Audio equipment and method for outputting parameters of said audio equipment

Abstract

To provide an information processing device that presents to a user parameters for bringing an input sound closer to a desired sound in an audio apparatus being used.SOLUTION: A method of outputting parameters of acoustic apparatus inputs sound signals to the acoustic apparatus, obtains information pertaining to parameters accepted from a user in the acoustic apparatus and outputs the information using a learned model that has learned the relationship between the output sound for learning in the acoustic apparatus, the input sound for learning in the acoustic apparatus, and the parameters of sound processing performed in the acoustic apparatus.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] One embodiment of this invention relates to audio devices such as guitar amplifiers and a method for outputting parameters of the audio device.

Background Art

[0002] The electronic musical instrument of Patent Document 1 includes an effect module in which a plurality of effectors are functionally connected in series, a plurality of multipliers arranged on the input side or the output side of each effector constituting the effect module, a RATIO operation unit as a first operation unit for instructing a change in the first characteristic in the effect module, and a DSP arithmetic unit that simultaneously changes the amplification factors of the plurality of multipliers in a lump so that the first characteristic in the effect module becomes the instructed characteristic according to the operation of the RATIO operation unit.

[0003] The distortion imparting device of Patent Document 2 includes first amplification means for attenuating an input audio signal based on an attenuation rate set by a user and amplifying the attenuated audio signal, second amplification means connected in series with the first amplification means, and limiting means connected between the output end of the first amplification means and the input end of the second amplification means for limiting the input voltage of the second amplification means to a predetermined distortion voltage. The limiting means determines the distortion voltage based on the attenuation rate.

[0004] When the pitch detection success / failure information is information indicating that the pitch detection is unsuccessful, the musical tone signal processing device of Patent Document 3 outputs the distortion signal obtained by processing the musical tone signal obtained by the string operation and generated by the distortion signal generation means.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Patent Document 3

[0006] All of the aforementioned prior art methods involve correcting an audio signal to a desired audio signal through signal processing.

[0007] One aspect of this disclosure aims to provide an audio device and a control method for the audio device that presents parameters to the user for bringing the input sound closer to the desired sound in the audio device being used. [Means for solving the problem]

[0008] A parameter output method for an audio device according to one embodiment of the present invention involves inputting an audio signal to the audio device, using a trained model that has learned the relationship between the training output sound of the audio device, the training input sound of the audio device, and the parameters of the sound processing performed by the audio device, obtaining information related to the parameters accepted by the user in the audio device, and outputting the said information. [Effects of the Invention]

[0009] According to one embodiment of the present invention, parameters can be presented to the user in the audio equipment being used to bring the input sound closer to the desired sound. [Brief explanation of the drawing]

[0010] [Figure 1] This is a diagram showing the configuration of the acoustic system 1. [Figure 2] This is a block diagram showing the configuration of guitar amplifier 11. [Figure 3] This is an external view showing an example of User I / F102. [Figure 4] This is a block diagram showing the main configuration of user terminal 12. [Figure 5] This is an external view of user terminal 12, showing an example of a display screen related to an application program. [Figure 6] Block diagram showing the functional configuration of the parameter output method implemented by the CPU 104 of the guitar amplifier 11. [Figure 7] This flowchart shows the operation of the parameter output method. [Figure 8] This figure shows the frequency characteristics (input) and spectral envelope of the sound signal from the electric guitar 10 that was input. [Figure 9] This figure shows the frequency characteristics (distorted:type1) and spectral envelope of an audio signal obtained by applying a distortion effect to the sound of an electric guitar performance, representing the target timbre information. [Figure 10] This is an external view of user terminal 12, showing an example of a display screen related to an application program. [Figure 11] This is a flowchart showing the operation of the trained model generation method performed by the trained model generation device. [Figure 12] This is an external view showing an example of the user interface 102 related to modified example 5. [Modes for carrying out the invention]

[0011] Figure 1 is an external view showing an example of the sound system 1. The sound system 1 includes an electric guitar 10, a guitar amplifier 11, and a user terminal 12.

