CN113793581B - Percussion intelligent education system based on motion detection auxiliary identification - Google Patents
Percussion intelligent education system based on motion detection auxiliary identification Download PDFInfo
- Publication number
- CN113793581B CN113793581B CN202111085548.7A CN202111085548A CN113793581B CN 113793581 B CN113793581 B CN 113793581B CN 202111085548 A CN202111085548 A CN 202111085548A CN 113793581 B CN113793581 B CN 113793581B
- Authority
- CN
- China
- Prior art keywords
- stick
- acceleration
- percussion
- motion detection
- education system
- 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.)
- Active
Links
- 238000009527 percussion Methods 0.000 title claims abstract description 45
- 238000001514 detection method Methods 0.000 title claims abstract description 22
- 230000001133 acceleration Effects 0.000 claims abstract description 78
- 230000005484 gravity Effects 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000010009 beating Methods 0.000 claims abstract description 16
- 230000009471 action Effects 0.000 claims abstract description 9
- 238000013528 artificial neural network Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 20
- 238000012937 correction Methods 0.000 claims description 19
- 238000003062 neural network model Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000003068 static effect Effects 0.000 claims description 5
- 210000000707 wrist Anatomy 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H1/00—Details of electrophonic musical instruments
- G10H1/0008—Associated control or indicating means
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Acoustics & Sound (AREA)
- Biophysics (AREA)
- Educational Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Electrophonic Musical Instruments (AREA)
Abstract
The invention relates to a percussion intelligent education system based on motion detection auxiliary identification, which comprises a drum stick, a drum set and a host, wherein an acceleration sensor and a gyroscope sensor are arranged on the drum stick; when the stick is in action, the rotation quantity is collected according to the gyroscope sensor, the current gravity acceleration is calculated based on the gravity acceleration value when the stick is stationary, then the current gravity acceleration is differenced with the data obtained by the current acceleration sensor, the acceleration of the stick after the gravity is removed is obtained, and finally the beating coordinate force of the stick is calculated by combining the head position of the stick; extracting audio features from the audio data; and identifying tone color and intensity through a neural network according to the audio characteristics and the striking coordinate intensity of the drum stick for scoring. Compared with the prior art, the method has the advantages of high recognition rate, accurate striking time acquisition, increased technical recognition and the like.
Description
Technical Field
The invention relates to the technical field of percussion music identification, in particular to a percussion music intelligent education system based on motion detection auxiliary identification.
Background
The existing percussion music identification adopts the method that the pronunciation of the percussion music is acquired through audio, the parameters such as short-time power spectrum, zero-crossing rate and the like of the audio are obtained through the analysis of the audio, and the audio initially belongs to the musical instrument. And then, dynamic time normalization is utilized to compare various musical instrument characteristic parameters (MFCC), and the types and the striking points of the musical instrument are obtained through methods such as editing distance, neural network learning and the like.
The invention discloses a musical instrument identification method and a system based on SE convolution network, wherein the method comprises the following steps: preprocessing the data to be identified, and converting the audio file to be identified into an autocorrelation spectrogram to be identified; the data to be identified are identified, the autocorrelation spectrogram to be identified is input into a pre-constructed instrument identification model for identification, and an output result matrix is obtained; and analyzing the musical instrument, namely integrating and analyzing an output result matrix of the musical instrument identification model into a musical instrument label of natural language representation.
The existing identification method has the defects that the identification rate of the system is low, the error of the identified instrument striking time is large, the smaller instrument sound is submerged by loud sound, and the striking action error cannot be pointed out.
Disclosure of Invention
The invention aims to overcome the defects of the prior art that the recognition rate of the system is low and the error of the striking time of the recognized musical instrument is large.
