generation algorithm according to the basic parameters and combining the fragment units to obtain a plurality of music fragments comprises:
according to the basic parameters, overlapping the plurality of segment units to obtain segment units of multiple sound parts;
and splicing the multi-part fragment units to obtain a plurality of music fragments.
6. An automated reverberation music composition creation method according to any one of claims 1 to 5, further comprising, before the obtaining of initial information of a reverberation music composition to be created:
acquiring music information of the existing symphony music, and forming the music information into a music training set, wherein the music information comprises music scores;
and training a deep learning algorithm by using the music training set to obtain a fragment recommendation algorithm.
7. An automatic composition method of a symphony melody according to any one of claims 1 to 5, wherein said determining a melody fragment from each type of fragment according to a user's selection and performing a conversion process on the determined melody fragment to obtain the symphony melody includes:
directly repeating, distributor changing or polyphonic changing the determined music fragment to obtain a changed music fragment;
and splicing the determined music fragment and the changed music fragment to obtain the symphony music.
8. An automatic composition apparatus of a symphony melody, characterized in that the automatic composition apparatus of a symphony melody includes:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring initial information of a symphony melody to be created, the initial information comprises a melody structure of the symphony melody and basic parameters of the symphony melody, and the melody structure is determined based on the type of the symphony melody;
the music fragment generating module is used for generating a plurality of corresponding fragment units of the reverberation music by using a preset music fragment generating algorithm according to the basic parameters and combining the fragment units to obtain a plurality of music fragments, wherein the fragment units comprise a plurality of note sequences with tones;
the feedback module is used for calculating the splicing integrity among different types of fragments in the music fragments according to a fragment recommendation algorithm in a sound effect feedback system, and selecting N music fragments with higher splicing integrity from each type of fragments based on the splicing integrity and pushing the N music fragments to a client used by a user;
and the music output module is used for determining a music fragment from each type of fragment according to the selection of the user and carrying out conversion processing on the determined music fragment to obtain the symphony music.
9. An automatic composition apparatus of a symphony melody, characterized by comprising:
a memory and at least one processor, the memory having instructions stored therein;
the at least one processor calls the instructions in the memory to cause the automated reverberation music composition authoring apparatus to execute the automated reverberation music composition authoring method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement a method of automatically authoring a symphony melody according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110311421.6A CN113096624B (en) | 2021-03-24 | 2021-03-24 | Automatic creation method, device, equipment and storage medium for symphony music |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110311421.6A CN113096624B (en) | 2021-03-24 | 2021-03-24 | Automatic creation method, device, equipment and storage medium for symphony music |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113096624A true CN113096624A (en) | 2021-07-09 |
| CN113096624B CN113096624B (en) | 2023-07-25 |
Family
ID=76669140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110311421.6A Active CN113096624B (en) | 2021-03-24 | 2021-03-24 | Automatic creation method, device, equipment and storage medium for symphony music |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113096624B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220066732A1 (en) * | 2020-08-26 | 2022-03-03 | Spotify Ab | Systems and methods for generating recommendations in a digital audio workstation |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6011212A (en) * | 1995-10-16 | 2000-01-04 | Harmonix Music Systems, Inc. | Real-time music creation |
| US20090272251A1 (en) * | 2002-11-12 | 2009-11-05 | Alain Georges | Systems and methods for portable audio synthesis |
| CN108228882A (en) * | 2018-01-26 | 2018-06-29 | 维沃移动通信有限公司 | The recommendation method and terminal device of a kind of audition for the songs segment |
