Intelligent timbre control method and device for electronic organ

Abstract

The invention relates to the technical field of timbre control, in particular to an electronic organ timbre intelligent control method and device, and the method comprises the steps: collecting note frequency vectors of bass tone and high tone, and calculating a current note frequency vector through employing the high and low frequency vectors; constructing a neural network model, and training a neural network by using the voltage signal amplitude and the partition value as input and the corresponding note frequency vector as output; and performing user tone prediction on the trained neural network model by using the historical voltage value of the user. The invention solves the problem that the traditional electronic organ control method cannot provide the functions of stepless tone adjustment, recommended tone according to the preference of the user and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of timbre control, and in particular to an electronic piano timbre intelligent control method and device. Background Art

[0002] The timbre of a traditional electronic keyboard is generally determined by three tones: high, medium, and low. However, there are countless beautiful tones between these three. Since traditional electronic keyboards do not provide functions such as infinite tone adjustment and recommended tones based on user preferences, traditional electronic keyboards have problems such as weakened competitiveness and poor user experience.

[0003] In order to meet the needs of users for different tones and timbres of songs, traditional electronic keyboards generally have three tone levels: high, medium, and low for users to choose from. With the development of music and the continuous improvement of users' needs, the demand for richer timbres has also put higher demands on the design of electronic keyboards. With the development of artificial intelligence, music services have also reflected the development direction of intelligence. For example, music apps will recommend music based on users' preferences, bringing users a better music experience. As a common musical instrument, electronic keyboards should reflect intelligence in functions and services to better serve users and gain greater market advantages. Summary of the invention

[0004] In view of the shortcomings of the existing methods, the present invention solves the problem that the traditional electronic piano control method cannot provide infinite timbre adjustment, and provides functions such as recommended timbre according to user preferences.

[0005] The technical solution adopted by the present invention is: an electronic piano timbre intelligent control method comprises the following steps:

[0006] Step 1: Collect the frequency vectors of low-pitched and high-pitched notes, and use the high and low frequency vectors to calculate the current note frequency vector;

[0007] As a preferred embodiment of the present invention, the formula of the current note frequency vector is:

[0008]

[0009] Among them, VCC is the voltage on the board connected to the variable resistor, T L is the note frequency vector corresponding to the low pitch, T H is the note frequency vector corresponding to the high pitch, V c is the voltage signal amplitude of the previous note.

[0010] Step 2: Construct a neural network model, use the voltage signal amplitude and partition value as input, and the corresponding note frequency vector as output to train the neural network;

[0011] As a preferred implementation of the present invention, the neural network model includes: BP neural network.

[0012] As a preferred implementation of the present invention, the neural network model also includes: an RNN network, a Hopfield network, a CNN network and an RBF network.

[0013] Step 3: Use the user's historical voltage values ​​to predict the user's timbre using the trained neural network model.

[0014] As a preferred implementation manner of the present invention, the historical voltage values ​​of the user are normalized to obtain an average value.

[0015] As a preferred embodiment of the present invention, the device of the electronic piano timbre intelligent control method comprises:

[0016] A tone wheel, a rheostat, an analog-to-digital converter and a microprocessor;

[0017] The tone dial is used to adjust the note frequency;

[0018] The rheostat converts the note frequency of the tone wheel into a corresponding resistance value;

[0019] The analog-to-digital converter is used to output the voltage signal amplitude corresponding to the note frequency;

[0020] The microprocessor is used to calculate the current note frequency vector and construct the neural network model.

[0021] As a preferred embodiment of the present invention, the microprocessor is an MCU controller or a host computer.

[0022] As a preferred embodiment of the present invention, the model of the variable resistor is R122.

[0023] As a preferred embodiment of the present invention, an electronic piano tone intelligent control system includes: a memory for storing instructions executable by a processor; a processor for executing the instructions to implement an electronic piano tone intelligent control method.

[0024] As a preferred embodiment of the present invention, a computer readable medium stores computer program code, and the computer program code implements the electronic piano tone intelligent control method when executed by a processor.

[0025] Beneficial effects of the present invention:

[0026] 1. The present invention uses the voltage signal amplitude of the current note and the high and low note frequency vectors to accurately calculate the note frequency vector of the current note and realize continuous stepless measurement;

[0027] 2. According to the voltage and partition value of the user's historical timbre, a neural network is constructed to model the timbre, and the output timbre is recommended to the user as the user's preferred timbre;

[0028] 3. Provide users with typical tone setting, storage and call functions, so that users can call stored tones with one click. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a flow chart of the electronic piano timbre intelligent control method of the present invention;

[0030] Figure 2 It is a connection diagram of the electronic piano tone intelligent control system of the present invention;

[0031] Figure 3 It is a schematic diagram of the timbre partitioning of the present invention;

[0032] Figure 4 It is a schematic diagram of the BP network model. DETAILED DESCRIPTION

[0033] The present invention is further described below in conjunction with the accompanying drawings and embodiments. This figure is a simplified schematic diagram, which only illustrates the basic structure of the present invention in a schematic manner, and therefore it only shows the components related to the present invention.

[0034] like Figure 1 As shown, a method for intelligently controlling the tone of an electronic piano comprises the following steps:

[0035] Step 1: Collect the frequency vectors of low-pitched and high-pitched notes, and use the high and low frequency vectors to calculate the current note frequency vector;

[0036] like Figure 2 As shown, the user rotates the pitch wheel, which can rotate infinitely within the range of high, medium and low pitches. The lower axis of the pitch wheel is connected to a variable resistor. The rotation of the pitch wheel drives the resistance value of the variable resistor to change, which in turn causes the voltage signal collected by the analog-to-digital converter (A / D) on the right to change. Assuming that the note frequency vector (Do, Re, Mi…Xi, There are 8 scales in total) for T L , the note frequency vector corresponding to the high pitch is T H ; The voltage signal amplitude of the current note is V c , calculate the note frequency vector of the current note, the formula is:

[0037]

[0038] Among them, VCC is the voltage on the board connected to the variable resistor.

[0039] The microprocessor calculates the note frequency of the current note set by the user according to formula (1), thereby determining the current corresponding timbre characteristics.

[0040] The present invention measures V c The value is used to realize the stepless adjustment of the tone by using formula (1), which is a continuous rather than discrete stepless adjustment. Assuming that the traditional high and low tone frequency range is [fmin, fmax], the corresponding voltage range is [0, VCC], so the current measured V c When the corresponding timbre characteristics (frequency) are determined, it is a linear mapping relationship.

[0041] like Figure 4 ,Step 2, construct a neural network model, use the voltage signal amplitude and partition value as input, and the corresponding note frequency vector as output to train the neural network;

[0042] Intelligent control should be able to recommend and provide users with their preferred settings based on their usage habits and historical usage data, helping users find their favorite timbre parameters; in order to use the user's historical timbre setting data to locate the user's preferred timbre, BP neural network is introduced for timbre modeling, so as to more accurately recommend timbre that suits the user's personal preferences; Figure 3 As shown, in order to facilitate normalization, the high→middle interval is defined as the "1" partition, that is, the partition value is 1; the middle→low interval is defined as the "0" partition, that is, the partition value is 0;

[0043] Build V c and corresponding to T C The data set is divided into a training set and a validation set; the analog-to-digital converter is used to collect V c , partition value as input feature, corresponding to T C As the output feature, the BP network model is trained; the error of the BP network model is verified using the verification set. If the error does not meet the requirements or the training cycle does not reach the set number of cycles, the training and verification are repeated until the termination condition is met;

[0044] Step 3: Use the user's historical voltage value to predict the user's timbre using the trained neural network model;

[0045] The microprocessor records the voltage value V' that the user has set k ,V' k =[V' t ,V' t-1 ,...,V' t-k+1 ], k is the data length, for V' k Find the mean Will and The corresponding partition value is input into the trained BP network model and the recommended timbre is output.

[0046] The microprocessor may be a single chip microcomputer, an MCU controller, or a host computer, etc.; the variable resistor may be a rotary potentiometer of a model such as R122.

[0047] The BP network model includes: input layer, hidden layer and output layer.

[0048] Other neural network models can also be used, such as: RNN network, Hopfield network, CNN network and RBF network.

[0049] The user can obtain a recommended timbre, which the user can store as a typical timbre, and notify the microprocessor to store the current typical timbre in the ROM of the electronic keyboard through the storage button on the electronic keyboard; when the user has stored a certain number of typical timbres, the electronic keyboard supports the user's typical timbre calling function by pressing the call button on the keyboard. At the same time, the LED next to the button on the electronic keyboard panel will display the number of the currently called typical timbre, and the electronic keyboard will give the corresponding timbre display sound through the speaker.

[0050] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. An intelligent control method for electronic piano timbre, characterized in that: The following steps are involved: Step 1: Collect the frequency vectors of low-pitched and high-pitched notes, and use the high and low frequency vectors to calculate the current note frequency vector; Step 2: Construct a neural network model, use the voltage signal amplitude and partition value as input, and the corresponding note frequency vector as output to train the neural network; Step 3: Use the user's historical voltage values ​​to predict the user's timbre using the trained neural network model.

2. The electronic piano timbre intelligent control method according to claim 1, characterized in that: The formula for the current note frequency vector is: Among them, VCC is the voltage on the board connected to the variable resistor, T L is the note frequency vector corresponding to the low pitch, T H is the note frequency vector corresponding to the high pitch, V c is the voltage signal amplitude of the previous note.

3. The electronic piano timbre intelligent control method according to claim 1, characterized in that: Neural network models include: BP neural network.

4. The electronic piano timbre intelligent control method according to claim 1, characterized in that: Neural network models also include: RNN network, Hopfield network, CNN network and RBF network.

5. The electronic piano timbre intelligent control method according to claim 1, characterized in that: Normalize the user's historical voltage values ​​and calculate the average value.

6. A device using the electronic piano timbre intelligent control method according to any one of claims 1 to 5, characterized in that: include: A tone wheel, a rheostat, an analog-to-digital converter and a microprocessor; The tone dial is used to adjust the note frequency; The rheostat converts the note frequency of the tone wheel into a corresponding resistance value; The analog-to-digital converter is used to output the voltage signal amplitude corresponding to the note frequency; The microprocessor is used to calculate the current note frequency vector and construct the neural network model.

7. The electronic piano timbre intelligent control device according to claim 6 is characterized in that: The microprocessor is a single chip microcomputer.

8. The electronic piano timbre intelligent control device according to claim 6 is characterized in that: The model of the variable resistor is R122.

9. An intelligent control system for electronic piano timbre, characterized in that: include: a memory for storing instructions executable by a processor; A processor is used to execute instructions to implement the electronic piano tone intelligent control method as described in any one of claims 1-5.

10. A computer readable medium storing computer program code, characterized in that: When the computer program code is executed by a processor, the computer program code implements the electronic piano tone intelligent control method as described in any one of claims 1 to 5.

Images