The aim of the invention can be achieved by the following technical scheme:
the utility model provides a percussion music intelligent education system based on motion detection auxiliary identification, includes stick, shelf drum and host computer, install acceleration sensor and gyroscope sensor on the stick, acceleration sensor and gyroscope sensor all communicate and connect the host computer, the host computer still is used for gathering the audio data of shelf drum, the data processing process of host computer includes following steps:
an initial correction step: at a static moment before the music starts, according to the detection value of the acceleration sensor, obtaining a gravity acceleration value, and determining the current position of the drum stick;
and (3) identifying the striking coordinate force: when the stick is in action, acquiring the rotation quantity of the stick according to the gyroscope sensor, calculating the current gravity acceleration according to the gravity acceleration value acquired in the initial correction step, then differencing with the data acquired by the current acceleration sensor to obtain the acceleration of the stick after removing the gravity, acquiring the position of the head of the stick based on the position of the stick, and finally calculating the beating coordinate force of the stick according to the momentum theorem;
an audio feature extraction step: extracting audio features according to the audio data;
a percussion music identification step: loading the audio characteristics and the beating coordinate force of the stick into a pre-established and trained beating recognition neural network model to obtain the tone color and force of the percussion instrument,
scoring: and according to the tone color and the intensity of the percussion instrument, giving a music score.
Further, the number of the acceleration sensors is three, and the three acceleration sensors are arranged in a pairwise orthogonal mode and are used for acquiring acceleration in three directions;
and in the initial correction step, triangular operation is carried out according to the gravity acceleration in three directions, and the current position of the drum stick is determined.
Further, the number of the gyro sensors is three, the three gyro sensors are arranged in a pairwise orthogonal mode and are used for acquiring rotation amounts in three directions, and the three gyro sensors correspond to the positions of the three acceleration sensors;
and according to the rotation quantity components in three directions acquired by the three gyroscope sensors, multiplying the rotation quantity components with the gravitational acceleration in three directions acquired in the initial correction step respectively to acquire the current gravitational acceleration.
Further, carrying out integral operation according to the acceleration of the drum stick after removing the gravity, obtaining a speed curve, and obtaining the position of the drum stick relative to the drum stick in the initial correction step according to the speed time; and obtaining the position of the head of the stick based on the position of the stick.
Further, the data processing process of the host further includes: determining the state of the stick according to the instantaneous change of the position of the head of the stick, wherein the state of the stick comprises translation, downward striking and rebound;
the scoring step includes: and according to the tone color, the dynamics and the state of the stick of the percussion instrument, giving out music scores.
Further, the data processing process of the host further includes: according to the proportion of the acceleration sensor and the gyroscope sensor, a force point of the drum stick is obtained, wherein the force point of the drum stick comprises a wrist and a whole body;
the scoring step includes: and giving out music scores according to the tone color, the dynamics, the state of the stick and the exertion point of the stick of the percussion instrument.
Further, in the audio feature extraction step, the audio feature is obtained by extracting the ADSR envelope variation of the time domain and the MFCC variation feature of the frequency domain in the audio data.
Further, according to the timbre and the dynamics obtained in real time, comparing the timbre and the dynamics with a preset hit score, and judging the hit accuracy, so that the music score is obtained.
Further, the training process of the hit recognition neural network model specifically comprises the following steps:
the method comprises the steps of obtaining training data, wherein the training data comprise model input data and actual striking action results, loading the training data into a pre-established striking recognition neural network model, and performing model training until a preset training stop condition is reached, so as to obtain a trained striking recognition neural network model.
Further, the strike recognition neural network model adopts a BP neural network.
Compared with the prior art, the invention has the following advantages:
(1) The recognition rate is improved: by reconstructing the beating position and combining the beating position parameters with the audio frequency, the recognition rate of the beating musical instrument and the beating coordinate force of the system can be improved;
(2) The striking time is accurate: the data of the acceleration sensor and the gyroscope sensor are used for calculating the acceleration of the drum stick after the gravity is removed, so that the striking action can be directly obtained, and the accurate striking time can be obtained;
(3) And (5) adding a manipulation identification: the states of the striking techniques and the force-exerting positions of the strikes can be obtained through the analysis of the acceleration and the gyroscope data, and education assistance is facilitated.
Drawings
Fig. 1 is a schematic hardware structure diagram of a percussion intelligent education system based on motion detection auxiliary recognition according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a percussion instrument tone color and strength recognition process of a percussion intelligent education system based on motion detection assisted recognition according to an embodiment of the present invention;
in the figure, 1 is a host, 2 is a drum stick, and 3 is a recorder.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1 and 2, the present embodiment provides a percussion intelligent education system based on motion detection auxiliary recognition, which comprises a drum stick 2, a drum set and a host computer 1, wherein an acceleration sensor and a gyroscope sensor are installed on the drum stick and are all in communication connection with the host computer, the host computer is further used for collecting audio data of the drum set through bluetooth communication connection in the embodiment, the audio data is collected through a recorder 3 in the embodiment, and the data processing process of the host computer comprises the following steps:
an initial correction step: at a static moment before the music starts, according to the detection value of the acceleration sensor, obtaining a gravity acceleration value, and determining the holding position of the current stick;
and (3) identifying the striking coordinate force: when the stick acts, the rotation quantity of the stick is collected according to the gyroscope sensor, the current gravity acceleration is calculated according to the gravity acceleration value obtained in the initial correction step, then the current gravity acceleration is differenced with the data obtained by the current acceleration sensor, the acceleration of the stick after removing the gravity is obtained, the position of the head of the stick is obtained based on the position of the stick, and finally the beating coordinate force of the stick is calculated according to the momentum theorem;
an audio feature extraction step: extracting audio features according to the audio data;
a percussion music identification step: loading the audio characteristics and the beating coordinate force of the stick into a pre-established and trained beating recognition neural network model to obtain the tone color and force of the beating instrument,
scoring: and (5) giving a music score according to the tone color and the intensity of the percussion instrument.
As a preferred embodiment, the number of the acceleration sensors is three, and the three acceleration sensors are orthogonally arranged in pairs and are used for acquiring acceleration in three directions;
in the initial correction step, triangular operation is carried out according to the gravity acceleration in three directions, and the position of the current drum stick is determined; the position where the stick is held when stationary is determined by the acceleration of gravity in three directions.
Further, as a preferred embodiment, the number of the gyro sensors is three, the three gyro sensors are arranged in a pairwise orthogonal manner and are used for acquiring rotation amounts in three directions, and the three gyro sensors correspond to the positions of the three acceleration sensors;
according to the rotation quantity components in three directions acquired by the three gyroscope sensors, multiplying the rotation quantity components with the gravitational acceleration in three directions acquired in the initial correction step respectively to acquire the current gravitational acceleration; the gyroscope sensor corresponds to the acceleration sensors in number and positions, so that component calculation is convenient, and the calculation accuracy is improved.
The striking coordinate force identification step comprises the steps of carrying out integral operation according to the acceleration of the stick after removing the gravity, obtaining a speed curve, and obtaining the position of the stick relative to the initial correction step according to the speed time; and based on the position where the stick is held, the position of the head of the stick is obtained.
As a preferred embodiment, the data processing process of the host further includes: determining the state of the stick according to the instantaneous change of the position of the head of the stick, wherein the state of the stick comprises translation, downward striking and rebound;
the scoring step comprises the following steps: and (5) giving out music scores according to the tone color, the dynamics, the state of the stick and the exertion point of the stick of the percussion instrument.
The identified state of the stick is added, and the state of the stick is also an element of performance scoring, so that the accuracy of scoring results can be improved.
Further, as a preferred embodiment, the data processing process of the host further includes: according to the proportion of the acceleration sensor and the gyroscope sensor, a force applying point of the drum stick is obtained, wherein the force applying point of the drum stick comprises a wrist and a whole body;
the scoring step comprises the following steps: and (5) giving out music scores according to the tone color, the dynamics, the state of the stick and the exertion point of the stick of the percussion instrument.
The method comprises the following steps: and (3) according to the real-time acquisition of tone color, strength, state of the stick and the force point of the stick, comparing with a preset percussion score and scoring standard, and judging the accuracy of percussion, thereby obtaining the score of the music.
The force application point of the stick is further added, and is also an element of performance grading, so that the accuracy of grading results can be further improved.
In a preferred embodiment, in the audio feature extraction step, the audio feature is obtained by extracting an ADSR envelope variation in the time domain and an MFCC variation feature in the frequency domain in the audio data.
In this embodiment, the training process of the hit recognition neural network model specifically includes:
the method comprises the steps of obtaining training data, wherein the training data comprises model input data and actual hitting action results, loading the training data into a pre-established hitting identification neural network model, and performing model training until a preset training stop condition is reached, obtaining a trained hitting identification neural network model, wherein the hitting identification neural network model adopts a BP neural network.