| CN109119057A (en) * | 2018-08-30 | 2019-01-01 | Oppo广东移动通信有限公司 | Musical composition method, apparatus and storage medium and wearable device |
| CN109584851A (en) * | 2018-11-26 | 2019-04-05 | 成都云创新科技有限公司 | The method of computer music teaching creation |
| CN110324726A (en) * | 2019-05-29 | 2019-10-11 | 北京奇艺世纪科技有限公司 | Model generation, method for processing video frequency, device, electronic equipment and storage medium |
| CN110660375A (en) * | 2018-06-28 | 2020-01-07 | 北京搜狗科技发展有限公司 | Method, device and equipment for generating music |
| CN111680185A (en) * | 2020-05-29 | 2020-09-18 | 平安科技（深圳）有限公司 | Music generation method, music generation device, electronic device and storage medium |
| CN112258932A (en) * | 2020-11-04 | 2021-01-22 | 深圳市平均律科技有限公司 | Auxiliary exercise device, method and system for musical instrument playing |
-
2021
- 2021-03-24 CN CN202110311421.6A patent/CN113096624B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6011212A (en) * | 1995-10-16 | 2000-01-04 | Harmonix Music Systems, Inc. | Real-time music creation |
| US20090272251A1 (en) * | 2002-11-12 | 2009-11-05 | Alain Georges | Systems and methods for portable audio synthesis |
| CN108228882A (en) * | 2018-01-26 | 2018-06-29 | 维沃移动通信有限公司 | The recommendation method and terminal device of a kind of audition for the songs segment |
| CN110660375A (en) * | 2018-06-28 | 2020-01-07 | 北京搜狗科技发展有限公司 | Method, device and equipment for generating music |
| CN109119057A (en) * | 2018-08-30 | 2019-01-01 | Oppo广东移动通信有限公司 | Musical composition method, apparatus and storage medium and wearable device |
| CN109584851A (en) * | 2018-11-26 | 2019-04-05 | 成都云创新科技有限公司 | The method of computer music teaching creation |
| CN110324726A (en) * | 2019-05-29 | 2019-10-11 | 北京奇艺世纪科技有限公司 | Model generation, method for processing video frequency, device, electronic equipment and storage medium |
| CN111680185A (en) * | 2020-05-29 | 2020-09-18 | 平安科技（深圳）有限公司 | Music generation method, music generation device, electronic device and storage medium |
| CN112258932A (en) * | 2020-11-04 | 2021-01-22 | 深圳市平均律科技有限公司 | Auxiliary exercise device, method and system for musical instrument playing |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220066732A1 (en) * | 2020-08-26 | 2022-03-03 | Spotify Ab | Systems and methods for generating recommendations in a digital audio workstation |
| US11593059B2 (en) * | 2020-08-26 | 2023-02-28 | Spotify Ab | Systems and methods for generating recommendations in a digital audio workstation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113096624B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ames | Automated composition in retrospect: 1956-1986 | |
| Johnson-Laird | How jazz musicians improvise | |
| Liu et al. | Computational intelligence in music composition: A survey | |
| Dibben | The cognitive reality of hierarchic structure in tonal and atonal music | |
| Kirke et al. | A survey of computer systems for expressive music performance | |
| CN109036355B (en) | Automatic composing method, device, computer equipment and storage medium | |
| Kirke et al. | An overview of computer systems for expressive music performance | |
| JP3533975B2 (en) | Automatic composer and storage medium | |
| Zhou et al. | BandNet: A neural network-based, multi-instrument Beatles-style MIDI music composition machine | |
| Hill | Markov melody generator | |
| Özcan et al. | A genetic algorithm for generating improvised music | |
| CN113096624A (en) | Method, device, equipment and storage medium for automatically creating symphony music | |
| JP2010026337A (en) | Method, and program and device for creating song, and song providing system | |
| Jensen | Evolutionary music composition: A quantitative approach | |
| Dean et al. | Algorithmically-generated corpora that use serial compositional principles can contribute to the modeling of sequential pitch structure in non-tonal music | |
| JP7251684B2 (en) | Arrangement generation method, arrangement generation device, and generation program | |
| Moroni et al. | Evolutionary computation applied to algorithmic composition | |
| Oliwa | Genetic algorithms and the abc music notation language for rock music composition | |
| Vargas et al. | Artificial musical pattern generation with genetic algorithms | |
| JP3724347B2 (en) | Automatic composition apparatus and method, and storage medium | |
| KR20200048717A (en) | Method and apparatus for composing bridge music that connect two music | |
| Marsden | A study of cognitive demands in listening to Mozart's quintet for piano and wind instruments, k. 452 | |
| Colton et al. | Neuro-Symbolic Composition of Music with Talking Points | |
| KR20200047198A (en) | Apparatus and method for automatically composing music | |
| Zhu et al. | Bachmmachine: An interpretable and scalable model for algorithmic harmonization for four-part baroque chorales |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |