CN110299049A - A kind of intelligence of electronic music shows method - Google Patents
A kind of intelligence of electronic music shows method Download PDFInfo
- Publication number
- CN110299049A CN110299049A CN201910519625.1A CN201910519625A CN110299049A CN 110299049 A CN110299049 A CN 110299049A CN 201910519625 A CN201910519625 A CN 201910519625A CN 110299049 A CN110299049 A CN 110299049A
- Authority
- CN
- China
- Prior art keywords
- user
- phrase
- sound
- music score
- note
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000000694 effects Effects 0.000 claims abstract description 18
- 238000010183 spectrum analysis Methods 0.000 claims abstract description 10
- 238000012797 qualification Methods 0.000 claims abstract description 7
- 239000000284 extract Substances 0.000 claims abstract description 4
- 238000001228 spectrum Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000033764 rhythmic process Effects 0.000 description 3
- 208000027534 Emotional disease Diseases 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B15/00—Teaching music
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Technology (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Auxiliary Devices For Music (AREA)
- Electrophonic Musical Instruments (AREA)
Abstract
The present invention proposes that a kind of intelligence of electronic music shows method and apparatus, wherein, which comprises the setting song music score to be played of user extracts music score content, sound, tune and playing technique note annotation in music score is obtained, and spectrum analysis is carried out to skill sound；Subordinate sentence is carried out to music score, the phrase is clustered；To the phrase of the same category, preset using similar color, different color depths；To under the same classification, it is default to carry out highlighting for the note difference for note difference between phrase；The note that identification user's current time plays, and note is corresponded in music score；The phrase that identification user plays judges that user is intended to, and the prompting of different content is carried out to user when the note and score note difference that user plays；Identify user to the playing effect of skill sound, skill sound grade change music score on different according to qualification of the user to each skill sound.
Description
Technical field
The present invention relates to the intelligence of audio and text-processing field, in particular to electronic music to show method.
Background technique
During musical instrument is begun to learn or practices, the note of music score is not often known about.It needs to see music score on one side, plays on one side.
When bow see key and look up music score when, be often nervously fumbled, it is not known which sound oneself being bound on music score,
And the phrase of music has very high similitude mostly, needs the time to search and scrutinize back and forth constantly on music score, therefore right
Similar portion progress color highlights in music score, user can be helped to position well.Similar phrase in music score, often allows user
Ignore difference details therein, reduce playing effect, therefore to the small variations of similar phrase, progress color, which highlights, also to be had
Important function.
Although whether the note for currently having had some softwares that can identify that active user plays is bounced, sound
Happy practice is different from music performance, and learner often in his unfamiliar place, plays several times repeatedly.Therefore it only identifies
Whether the sound above current music score is bounced, and is inadequate.It also needs to identify, whether user refunds, and in front one
It repeats to practice in two phrases, system will not be thought as wrong performance, and performance error information continuously emerges.
During musical instrument practice, in the phrase that some comparisons have musical expression, playing technique is often used.
Playing skill of instruments is that there is advanced and rudimentary difficulty to distinguish.If some high level note user players drill always
It plays inaccurate, also will affect the practice enthusiasm of user.Need music score can be according to the performance level of current player, skill sound energy
The matching of Zhi Shiying is automatically carried out to player one by one.
Summary of the invention
The present invention provides a kind of intelligence of electronic music to show method, to solve the problems, such as that electronic music is not smart enough.
In a first aspect, the embodiment of the invention provides a kind of electronic musics intelligently to show method, comprising:
The music score to be played of user is set, music score content is extracted, including to musical alphabet, tune and the playing technique in music score
Sound is obtained, and carries out spectrum analysis to skill sound；The playing technique sound refers to is shown in the note upper right corner in music score
, show how the note should be added the specific mark that skill is played.
Subordinate sentence is carried out to music score, the phrase is clustered；
To the phrase of the same category, preset using similar color, different color depths；Described preset refers to, passes through
The result analyzed carrys out pre-set color, when waiting needs to show, so that it may be shown according to the color preset.
To under the same classification, note difference between phrase carries out highlighting for the note difference；
The note that identification user's current time plays, and note is corresponded in music score；The correspondence refers to will be used by software
Family according to music score play out come note, be mapped with music score content.
The phrase that identification user plays, record active user plays position of the phrase in music score, when the sound that user plays
When symbol is with score note difference, judge that user is intended to, and the different content is carried out to user and is reminded；
Identify that user changes on music score the playing effect of skill sound according to user to the qualification difference of each skill sound
Skill sound grade.
With reference to first aspect, described that subordinate sentence is carried out to music score in second of way of example of first aspect, to described
Phrase is clustered, comprising:
The duration of a sound for obtaining each sound in music score, obtains the last one sound in each trifle, as segmentation candidates sound.Obtain the candidate
The interval for dividing sound, compares the interval.The longest n segmentation candidates sound of interval is extracted, as segmentation sound.According to the segmentation sound
Carry out subordinate sentence.After subordinate sentence, when phrase is less than preset length, the shorter phrase in phrase sentence adjacent with left and right is closed
And redistribute phrase.
According to the musical alphabet and interval in phrase, the similarity between phrase is calculated, phrase is clustered, by similar pleasure
Sentence, as the same phrase classification；
Wherein, the similarity calculating method is carried out using the similarity calculation mode of editing distance, and clustering algorithm uses
Text cluster kit in scikit-learn kit is clustered, and the phrase classification of the music score of Chinese operas is obtained.
With reference to first aspect or its any embodiment, in the third way of example of first aspect, the needle
To the phrase of the same category, preset using similar color, different color depths, comprising:
To the phrase of the same category, the background color that should be shown when phrase is played is preset with Similar color, is used
Different color shows different classes of phrase background color.Different phrases in the same category, using Similar color, difference
Color depth show.
With reference to first aspect or its any embodiment, described right in the 4th kind of way of example of first aspect
Under the same classification, it is default to carry out highlighting for the difference note for note difference between phrase, comprising:
When user plays to current phrase, in the same classification, has discrepant sound with other phrases and highlighted；
The phrase variance analysis uses hash algorithm first, has discrepant phrase to phrase in the same classification and determines
Position, then to difference phrase, is matched using diff function, obtains difference tiny between phrase, and carry out to the difference
It highlights.
With reference to first aspect or its any embodiment, in the 5th kind of way of example of first aspect, the knowledge
The current sound that other user plays, and sound is corresponded to the sound in music score, comprising:
Obtain player currently plays note, and the fundamental frequency vibration frequency of the current sound issued according to musical instrument is converted to the pleasure of standard
Sound.The conversion, the frequency including identifying current note, which is corresponded on musical sound frequency spectrum, carries out frequency to the sound of frequency spectrum
Rate is corresponding, and the note after the conversion is corresponded on music score, obtains the corresponding correspondence note in music score of current performance sound；
With reference to first aspect or its any embodiment, in the 6th kind of way of example of first aspect, the identification is used
The phrase that family is played, record active user play position of the phrase in music score, when the note and score note that user plays not
Meanwhile judging that user is intended to, and the prompting of different content is carried out to user, comprising:
Continuous n note before the performance of user is recorded, searches for the current phrase of user in which of music score sentence, system
Constantly record user plays progress of the content in music score.
When content that user plays and music score are not inconsistent, successively judge user's intention, mainly include judge user whether because
It is jumped on other similar phrases to misunderstand, judges whether user is repeating one his unskilled sentence of practice, judge to use
Whether the note of mistake has really been played in family.
With reference to first aspect or its any embodiment, described to sentence in the 7th kind of way of example of first aspect
Whether disconnected user is jumped to because of misunderstanding on other similar phrases, comprising:
When the content that user plays and music score content are not inconsistent, to the pleasure for the phrase cluster classification identical as this that user currently plays
Sentence is matched, if there is the phrase that phrase and user play is even more like, to the reality of two phrases progress pre-set colors, and
To currently correctly highlighting to music score phrase, prompt is provided.
It is described to judge whether user is repeating one his unskilled phrase of practice, comprising:
When the content that user plays and music score content are not inconsistent, whether the phrase content that search user currently plays is repeated, and passes through phase
Like the mode that degree calculates, similarity calculation is carried out to the wrong content that user plays, if the music score that user repeatedly plays belongs to
The same phrase searches for the phrase, and according to described pre- using the music score content played near user as search order
If color the music score being matched to is highlighted.
It is described judge user whether really played mistake note, comprising: when judge user not to similar phrase into
Row is played, and also without the multiple practice of the same phrase of progress, is then judged as that performance mistake, system prompt user.
With reference to first aspect or its any embodiment tells knowledge in the 8th kind of way of example of first aspect
Playing effect of the other user to skill sound, skill change music score on different according to qualification of the user to each skill sound
Sound grade, comprising:
The current playing technique sound of user is obtained, spectrum analysis is carried out to the skill sound, with the authoritative playing effect audio
Frequency spectrum carries out similarity mode.If similarity is greater than certain threshold value, it is judged as that user's playing technique is correct, if similarity
Do not reach dependent thresholds, then judges user's playing technique mistake；
Each user's playing technique sound is obtained, judges that each skill sound plays the correctly number with performance mistake respectively.When certain
When skill is repeatedly played correctly or incorrectly, change music score skill sound grade；
The change skill sound grade, including, when the correct number of skill sound that user plays is greater than certain number, change the skill
The ingeniously difficulty on music score is changed to higher skill；When user's playing skill sound mistake is greater than certain threshold value, change skill
Sound is the skill of lower level.
Second aspect, the embodiment of the present invention also provide a kind of intelligent display device of electronic music, comprising:
Music score content extraction module, the music score content to be played for obtaining user obtain music score tune and playing technique note
Annotation.And extract playing effect authority's video of skill note annotation；
Music score subordinate sentence and cluster module, for carrying out subordinate sentence to the phrase in music score, sentence cluster of making merry of going forward side by side.
Music score color is changed the default of rule by music score color presets module, user；
Sound identification and logging modle are played, identifies and corresponds in music score for user currently to be played to sound, and record
Lower user played any sound；
Music score color control module carries out color presets for according to music score color presets module, currently playing user phrase,
Music score is highlighted according to current sound of playing, and provides different miscues when user plays mistake；
Music score playing technique modified module, user is according to user to the performance situation of skill sound, dynamic change playing technique sound.
Through the invention, music score model is segmented, and carries out the difference of color in the current phrase played of user
Variation display, while prominent current performance sound.And prominent current phrase can be recalled according to the practice conditions of user.When with
When family playing skill can not be up to standard, time update changes rudimentary skill of the sound on music score.
Reach following four technical effect by above method:
Firstly, can highlight to difference details in phrase similar in music score, user is helped to pay attention to playing in similar period
Difference sound promotes playing effect.
Secondly, can allow user rapidly according to music score color understand the music score similar phrase and front and back echo situation.?
Solve this uses what playing method and fixed finger mode.And find which section that current period belongs in music score, Bu Huiyin
For music score similar row and occur naked eyes frequent location of mistake the case where.
Again, it can repeat to practice a phrase in user to be that identification user is intended to, and then the performance progress of user, into
Row color highlights.
Finally, can be automatic to correct the difficulty that playing technique is added in music score according to user to the qualification of playing technique
Easy grade, not only whole first change, but according to the adept degree of user, the skill of the displaying more adaptability at individual character family
Sound is to user.
Detailed description of the invention
Fig. 1 is that the intelligence of electronic music of the invention shows the flow chart of embodiment of the method.
Fig. 2 is the electronic music schematic diagram of the embodiment of the present invention.
Fig. 3 is the schematic diagram of the embodiment of the present invention clustered to music score progress subordinate sentence to similar phrase.
Fig. 4 is the schematic diagram that phrase uses different colours to show in the music score of the embodiment of the present invention.
Fig. 5 is the structure chart of the intelligent display device embodiment of electronic music of the invention.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize that
Like that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes.
Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
The embodiment of the invention provides a kind of intelligence of electronic music to show method.It is specific as follows:
Step 100, the music score for setting the song to be played of active user.The tune for obtaining music score carries out subordinate sentence, identification to music score
Music score skill sound, and obtain the correct performance audio of skill sound.
It include tune in music score, such as by the format of image recognition ocr or the music score of Chinese operas itself, can obtain such as Fig. 2
The symbol of the Bb tune in the upper left corner is taken, and is stored into database.Similarly, the musical alphabet and interval of each available sound.Simultaneously
Obtain playing technique mark, such as the skills symbol such as trill (tr), folded sound (again), forte (>).And it can be obtained by network
When famous performing artist performs the skill sound, correct, the authoritative performance audio of use.
Playing technique is that have different representation method and playing method, they are player for different musical instruments
When practising the musical instrument, for improving study required for musical expression, the playing technique of specific various musical instruments can check religion section
The description of book, herein without repeating.
Spectrum analysis is carried out to the skill sound recording of online authoritative audio, librosa software can be used, carry out frequency spectrum point
Analysis obtains the frequency spectrum of these skill sounds, convenient followed by comparative analysis.
Step 101 carries out subordinate sentence according to interval to music score.Electronic music content is extracted, each sound of music score is obtained
The duration of a sound.Judge the last one sound in each trifle, obtain in music score the longest n of the sound interval, subordinate sentence is carried out according to the long.
After subordinate sentence, when phrase is less than preset length, shorter phrase in phrase sentence adjacent with left and right is merged.Again
Obtain phrase.
For example, as shown in Fig. 2, phrase first and second cutting, it can be by above-mentioned cutting method, because of judgement
In the music of song, the last sound of trifle, longest interval is 2 dieresis.Therefore, between first and second, can pass through
The cutting of 5-sounds.It is too long after writing phrase cutting, it can be divided according to having similar duration length between phrase
It cuts.
Step 102, musical alphabet and interval according to the sound in phrase.The similarity between phrase is calculated, phrase is gathered
Class.Wherein, the similarity calculating method is carried out using the similarity calculation mode of editing distance, and clustering algorithm uses
Text cluster kit in scikit-learn kit is clustered, and the phrase classification of the music score of Chinese operas is obtained.
To the phrase gathered in the same classification, with similar color but different depth is to be preset, and drills in user
When playing this music, it is shown as preset color.User is set to identify current phrase rapidly, and user can be according to pleasure
The similitude of sentence, using substantially similar playing technique.Because often having similitude and fascination between phrase, and music
Rhythm a little time delay will lead to rhythm and be disturbed, and beginner often examines since it is desired that watching qin spectrum again
The case where seeing key, leading to not to quickly find the current position for playing sound in the music score of Chinese operas, to belonging to the similar of different phrases
Phrase distinguishes, and user can be facilitated to distinguish the positioning of phrase position according to colour-difference, eyes are played and quickly position, played rapidly
Effect.User is also allowed to understand the probable ranges of similar phrase in music score simultaneously.
As shown in figure 3, second and the 6th, it can be aggregated to the same classification, third sentence is aggregated to the 7th meeting
The same classification.
Step 103, as shown in figure 4, the same category phrase, being preset when phrase is played with Similar color should show
Background color, different classes of phrase background color is shown using different color.Different phrases in the same category, are adopted
It is shown with Similar color, different color depths.
When user plays to current phrase, in the same classification, has discrepant sound with other phrases and highlighted；
The phrase variance analysis uses hash algorithm first, has discrepant phrase to phrase in the same classification and determines
Position, then to difference phrase, is matched using diff function, obtains difference tiny between phrase, and carry out to the difference
It highlights.Mode is highlighted, as shown in figure 3, display can be amplified, or change prospect to discrepant note
Color is shown.
Such as in Fig. 3, second and the 6th phrase belonged in same class, still there is difference in them.Such as
Second the 4th sound 5 from left to right, just two 55 playing methods with the 6th are had any different.If these sounds do not pay attention to
It arrives, can be easy to be ignored by player.Music score passes through these prominent differences, and the difference in these similar music score can be allowed to be drilled
It plays, more interesting to listen to music effect can be deduced.
The current sound that step 104, identification user play, and the sound in music score is corresponded to by sound is played.
Obtain player currently plays note, and the fundamental frequency vibration frequency of the current sound issued according to musical instrument is converted to standard
Musical sound.The conversion, the frequency including identifying current note, which is corresponded on musical sound frequency spectrum, to the sound of frequency spectrum into
Line frequency is corresponding, and the note after the conversion is corresponded on music score, obtains the corresponding correspondence in music score of current performance sound
Note；
The similar humming identification of the process or music retrieval, belong to the prior art.It is complete software can be retrieved by relevant musical
At.
The phrase that step 105, identification user play, record active user play position of the phrase in music score, work as user
When the note and score note difference played, judge that user is intended to, and the prompting of different content is carried out to user.
Continuous n note before the performance of user is recorded, searches for the current phrase of user in which of music score sentence,
What system constantly recorded user plays progress of the content in music score.
When content that user plays and music score are not inconsistent, successively judge user's intention, mainly include judge user whether because
It is jumped on other similar phrases to misunderstand, judges whether user is repeating one his unskilled sentence of practice, judge to use
Whether the note of mistake has really been played in family.
It is described to judge whether user is jumped to because of misunderstanding on other similar phrases, comprising:
When the content that user plays and music score content are not inconsistent, to the pleasure for the phrase cluster classification identical as this that user currently plays
Sentence is matched, if there is the phrase that phrase and user play is even more like, to the reality of two phrases progress pre-set colors, and
To currently correctly highlighting to music score phrase, prompt is provided.
The mode for providing prompt can be to similar phrase while carrying out the flashing of pre-set color, then will currently should
The phrase played is always on, and prompt user's performance should be this sentence.It can also be used in spectrum, near correct phrase
The prompt such as text importing " you play whether should be this sentence ".
It is described to judge whether user is repeating one his unskilled phrase of practice, comprising:
When the content that user plays and music score content are not inconsistent, whether the phrase content that search user currently plays is repeated, and passes through phase
Like the mode that degree calculates, similarity calculation is carried out to the wrong content that user plays, if the music score that user repeatedly plays belongs to
The same phrase searches for the phrase, and according to described pre- using the music score content played near user as search order
If color the music score being matched to is highlighted.
Highlighted mode, can be to phrase carry out pre-set color flashing, be also possible to fixed color, when with
The content that family is played more is consistent with the rhythm that phrase should be played originally, and the color of display is lighter, or provides and " play not
The encouragement and prompt of mistake " etc..
It is described judge user whether really played mistake note, comprising: when judge user not to similar phrase into
Row is played, and also without the multiple practice of the same phrase of progress, is then judged as that performance mistake, system prompt user.
The mode for providing prompt can be the flashing that pre-set color is carried out to phrase, or on music score, match in discovery
Near the note of mistake, prompted with text importing " playing mistake herein " etc..
Step 106, identification user to the playing effect of skill sound, according to user to the qualification of each skill sound not
Together, change the skill sound grade on music score.
The current playing technique sound of user is obtained, spectrum analysis is carried out to the skill sound, with the authoritative playing effect
Audible spectrum carries out similarity mode.If similarity is greater than certain threshold value, it is judged as that user's playing technique is correct, if phase
Do not reach dependent thresholds like degree, then judges user's playing technique mistake；
Spectrum analysis can use librosa software, and wherein MFCC algorithm can propose the audible spectrum of skill sound progress feature
It takes, similarity calculation then is done to the feature after extraction.Obtain the skill sound that user plays, if play with authoritative concert performer
It is similar.
Each user's playing technique sound is obtained, judges that each skill sound plays the correctly number with performance mistake respectively.
When certain skill is repeatedly played correctly or incorrectly, change music score skill sound grade；
The change skill sound grade, including, when the correct number of skill sound that user plays is greater than certain number, change the skill
The ingeniously difficulty on music score is changed to higher skill；When user's playing skill sound mistake is greater than certain threshold value, change skill
Sound is the skill of lower level.
The high low level of skill can carry out the high rudimentary switching of skill by the level of skill defined inside textbook.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment can
The mode of necessary general hardware platform can also be added to realize by software by software realization.Based on this understanding,
The technical solution of above-described embodiment can be embodied in the form of software products, which can store non-easy at one
In the property lost storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.
Claims (10)
1. a kind of electronic music intelligently shows method characterized by comprising
The music score to be played of user is set, music score content is extracted, including to musical alphabet, tune and the playing technique in music score
Sound is obtained, and carries out spectrum analysis to skill sound；The playing technique sound refers to is shown in the note upper right corner in music score
, show how the note should be added the specific mark that skill is played;
Subordinate sentence is carried out to music score, the phrase is clustered；
To the phrase of the same category, preset using similar color, different color depths；Described preset refers to, passes through
The result analyzed carrys out pre-set color, when waiting needs to show, so that it may be shown according to the color preset;
To under the same classification, note difference between phrase carries out highlighting for the note difference；
The note that identification user's current time plays, and note is corresponded in music score；The correspondence refers to will be used by software
The note come is played out at family according to music score, is mapped with music score content;
The phrase played of identification user, record active user play position of the phrase in music score, when the note that user plays with
When score note difference, judge that user is intended to, and the different content is carried out to user and is reminded；
Identify that user changes on music score the playing effect of skill sound according to user to the qualification difference of each skill sound
Skill sound grade.
2. according to the method described in claim 1, wherein, the setting song music score to be played of user, to music score content into
Row extracts, and obtains to sound, tune and the playing technique note annotation in music score, and carry out spectrum analysis, packet to skill sound
It includes:
Obtaining indicates on music score about the note of playing technique, while in teaching audio, the authority for extracting the skill sound is played
Effect audio, and spectrum analysis is carried out to playing effect audio by software, obtain playing technique sound spectrum.
3. it is described that subordinate sentence is carried out to music score according to the method described in claim 1, wherein, the phrase is clustered, is wrapped
It includes:
The duration of a sound for obtaining each sound in music score, obtains the last one sound in each trifle, as segmentation candidates sound;Obtain the candidate
The interval for dividing sound, compares the interval;The longest n segmentation candidates sound of interval is extracted, as segmentation sound;According to the segmentation sound
Carry out subordinate sentence;After subordinate sentence, when phrase is less than preset length, the shorter phrase in phrase sentence adjacent with left and right is closed
And redistribute phrase;
According to the musical alphabet and interval in phrase, the similarity between phrase is calculated, phrase is clustered, by similar phrase,
As the same phrase classification；
Wherein, the similarity calculating method is carried out using the similarity calculation mode of editing distance, and clustering algorithm uses
Text cluster kit in scikit-learn kit is clustered, and the phrase classification of the music score of Chinese operas is obtained.
4. method according to claim 1 or 3, wherein the phrase for the same category, using similar color,
Different color depths are preset, comprising:
To the phrase of the same category, the background color that should be shown when phrase is played is preset with Similar color, is used
Different color shows different classes of phrase background color;Different phrases in the same category, using Similar color, difference
Color depth show.
5. method according to claim 1 or 3, wherein described under the same classification, the note difference between phrase,
It is default to carry out highlighting for the difference note, comprising:
When user plays to current phrase, in the same classification, has discrepant sound with other phrases and highlighted；
The phrase variance analysis uses hash algorithm first, has discrepant phrase to phrase in the same classification and determines
Position, then to difference phrase, is matched using diff function, obtains difference tiny between phrase, and carry out to the difference
It highlights.
6. according to the method described in claim 1, wherein, the current sound that the identification user plays, and sound is corresponded into music score
In sound, comprising:
Obtain player currently plays note, and the fundamental frequency vibration frequency of the current sound issued according to musical instrument is converted to the pleasure of standard
Sound;The conversion, the frequency including identifying current note, which is corresponded on musical sound frequency spectrum, carries out frequency to the sound of frequency spectrum
Rate is corresponding, and the note after the conversion is corresponded on music score, obtains the corresponding correspondence note in music score of current performance sound.
7. according to the method described in claim 1, wherein, the phrase that the identification user plays, record active user plays pleasure
Position of the sentence in music score judges that user is intended to, and carry out not to user when the note and score note difference that user plays
With the prompting of content, comprising:
Continuous n note before the performance of user is recorded, searches for the current phrase of user in which of music score sentence, system
Constantly record user plays progress of the content in music score；When the content and music score that user plays are not inconsistent, successively judgement is used
Family is intended to, and mainly includes judging whether user is jumped to because of misunderstanding on other similar phrases, judges whether user is repeating
One his unskilled sentence of practice, judges whether user has really played the note of mistake.
8. method according to claim 5, wherein described to judge whether user jumps to other similar phrases because of misunderstanding
On, comprising:
When the content that user plays and music score content are not inconsistent, to the pleasure for the phrase cluster classification identical as this that user currently plays
Sentence is matched, if there is the phrase that phrase and user play is even more like, to the reality of two phrases progress pre-set colors, and
To currently correctly highlighting to music score phrase, prompt is provided；
It is described to judge whether user is repeating one his unskilled phrase of practice, comprising:
When the content that user plays and music score content are not inconsistent, whether the phrase content that search user currently plays is repeated, and passes through phase
Like the mode that degree calculates, similarity calculation is carried out to the wrong content that user plays, if the music score that user repeatedly plays belongs to
The same phrase searches for the phrase, and according to described pre- using the music score content played near user as search order
If color the music score being matched to is highlighted；
The note for judging user and whether really having played mistake, comprising: when judging that user do not drill similar phrase
It plays, also without the multiple practice of the same phrase of progress, is then judged as that performance mistake, electronic music system should carry out user
Prompt.
9. according to the method for right 1, wherein tell identification user to the playing effect of skill sound, according to user to each skill
The qualification of sound is different, changes the skill sound grade on music score, comprising:
The current playing technique sound of user is obtained, spectrum analysis is carried out to the skill sound, with the authoritative playing effect audio
Frequency spectrum carries out similarity mode；If similarity is greater than certain threshold value, it is judged as that user's playing technique is correct, if similarity
Do not reach dependent thresholds, then judges user's playing technique mistake；
Each user's playing technique sound is obtained, judges that each skill sound plays the correctly number with performance mistake respectively；When certain
When skill repeatedly plays correct or repeatedly wrong, change music score skill sound grade；
The change skill sound grade, including, when the correct number of skill sound that user plays is greater than certain number, change the skill
The ingeniously difficulty on music score is changed to higher skill；When user's playing skill sound mistake is greater than certain number, change skill
Sound is the skill of lower level.