The above preferred embodiments are combined to obtain a preferred embodiment, and the preferred embodiment will be described in detail below.
The embodiment provides a percussion intelligent education system based on motion detection auxiliary identification, which consists of a host, a drum stick and a common drum set, wherein the host can directly record sound and analyze data. The intelligent drum stick is used for improving the drum stick of the percussion music, a gyroscope sensor and an acceleration sensor are added into the drum stick and are arranged at the hand-held position of the rear end, a wireless transmission chip is used for transmitting gyroscope acceleration information data to a host at regular time.
The detailed description is as follows:
1. and (3) correction:
before the music starts, a static moment is found, and when the three gyroscope sensors are zero, the drum stick is in a static state, and the system only has gravity acceleration. According to the principle that the combination of the three acceleration sensors is just one gravity acceleration, the three acceleration sensors are combined by physical triangle force and just coincide with the gravity acceleration. And when the positions are consistent, performing triangular operation on the combination force and the three component forces to obtain the current position of the drum stick.
The time difference of the transmission is corrected by the wireless time correction, and the clock error is corrected.
2. And (3) collecting:
and acquiring data of the acceleration sensor and the gyroscope sensor at fixed time to obtain the state of the drum stick, and transmitting the state to a host computer through a wireless system. The host directly collects audio data.
3. And (3) identification:
and reconstructing the position of the drum stick according to the characteristic values of the audio data, the acceleration sensor and the gyroscope sensor.
Calculating the rotation quantity of the drum stick through the data change of the three gyroscope sensors;
calculating the components of the current gravity acceleration in three axial directions through the rotation quantity and the gravity acceleration components during correction;
calculating the acceleration of the drum stick for removing the gravity according to the components of the current gravity acceleration in three axial directions and the values of the three acceleration sensors;
obtaining a speed curve according to the acceleration integration of the gravity removal, and obtaining the relative correction time position of the drum stick through speed time calculation;
the position of the head of the drum stick is obtained through the gyroscope sensor and the installation position of the gyroscope sensor, and the striking force is calculated according to the momentum theorem;
calculating the state of the stick according to the instantaneous change of the head of the stick, and translating, beating downwards and rebounding;
according to the speed proportion of the gyroscope sensor and the acceleration sensor, the force application point, the wrist and the whole body of the drum stick are obtained;
identifying the percussion instrument and strength through a neural network according to the state of the stick and the audio;
extracting audio characteristics, namely extracting ADSR envelope variation of a time domain and MFCC variation characteristics of a frequency domain as the characteristics of the audio to participate in recognition;
algorithm training:
by adopting BP neural network, through the existing known example, an audio frequency and coordinate force data and actual striking action result are input into a training algorithm. The hit recognition neural network model is obtained through a large amount of data learning.
The identification process comprises the following steps:
and (3) adopting a BP neural network, identifying a neural network model according to the learned striking, inputting audio characteristics and striking coordinate force, and obtaining the tone color and the force of the striking instrument.
4. Scoring:
and scoring the music according to the force point of the stick, the rhythm of the striking state and the accuracy of striking, and indicating the insufficiency of playing.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (10)
1. The utility model provides a percussion music intelligent education system based on motion detection auxiliary identification, includes stick, shelf drum and host computer, its characterized in that, install acceleration sensor and gyroscope sensor on the stick, acceleration sensor and gyroscope sensor all communicate and connect the host computer, the host computer still is used for gathering the audio data of shelf drum, the data processing process of host computer includes following steps:
an initial correction step: at a static moment before the music starts, according to the detection value of the acceleration sensor, obtaining a gravity acceleration value, and determining the current position of the drum stick;
and (3) identifying the striking coordinate force: when the stick is in action, acquiring the rotation quantity of the stick according to the gyroscope sensor, calculating the current gravity acceleration according to the gravity acceleration value acquired in the initial correction step, then differencing with the data acquired by the current acceleration sensor to obtain the acceleration of the stick after removing the gravity, acquiring the position of the head of the stick based on the position of the stick, and finally calculating the beating coordinate force of the stick according to the momentum theorem;
an audio feature extraction step: extracting audio features according to the audio data;
a percussion music identification step: loading the audio characteristics and the beating coordinate force of the stick into a pre-established and trained beating recognition neural network model to obtain the tone color and force of the percussion instrument,
scoring: and according to the tone color and the intensity of the percussion instrument, giving a music score.