[0012] The electric guitar 10 is an example of a musical instrument. In this embodiment, the electric guitar 10 is shown as an example of a musical instrument, but the musical instrument is not limited to an electric guitar. The musical instrument may be any other stringed instrument. The musical instrument may also include other electric instruments such as an electric bass, acoustic instruments such as a piano or violin, or electronic instruments such as an electronic piano.

[0013] The guitar amplifier 11 is connected to the electric guitar 10 via an audio cable. The guitar amplifier 11 is also connected to the user terminal 12 by wireless communication such as Bluetooth (registered trademark) or wireless LAN. The electric guitar 10 outputs an analog sound signal related to the performance sound to the guitar amplifier 11. When the instrument is an acoustic instrument, a microphone or a pickup is used to input a sound signal to the guitar amplifier 11.

[0014] Figure 2 is a block diagram showing the configuration of the guitar amplifier 11. The guitar amplifier 11 includes a display 101, a user interface (I / F) 102, a flash memory 103, a CPU 104, a RAM 105, a DSP 106, a communication I / F 107, an audio I / F 108, an A / D converter 109, a D / A converter 110, an amplifier 111, and a speaker 112.

[0015] The display 101 is composed of, for example, an LED, an LCD (Liquid Crystal Display), or an OLED (Organic Light-Emitting Diode), etc., and displays the state of the guitar amplifier 11 and the like.

[0016] The user I / F 102 is composed of knobs, switches, or buttons, etc., and accepts the operations of the user. Figure 3 is an external view showing an example of the user I / F 102. In this example, the user I / F 102 has five knobs. The five knobs are knobs for accepting the adjustment of the parameters of DRIVE, MASTER, BASS, TREBLE, and TONE, respectively.

[0017] In this embodiment, as an example of the user I / F 102, a knob for mainly adjusting the parameters related to distortion is shown, but the user I / F 102 also has operators such as a power switch and the like.

[0018] DRIVE is a knob for adjusting the strength of distortion. The more the DRIVE knob is rotated in the clockwise direction, the stronger the strength of distortion becomes.

[0019] The MASTER knob is used to adjust the amplification of amplifier 111. The more you turn the MASTER knob clockwise, the higher the amplification of amplifier 111 becomes. Also, the more you turn the MASTER knob clockwise, the stronger the distortion produced by amplifier 111 becomes.

[0020] The BASS knob adjusts the strength of the low frequencies. Turning the BASS knob clockwise emphasizes the low frequencies. Also, turning the BASS knob clockwise increases the intensity of the low-frequency distortion. The TREBLE knob adjusts the strength of the high frequencies. Turning the TREBLE knob clockwise emphasizes the high frequencies. Also, turning the TREBLE knob clockwise increases the intensity of the high-frequency distortion. The TONE knob adjusts the brightness of the sound. Turning the TONE knob clockwise makes the sound brighter.

[0021] The user interface 102 may be a touch panel stacked on the LCD of the display unit 101. Alternatively, the user may adjust parameters such as DRIVE, MASTER, BASS, TREBLE, and TONE via an application program on the user terminal 12. In this case, the user terminal 12 receives parameter adjustment requests from the user via a touch panel display or the like, and transmits information indicating the parameter adjustment amount to the guitar amplifier 11.

[0022] Figure 4 is a block diagram showing the configuration of the user terminal 12. Figure 5 is an external view of the user terminal 12, showing an example of a display screen related to an application program.

[0023] The user terminal 12 is an information processing device such as a personal computer or a smartphone. The user terminal 12 is equipped with a display 201, a user interface 202, flash memory 203, a CPU 204, RAM 205, and a communication interface 206.

[0024] The display unit 201 consists of, for example, an LED, LCD, or OLED, and displays various information. The user interface 202 is a touch panel stacked on the LCD or OLED of the display unit 201. Alternatively, the user interface 202 may be a keyboard or mouse. If the user interface 202 is a touch panel, it, together with the display unit 201, constitutes a GUI (Graphical User Interface).

[0025] The CPU 204 is an example of a processor and is a control unit that controls the operation of the user terminal 12. The CPU 204 performs various operations by reading predetermined programs, such as application programs, stored in the flash memory 203 (a storage medium) into the RAM 205 and executing them. The programs may also be stored on a server (not shown). The CPU 204 may also download and execute programs from the server via a network.

[0026] As shown in Figure 5, the CPU 204 displays icon images of the five knobs (DRIVE, MASTER, BASS, TREBLE, and TONE) on the user interface 102 of the guitar amplifier 11 on the display unit 201, thereby configuring the GUI. The guitar amplifier 11 transmits information indicating the current position of the five knobs via the communication interface 107. The CPU 204 receives this information from the guitar amplifier 11 and controls the icon images of the five knobs to be displayed on the display unit 201.

[0027] The user can also adjust the parameters by manipulating the icon images of the five knobs (DRIVE, MASTER, BASS, TREBLE, and TONE) via the GUI. The CPU 204 receives the operation on these icon images and sends the parameter information after the operation to the guitar amplifier 11.

[0028] The CPU 104 of the guitar amplifier 11 reads various programs stored in the flash memory 103, which is a storage medium, into the RAM 105 to control the guitar amplifier 11. For example, as described above, the CPU 104 receives parameters related to signal processing from the user I / F 102 or user terminal 12 to control the DSP 106 and amplifier 111. The DSP 106 and amplifier 111 correspond to the signal processor of the present invention.

[0029] The communication interface 107 connects to other devices, such as the user terminal 12, via Bluetooth® or wireless LAN.

[0030] The Audio I / F 108 has analog audio terminals. The Audio I / F 108 accepts analog audio signals from the electric guitar 10 via an audio cable.

[0031] The A / D converter 109 converts the analog audio signal received by the audio interface 108 into a digital audio signal.

[0032] The DSP106 applies various signal processing, such as effects, to the digital audio signal. Parameters related to signal processing are received from the user I / F102. In this embodiment, the user can change the effect parameters in the DSP106 by operating the five knobs described above, thereby adjusting the tone of the electric guitar 10 output from the guitar amplifier 11. Note that "effect" includes all signal processing that alters the sound. The parameters corresponding to the five knobs shown in this embodiment are, as an example, parameters related to distortion effects.

[0033] The DSP106 outputs the digital audio signal, after signal processing, to the D / A converter 110.

[0034] The D / A converter 110 converts the digital audio signal received from the DSP 106 into an analog audio signal. The amplifier 111 amplifies the analog audio signal. Amplification parameters are received via the user interface 102.

[0035] The speaker 112 outputs the sound of the electric guitar 10 being played, based on the analog sound signal amplified by the amplifier 111.

[0036] Figure 6 is a block diagram showing the functional configuration of the parameter output method implemented by the CPU 104 of the guitar amplifier 11. Figure 7 is a flowchart showing the operation of the parameter output method. The CPU 104 configures the input unit 51, calculation unit 52, and output unit 53 shown in Figure 4 using a predetermined program read from the flash memory 103.

[0037] The input unit 51 receives a digital sound signal related to the sound produced by the electric guitar 10 (S111). The user inputs the sound to the guitar amplifier 11 by, for example, playing all of the strings of the electric guitar 10, or a specific string, as an open string. The calculation unit 52 determines the timbre (acoustic features) of the input sound signal (S12).

[0038] Acoustic features include, for example, frequency characteristics, and more specifically, spectral envelopes. Figure 8 shows the frequency characteristics (input) and spectral envelope of the sound signal of the sound played by the electric guitar 10. In the graph of Figure 8, the horizontal axis is frequency (Hz) and the vertical axis is amplitude. The spectral envelope can be obtained from the input sound signal using, for example, linear predictive coding (LPC) or cepstrum analysis. For example, the calculation unit 52 converts the sound signal to the frequency axis using a short-time Fourier transform and obtains the amplitude spectrum of the sound signal. The calculation unit 52 averages the amplitude spectrum over a specific period and obtains the average spectrum. The calculation unit 52 removes the bias (the 0th order component of the cepstrum), which is an energy component, from the average spectrum and obtains the spectral envelope of the sound signal. Note that averaging in the time axis direction and bias removal can be performed in either order. That is, the calculation unit 52 may first remove the bias from the amplitude spectrum and then obtain the average spectrum averaged in the time axis direction as the spectral envelope.

[0039] The input unit 51 acquires target timbre information (S13). Target timbre information refers to, for example, the acoustic features of a sound signal related to the performance of a certain artist. Acoustic features are, for example, frequency characteristics, and more specifically, spectral envelopes. Figure 9 shows the frequency characteristics (distorted:type1) and spectral envelope of a sound signal obtained by applying a distortion effect to the performance of an electric guitar, as target timbre information. In the graph of Figure 9, the horizontal axis is frequency (Hz), and the vertical axis is amplitude. The acoustic features corresponding to the target timbre information are calculated from the sound signal of a performance of a specific artist desired by the user, obtained from audio content, etc. The spectral envelope calculation method is the linear predictive coding (LPC) or cepstrum analysis method described above. The input unit 51 may also acquire the spectral envelope already calculated by the server via the network.

[0040] The user operates the user interface 102 and inputs, for example, the name of a specific artist as target timbre information. The input unit 51 acquires the performance sound or acoustic features of the input artist from audio content or a server, etc. Alternatively, the input unit 51 may acquire acoustic features in advance and store them in the flash memory 103.

[0041] Alternatively, the user may input target tone information via the application program on the user terminal 12.

[0042] Figure 10 is an external view of a user terminal 12, showing an example of a display screen related to an application program.

[0043] As shown in Figure 10, the CPU 204 displays text indicating the target tone information and icon images of the five knobs (DRIVE, MASTER, BASS, TREBLE, and TONE) on the user interface 102 of the guitar amplifier 11 on the display unit 201.

[0044] In the example in Figure 10, the target timbre information is displayed as the name of a distortion effect by a certain artist desired by the user, "DISTORTION of Artist A". This display is a list box 50, allowing the user to select the desired artist and effect name from a large number of artists and effect names. The CPU 204 retrieves the acoustic feature quantities corresponding to the selected artist and effect name from the server and sends them to the guitar amplifier 11.

[0045] Next, the calculation unit 52 calculates signal processing parameters to bring the input sound closer to the target timbre, based on the performance sound input by the input unit 51 and the acquired target timbre information (S14).

[0046] For example, the calculation unit 52 calculates parameters based on a trained model that has learned the relationship between acoustic features related to the sound of the electric guitar 10 being played, target timbre information, and parameters using a DNN (Deep Neural Network).

[0047] Figure 11 is a flowchart showing the operation of the trained model generation method performed by the trained model generation device. The trained model generation device is implemented, for example, by a program running on a computer (server) used by the manufacturer of the guitar amplifier 11.

[0048] The device for generating trained models acquires a large dataset (training data) during the training phase, which includes training input sounds from audio equipment, training output sounds from audio equipment, and parameters for sound processing performed by the audio equipment (S21). The training input sounds from audio equipment are, for example, the sound of an electric guitar 10 being input to a guitar amplifier 11, and are undistorted. The training output sounds from audio equipment are the sound of the target timbre, for example, a distorted sound played by an artist using a certain effect. More specifically, the training input sounds from audio equipment are, for example, the acoustic features of the sound of an electric guitar 10 being input to a guitar amplifier 11, and the training output sounds from audio equipment are the acoustic features of the target timbre. In this embodiment, the acoustic features include the acoustic features of the distorted sound. More specifically, the acoustic features of the input sound used for learning by the audio equipment are the frequency characteristics (more specifically, the spectral envelope) of the sound signal before distortion, and the acoustic features of the output sound used for learning by the audio equipment are the frequency characteristics (more specifically, the spectral envelope) of the sound signal after distortion.

[0049] The parameters for sound processing performed by audio equipment are parameters received from the user, and in this embodiment, these are the parameters of the five knobs (DRIVE, MASTER, BASS, TREBLE, and TONE) related to distortion in the guitar amplifier 11.

[0050] The device for generating trained models uses a predetermined algorithm to train a predetermined trained model on the relationship between the acoustic features of the training input sound of the audio device, the acoustic features of the training output sound of the audio device, and the parameters that the audio device receives from the user (S22).

[0051] The algorithm used to train the learning model is not limited, and any machine learning algorithm such as CNN (Convolutional Neural Network) or RNN (Recurrent Neural Network) can be used. The machine learning algorithm may be supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, inverse reinforcement learning, active learning, or transfer learning. Furthermore, the calculation unit 52 may train the learning model using machine learning models such as HMM (Hidden Markov Model) or SVM (Support Vector Machine).

[0052] The sound of the electric guitar 10 input to the guitar amplifier 11 can be made to approximate a target tone (for example, the sound when a certain artist plays using a certain effect) through the effects of the guitar amplifier 11. In other words, there is a correlation between the sound of the electric guitar 10 input to the guitar amplifier 11, the sound when a certain artist plays using a certain effect, and the parameters in the effect processing of the guitar amplifier 11. Therefore, the trained model generation device trains a predetermined trained model to learn the relationship between the sound of the electric guitar 10 input to the guitar amplifier 11, the sound when a certain artist plays using a certain effect, and the parameters in the effect processing of the guitar amplifier 11, and generates a trained model (S23).

[0053] Note that "training data" can also be expressed as "teacher data" or "training data." Furthermore, the expression "to train a model" can be expressed as "to train a model." For example, the expression "the computer uses teacher data to train a learning model" can be replaced with "the computer uses training data to train a learning model."

[0054] The calculation unit 52 obtains the trained model from a trained model generation device (e.g., a musical instrument manufacturer's server) via the network. In the execution stage, the calculation unit 52 uses the trained model to determine the parameters for the effect processing of the guitar amplifier 11 in order to bring the sound of the electric guitar 10 input to the guitar amplifier 11 closer to the target tone (e.g., the sound when a certain artist plays using a certain effect) (S14). The information regarding the parameters determined by the calculation unit 52 is within the range of values ​​that can be set on the guitar amplifier 11. More specifically, the calculation unit 52 determines the parameters of the five knobs (DRIVE, MASTER, BASS, TREBLE, and TONE) of the guitar amplifier 11.

[0055] The output unit 53 outputs information relating to the parameters calculated by the calculation unit 52 (S15). For example, the output unit 53 transmits this information to the user terminal 12 via the communication interface 107. The CPU 204 of the user terminal 12 receives this information and displays the parameters on the display unit 201. For example, as shown in Figure 10, the CPU 204 displays icon images of the five knobs (DRIVE, MASTER, BASS, TREBLE, and TONE) on the user interface 102 of the guitar amplifier 11 on the display unit 201 and displays the target parameters. In the example in Figure 10, the CPU 204 displays the target positions of the five knobs (DRIVE, MASTER, BASS, TREBLE, and TONE) in black. Also in the example in Figure 10, the CPU 204 displays the current positions of the five knobs with dashed lines.

[0056] In this way, the guitar amplifier 11 of this embodiment can present the user with information regarding effect parameters for bringing the sound of the electric guitar 10 closer to a target tone. This allows the user to easily determine, simply by playing the electric guitar 10, which parameters in the guitar amplifier 11 need to be adjusted and by how much to approach the target tone. The guitar amplifier 11 of this embodiment can, for example, simulate the playing sound of an artist the user admires, allowing the user to experience playing with their preferred sound as if they were playing themselves. Specifically, the user of the guitar amplifier 11 can reproduce the distorted sound of an admired artist using the guitar amplifier 11, allowing them to experience playing with their preferred distorted sound as if they were playing themselves.

[0057] (Variation 1) In the above embodiment, as part of the learning phase, the learning model was trained using the acoustic features (more specifically, the spectral envelope) of the input sound for training and the acoustic features (more specifically, the spectral envelope) of the output sound for training. In addition, as part of the execution phase, the guitar amplifier 11 acquired the acoustic features (more specifically, the spectral envelope) related to the sound played by the electric guitar 10 and the target acoustic features (more specifically, the spectral envelope) to obtain information related to the parameters that the audio equipment receives from the user.