10. a kind of intelligent display device of electronic music characterized by comprising
Music score content extraction module, the music score content to be played for obtaining user obtain music score tune and playing technique note
Annotation；And extract playing effect authority's video of skill note annotation；
Music score subordinate sentence and cluster module, for carrying out subordinate sentence to the phrase in music score, sentence cluster of making merry of going forward side by side；
Music score color is changed the default of rule by music score color presets module, user；
Sound identification and logging modle are played, identifies and corresponds in music score for user currently to be played to sound, and record
Lower user played any sound；
Music score color control module carries out color presets for according to music score color presets module, currently playing user phrase,
Music score is highlighted according to current sound of playing, and provides different miscues when user plays mistake；
Music score playing technique modified module, user is according to user to the performance situation of skill sound, dynamic change playing technique sound.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910519625.1A CN110299049B (en) | 2019-06-17 | 2019-06-17 | Intelligent display method of electronic music score |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910519625.1A CN110299049B (en) | 2019-06-17 | 2019-06-17 | Intelligent display method of electronic music score |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110299049A true CN110299049A (en) | 2019-10-01 |
| CN110299049B CN110299049B (en) | 2021-12-17 |
Family
ID=68027974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910519625.1A Active CN110299049B (en) | 2019-06-17 | 2019-06-17 | Intelligent display method of electronic music score |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110299049B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113076967A (en) * | 2020-12-08 | 2021-07-06 | 无锡乐骐科技有限公司 | Image and audio-based music score dual-recognition system |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002006835A (en) * | 2000-06-21 | 2002-01-11 | Yamaha Corp | Method and device for displaying data |
| US20020088334A1 (en) * | 2001-01-05 | 2002-07-11 | International Business Machines Corporation | Method and system for writing common music notation (CMN) using a digital pen |
| CN1591517A (en) * | 2003-09-01 | 2005-03-09 | 刘见平 | Music labelling method |
| EP1835503A2 (en) * | 2006-03-16 | 2007-09-19 | Sony Corporation | Method and apparatus for attaching metadata |
| CN204496755U (en) * | 2015-03-16 | 2015-07-22 | 周友仁 | A kind of intelligent piano Partner training device |
| CN106157973A (en) * | 2016-07-22 | 2016-11-23 | 南京理工大学 | Music detection and recognition methods |
| CN106203465A (en) * | 2016-06-24 | 2016-12-07 | 百度在线网络技术（北京）有限公司 | A kind of method and device generating the music score of Chinese operas based on image recognition |
| CN106340286A (en) * | 2016-09-27 | 2017-01-18 | 华中科技大学 | Universal real-time musical instrument playing evaluation system |
| CN107039024A (en) * | 2017-02-10 | 2017-08-11 | 美国元源股份有限公司 | Music data processing method and processing device |
| CN107680614A (en) * | 2017-09-30 | 2018-02-09 | 广州酷狗计算机科技有限公司 | Acoustic signal processing method, device and storage medium |
| CN108364528A (en) * | 2018-04-17 | 2018-08-03 | 南通理工学院 | Piano playing note correction system and method |
| CN109473084A (en) * | 2018-12-14 | 2019-03-15 | 广州沛乐科技有限公司 | Electronic music device |
| CN109522959A (en) * | 2018-11-19 | 2019-03-26 | 哈尔滨理工大学 | A kind of music score identification classification and play control method |
| CN109791758A (en) * | 2016-09-21 | 2019-05-21 | 雅马哈株式会社 | Musical performance training device and method |
-
2019
- 2019-06-17 CN CN201910519625.1A patent/CN110299049B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002006835A (en) * | 2000-06-21 | 2002-01-11 | Yamaha Corp | Method and device for displaying data |
| US20020088334A1 (en) * | 2001-01-05 | 2002-07-11 | International Business Machines Corporation | Method and system for writing common music notation (CMN) using a digital pen |
| CN1591517A (en) * | 2003-09-01 | 2005-03-09 | 刘见平 | Music labelling method |
| EP1835503A2 (en) * | 2006-03-16 | 2007-09-19 | Sony Corporation | Method and apparatus for attaching metadata |
| CN204496755U (en) * | 2015-03-16 | 2015-07-22 | 周友仁 | A kind of intelligent piano Partner training device |