2. The intelligent education system for percussion music based on motion detection auxiliary recognition according to claim 1, wherein the number of the acceleration sensors is three, and the three acceleration sensors are orthogonally arranged in pairs and are used for acquiring accelerations in three directions;
and in the initial correction step, triangular operation is carried out according to the gravity acceleration in three directions, and the current position of the drum stick is determined.
3. The intelligent percussion education system based on motion detection auxiliary recognition according to claim 2, wherein the number of the gyro sensors is three, the three gyro sensors are orthogonally arranged in pairs and are used for acquiring rotation amounts in three directions, and the three gyro sensors correspond to the positions of the three acceleration sensors;
and according to the rotation quantity components in three directions acquired by the three gyroscope sensors, multiplying the rotation quantity components with the gravitational acceleration in three directions acquired in the initial correction step respectively to acquire the current gravitational acceleration.
4. The intelligent education system for percussion music based on motion detection assisted recognition according to claim 3, wherein the speed profile is obtained by performing an integral operation based on the acceleration of the stick after removing the gravity, and the position of the stick with respect to the initial correction step is obtained based on the speed time; and obtaining the position of the head of the stick based on the position of the stick.
5. The intelligent education system for percussion music based on motion detection aided recognition of claim 1 wherein the data processing process of the host computer further comprises: determining the state of the stick according to the instantaneous change of the position of the head of the stick, wherein the state of the stick comprises translation, downward striking and rebound;
the scoring step includes: and according to the tone color, the dynamics and the state of the stick of the percussion instrument, giving out music scores.
6. The intelligent education system for percussion music based on motion detection aided recognition of claim 1 wherein the data processing process of the host computer further comprises: according to the proportion of the acceleration sensor and the gyroscope sensor, a force point of the drum stick is obtained, wherein the force point of the drum stick comprises a wrist and a whole body;
the scoring step includes: and giving out music scores according to the tone color, the dynamics, the state of the stick and the exertion point of the stick of the percussion instrument.
7. The intelligent education system for percussion music based on motion detection aided recognition according to claim 1, wherein in the audio feature extraction step, the audio feature is obtained by extracting an ADSR envelope variation in a time domain and an MFCC variation feature in a frequency domain in the audio data.
8. The intelligent education system for percussion music based on motion detection aided recognition of claim 1, wherein the score of the musical composition is obtained by obtaining the timbre and the strength in real time, comparing the timbre and the strength with a preset score of percussion music, and judging the accuracy of the percussion.
9. The intelligent education system for percussion music based on motion detection aided recognition according to claim 1, wherein the training process of the percussion recognition neural network model is specifically as follows:
the method comprises the steps of obtaining training data, wherein the training data comprise model input data and actual striking action results, loading the training data into a pre-established striking recognition neural network model, and performing model training until a preset training stop condition is reached, so as to obtain a trained striking recognition neural network model.