[0058] However, the device for generating trained models may train the trained model to learn the relationship between the sound signal of the input sound for training, the sound signal of the output sound for training, and the parameters received from the user by the audio equipment. The guitar amplifier 11 may, as part of its execution phase, acquire sound signals related to the sound played by the electric guitar 10 and sound signals of the target timbre, and obtain information related to the parameters received from the user.

[0059] However, the guitar amplifier 11 can obtain results faster and with greater accuracy by using a pre-trained model that has learned based on acoustic features, compared to using a pre-trained model that has learned based on sound signals.

[0060] (Modification 2) In the above embodiment, the parameters were displayed on the display 201 of the user terminal 12. However, the guitar amplifier 11, which is an audio device, may display the parameters for approaching the target tone on the display 101. In this case, the user terminal 12 is unnecessary.

[0061] (Variation 3) In the above embodiment, as part of the execution phase, the guitar amplifier 11 acquired acoustic features (more specifically, spectral envelopes) related to the sound played by the electric guitar 10 and target acoustic features (more specifically, spectral envelopes) to obtain information about parameters to be received from the user. However, the execution phase does not need to be performed by the guitar amplifier 11. For example, the user terminal 12 may acquire acoustic features (more specifically, spectral envelopes) related to the sound played by the electric guitar 10 and target acoustic features (more specifically, spectral envelopes) as part of the execution phase to obtain information about parameters to be received from the user.

[0062] (Modification 4) The guitar amplifier 11 in Modification 4 performs the training phase shown in Figure 11, which is the generation of a trained model, and the execution phase shown in Figure 7, which is the output of parameter information. In other words, the operation of the training phase of the training model and the operation of the execution phase of the trained model may be performed by a single device. Alternatively, instead of the guitar amplifier 11, the server may perform the training phase (generation of a trained model) and the execution phase (output of parameter information). In this case, the guitar amplifier 11 only needs to send the acoustic features of the sound played by the electric guitar 10 and the target timbre information to the server via the network and receive the parameter information from the server.

[0063] (Variation 5) Figure 12 is an external view showing an example of a user interface 102 according to modified example 5. In this example, the user interface 102 has five knobs in addition to a selection knob 501 for the acoustic processing model.

[0064] The guitar amplifier 11 has multiple sound processing models that model the input / output characteristics of multiple audio devices. In the example in Figure 12, the select knob 501 selects one of the sound processing models: CLEAN, CRUNCH, or BRIT. CLEAN is a sound processing model that outputs a clear sound with little distortion to the input sound. CRUNCH is a sound processing model that outputs a sound with slight distortion to the input sound. BRIT is a sound processing model that outputs a sound with strong distortion to the input sound. The guitar amplifier 11 applies sound processing to the sound played by the electric guitar 10 input to the guitar amplifier 11 using the selected sound processing model.

[0065] In Modification 5, the parameters include information specifying which of these multiple sound processing models to use. In the learning phase, the trained model generator trains the trained model to learn the relationship between the learning input sound of the audio equipment, the learning output sound of the audio equipment, and the parameters including the sound processing model used by the audio equipment. In the execution phase, the guitar amplifier 11 uses the trained model to determine the parameters including the sound processing model to be used by the guitar amplifier 11 in order to bring the sound of the electric guitar 10 input to the guitar amplifier 11 closer to the target timbre.

[0066] This makes it easy for users to determine which sound processing model to select and how much to adjust which parameters to get closer to their target timbre.

[0067] The description of this embodiment should be considered in all respects to be illustrative and not restrictive. The scope of the invention is indicated by the claims, rather than by the embodiments described above. Furthermore, the scope of the invention includes the scope equivalent to the claims.

[0068] For example, in the above embodiment, a guitar amplifier 11 was shown as an example of audio equipment, but audio equipment is not limited to a guitar amplifier 11. For example, any equipment that performs sound processing, such as a powered speaker, audio mixer, or electronic musical instrument, is included in the audio equipment of the present invention.

[0069] In the above embodiment, the spectral envelope was shown as an example of an acoustic feature. However, the acoustic feature may be, for example, power, fundamental frequency, formant frequency, or Mel spectrum. In other words, any type of acoustic feature related to timbre may be used.