| CN106203465A (en) * | 2016-06-24 | 2016-12-07 | 百度在线网络技术（北京）有限公司 | A kind of method and device generating the music score of Chinese operas based on image recognition |
| CN106157973A (en) * | 2016-07-22 | 2016-11-23 | 南京理工大学 | Music detection and recognition methods |
| CN109791758A (en) * | 2016-09-21 | 2019-05-21 | 雅马哈株式会社 | Musical performance training device and method |
| CN106340286A (en) * | 2016-09-27 | 2017-01-18 | 华中科技大学 | Universal real-time musical instrument playing evaluation system |
| CN107039024A (en) * | 2017-02-10 | 2017-08-11 | 美国元源股份有限公司 | Music data processing method and processing device |
| CN107680614A (en) * | 2017-09-30 | 2018-02-09 | 广州酷狗计算机科技有限公司 | Acoustic signal processing method, device and storage medium |
| CN108364528A (en) * | 2018-04-17 | 2018-08-03 | 南通理工学院 | Piano playing note correction system and method |
| CN109522959A (en) * | 2018-11-19 | 2019-03-26 | 哈尔滨理工大学 | A kind of music score identification classification and play control method |
| CN109473084A (en) * | 2018-12-14 | 2019-03-15 | 广州沛乐科技有限公司 | Electronic music device |
Non-Patent Citations (4)
| Title |
|---|
| APURVA A MEHTA ET AL: "Optical music notes recognition for printed piano music score sheet", 《2015 INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND INFORMATICS (ICCCI)》 * |
| 乐器社: "《https://www.musicbody.net/keyboard-course/36584.html》", 28 April 2018 * |
| 卡尔·莱默尔，瓦尔特·吉泽金著: "《现代钢琴演奏技巧》", 8 April 2015 * |
| 李碧: "基于卷积神经网络的钢琴音乐推荐算法研究", 《武汉工程大学硕士论文》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113076967A (en) * | 2020-12-08 | 2021-07-06 | 无锡乐骐科技有限公司 | Image and audio-based music score dual-recognition system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110299049B (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103824565B (en) | Humming music reading method and system based on music note and duration modeling | |
| US9659572B2 (en) | Apparatus, process, and program for combining speech and audio data | |
| CN103003875B (en) | Methods and systems for performing synchronization of audio with corresponding textual transcriptions and determining confidence values of the synchronization | |
| CN103165119B (en) | Karaoke method and system | |
| US7054817B2 (en) | User interface for speech model generation and testing | |
| US7778590B2 (en) | Game apparatus with music performance processing unit | |
| CN108769772A (en) | Direct broadcasting room display methods, device, equipment and storage medium | |
| CN106340286A (en) | Universal real-time musical instrument playing evaluation system | |
| CN105070283A (en) | Singing voice scoring method and apparatus | |
| TWI554984B (en) | Electronic device | |
| CN107103915A (en) | A kind of audio data processing method and device | |
| WO2006005533A2 (en) | Method for classifying music | |
| CN111081084B (en) | Method for broadcasting dictation content and electronic equipment | |
| CN108920450A (en) | A kind of knowledge point methods of review and electronic equipment based on electronic equipment | |
| CN107767850A (en) | A kind of singing marking method and system | |
| CN106611603A (en) | Audio processing method and audio processing device | |
| CN113010730A (en) | Music file generation method, device, equipment and storage medium | |
| JP3961544B2 (en) | GAME CONTROL METHOD AND GAME DEVICE | |
| CN110299049A (en) | A kind of intelligence of electronic music shows method | |
| CN105118490B (en) | Polyphony instrumental notes localization method and device | |
| CN105022993A (en) | Stave playing system based on image recognition technology | |
| CN105489209A (en) | Electroacoustic musical instrument rhythm controllable method and improvement of karaoke thereof | |
| CN105244021B (en) | Conversion method of the humming melody to MIDI melody | |
| CN109830221A (en) | A kind of singing guidance method and system | |
| JP5813844B2 (en) | Speech learning apparatus, method and program |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230714 Address after: Room 424, Building 2, No. 318, Waihuan West Road, University Town, Xiaoguwei Street, Panyu District, Guangzhou, Guangdong 510000 Patentee after: Guangzhou Xinqi Intelligent Technology Co.,Ltd. Address before: Room f101-12, No.1 incubation and production building, guanshao shuangchuang (equipment) center, Huake City, 42 Baiwang Avenue, Wujiang District, Shaoguan City, Guangdong Province, 512026 Patentee before: Shaoguan Qizhi Information Technology Co.,Ltd. |