10. The intelligent education system for percussion music based on motion detection aided recognition according to claim 9, wherein the percussion recognition neural network model adopts a BP neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111085548.7A CN113793581B (en) | 2021-09-16 | 2021-09-16 | Percussion intelligent education system based on motion detection auxiliary identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111085548.7A CN113793581B (en) | 2021-09-16 | 2021-09-16 | Percussion intelligent education system based on motion detection auxiliary identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113793581A CN113793581A (en) | 2021-12-14 |
| CN113793581B true CN113793581B (en) | 2024-02-20 |
Family
ID=79183800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111085548.7A Active CN113793581B (en) | 2021-09-16 | 2021-09-16 | Percussion intelligent education system based on motion detection auxiliary identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113793581B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114937227A (en) * | 2022-06-15 | 2022-08-23 | 安徽云佑信息科技有限公司 | Primary and secondary school student movement scoring system based on machine vision |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105391764A (en) * | 2015-10-14 | 2016-03-09 | 小米科技有限责任公司 | Method and device for monitoring musical instrument learning |
| WO2016111716A1 (en) * | 2015-01-08 | 2016-07-14 | Muzik LLC | Interactive instruments and other striking objects |
| CN109300453A (en) * | 2018-06-09 | 2019-02-01 | 程建铜 | A kind of bulging stick, terminal device and audio frequency broadcast system |
| CN109643533A (en) * | 2016-06-30 | 2019-04-16 | 莱福思科有限公司 | Device and method for unit composition |
| CN109741658A (en) * | 2019-03-20 | 2019-05-10 | 任磊 | A kind of Multi-function electronic music instrument tutoring system for music teaching |
| CN111862910A (en) * | 2019-04-25 | 2020-10-30 | 逢甲大学 | Virtual electronic musical instrument system and operation method thereof |
-
2021
- 2021-09-16 CN CN202111085548.7A patent/CN113793581B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016111716A1 (en) * | 2015-01-08 | 2016-07-14 | Muzik LLC | Interactive instruments and other striking objects |
| CN107408376A (en) * | 2015-01-08 | 2017-11-28 | 沐择歌有限责任公司 | Interactive musical instrument and other strike objects |
| CN105391764A (en) * | 2015-10-14 | 2016-03-09 | 小米科技有限责任公司 | Method and device for monitoring musical instrument learning |
| CN109643533A (en) * | 2016-06-30 | 2019-04-16 | 莱福思科有限公司 | Device and method for unit composition |
| CN109300453A (en) * | 2018-06-09 | 2019-02-01 | 程建铜 | A kind of bulging stick, terminal device and audio frequency broadcast system |
| CN109741658A (en) * | 2019-03-20 | 2019-05-10 | 任磊 | A kind of Multi-function electronic music instrument tutoring system for music teaching |
| CN111862910A (en) * | 2019-04-25 | 2020-10-30 | 逢甲大学 | Virtual electronic musical instrument system and operation method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 计算机音乐制作软件研究;宋方;;黑龙江科技信息(18);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113793581A (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109682561B (en) | Method for automatically detecting free vibration response of high-speed railway bridge to identify mode | |
| CN107767847B (en) | Intelligent piano playing evaluation method and system | |
| CN102664016B (en) | Singing evaluation method and system | |
| CN108847215B (en) | Method and device for voice synthesis based on user timbre | |
| CN109920449B (en) | Beat analysis method, audio processing method, device, equipment and medium | |
| CN103714806B (en) | A kind of combination SVM and the chord recognition methods of in-dash computer P feature | |
| CN105825852A (en) | Oral English reading test scoring method | |
| CN113793581B (en) | Percussion intelligent education system based on motion detection auxiliary identification | |
| CN105023573A (en) | Speech syllable/vowel/phone boundary detection using auditory attention cues | |
| CN103680493A (en) | Voice data recognition method and device for distinguishing regional accents | |
| CN101373593A (en) | Speech analysis apparatus, speech analysis method and computer program | |
| Heggarty | Interdisciplinary indiscipline? Can phylogenetic methods meaningfully be applied to language data—and to dating language | |
| CN112146882B (en) | Bearing fault diagnosis method based on transfer learning vibration signal image recognition | |
| CN108492834A (en) | A kind of musicology teaching performance technical ability detecting system | |
| CN103852525A (en) | Acoustic emission signal identification method based on AR-HMM | |
| CN114140903A (en) | Road type recognition vehicle-mounted device based on decision tree generation rule | |
| CN103505189B (en) | Pulse signal sorting technique based on wavelet package transforms and HMM | |
| CN117191956A (en) | Acoustic emission-based titanium alloy stress corrosion damage classification method and apparatus | |
| CN113823326B (en) | Method for using training sample of high-efficiency voice keyword detector | |
| CN113742638B (en) | Kurtosis-based STLBO motor bearing fault diagnosis method based on FastICA and approximation solution domain | |
| CN107871113B (en) | Emotion hybrid recognition detection method and device | |
| JP6059878B2 (en) | Extraction method of impact time in golf swing | |
| KR100896130B1 (en) | Method and system for playing motion animation of virtal character | |
| CN118364262B (en) | Sensor feature optimization method for behavior pattern recognition | |
| CN115862636B (en) | Internet man-machine verification method based on voice recognition technology |
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 |