[0070] In this embodiment, distortion is shown as an example of an effect, but the effect is not limited to distortion; other effects such as chorus, compressor, delay, or reverb may also be used.

[0071] In the above embodiment, the calculation unit 52 calculated the parameters based on a trained model that learned the relationship between acoustic features related to the sound of the electric guitar 10 being played, the target timbre information, and the parameters. However, the calculation unit 52 may also calculate the parameters by referring to a table that defines the relationship between acoustic features related to the sound of the electric guitar 10 being played, the target timbre information, and the parameters. This table is pre-registered in the flash memory 103 of the guitar amplifier 11 or in a database on a server (not shown).

[0072] This allows the guitar amplifier 11 to present the user with information regarding effect parameters that bring the sound of the electric guitar 10 closer to the target tone, without using artificial intelligence algorithms. [Explanation of Symbols]

[0073] 1: Sound System 10: Electric guitar 11: Guitar Amplifier 12: User terminal 50: List Box 51: Input section 52: Calculation Unit 53: Output section 101:Display unit 102: User Interface 103: Flash memory 104:CPU 105: RAM 106: DSP 107: Communication I / F 108: Audio Interface 109: A / D converter 110: D / A converter 111: Amplifier 112: Speaker 201:Display unit 202: User Interface 203: Flash memory 204:CPU 205: RAM 206: Communication I / F

Claims

1. The audio equipment has an input section for inputting the user's performance sound, The aforementioned audio equipment adjusts the timbre of the performance sound using parameters, A calculation unit obtains information related to the parameters from the performance sound input via the input unit, using a trained model that has learned the relationship between the learning input sound input to the audio equipment, the target timbre, and the parameters, in order to bring the performance sound closer to the target timbre sound which is a performance sound by an artist different from the user. An output unit that outputs information relating to the parameters calculated by the calculation unit, Audio equipment equipped with these features.

2. The audio device according to claim 1, further comprising a display unit for displaying information output from the output unit.

3. A user interface for receiving the parameters from the user, A signal processor that applies sound processing to the performance sound based on the parameters received by the user interface, The sound device according to claim 1 or claim 2, further comprising:

4. The aforementioned sound processing includes effect processing, The aforementioned parameters include the parameters for the effect processing, The sound device according to claim 3.

5. The information related to the parameters determined by the calculation unit indicates a range of values ​​that can be set by the audio device. The sound device according to any one of claims 1 to 4.

6. The aforementioned audio equipment has multiple audio processing models that model the input / output characteristics of multiple audio devices, The aforementioned parameter includes information specifying which of the plurality of acoustic processing models to use. The sound device according to any one of claims 1 to 5.

7. The aforementioned timbre includes acoustic feature quantities of sound signals related to the performance sound of an artist different from the user, The sound device according to any one of claims 1 to 6.

8. The sound of the user's performance is input into the audio equipment. The aforementioned audio equipment adjusts the timbre of the performance sound using parameters, From the input performance sound, information related to the parameters is obtained using a trained model that has learned the relationship between the learning input sound input to the audio equipment, the target timbre, and the parameters, in order to make the performance sound closer to the target timbre, which is a performance sound by an artist different from the user. Output information related to the aforementioned parameters. Methods for outputting parameters of audio equipment.

9. The outputted information is displayed as follows: A method for outputting parameters of an audio device according to claim 8.

10. The user receives the aforementioned parameters, The sound of the performance is processed based on the aforementioned parameters. A method for outputting parameters of an audio device according to claim 8 or claim 9.

11. The aforementioned sound processing includes effect processing, The aforementioned parameters include the parameters for the effect processing, A method for outputting parameters of an audio device according to claim 10.

12. The aforementioned audio equipment has multiple audio processing models that model the input / output characteristics of multiple audio devices, The aforementioned parameter includes information specifying which of the plurality of acoustic processing models to use. A method for outputting parameters of an audio device according to any one of claims 8 to 11.

13. The target timbre includes acoustic feature quantities of sound signals related to the performance sound of an artist different from the user, A method for outputting parameters of an audio device according to any one of claims 8 to 12.

Images