Palatability reflection device for acoustic device and palatability reflection method

Abstract

To reflect an output characteristic in accordance with palatability of each individual user instead of a fixed output characteristic to an output sound of an acoustic device.SOLUTION: A palatability reflection device 10 for an acoustic device for reflecting palatability of a user against an acoustic device 30, comprises: a characteristic storage part 13 that stores an output characteristic for regulating an output level in each frequency of an output sound of the acoustic device 30; a control part 11 that selects the output characteristic stored in the characteristic storage part 13 on the basis of reflection information reflecting a reaction of the user against the output sound; and a characteristic setting part 15 that refers the output characteristic selected by the control part 11 in the characteristic storage part 13, and sets the output characteristic of the output sound. The reaction information is sound information emitted by the user.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a preference reflecting device and a preference reflecting method for audio equipment. [Background technology]

[0002] Patent Document 1 discloses a user hospitality system for automobiles. In this system, the operation content of the hospitality operation unit changes according to the content of the user's biometric characteristic information, and thus the service (hospitality) effect for the user when using the automobile can be further optimized according to the user's mental or physical condition. Specifically, standard reference information at the time of operation control for a function specified from the function extraction matrix is ​​extracted, and the standard reference information is added with the physical or mental state reflected in the user's biometric characteristic information acquired separately, thereby optimizing the operation content of the selected function. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 4572889 Summary of the Invention [Problem to be solved by the invention]

[0004] Patent Document 1 discloses a function for detecting the state of a user in an automobile user hospitality system and changing the contents of the interior lighting and audio based on the detection result. However, the system in this document is not capable of changing the parameter settings inside the device according to the preferences and environment of the user who is in the vehicle, and does not perform detailed setting changes according to individual users.

[0005] The present disclosure provides an audio equipment preference reflecting device and preference reflecting method for reflecting an individual user's audio preferences in the output characteristics of the audio equipment. [Means for solving the problem]

[0006] The preference reflection device for audio equipment of the present disclosure is a preference reflection device for audio equipment for reflecting a user's preferences in the audio equipment, and includes a characteristic memory unit that stores output characteristics that specify the output level for each frequency in the output sound of the audio equipment, a control unit that selects the output characteristic stored in the characteristic memory unit based on reaction information that reflects the user's reaction to the output sound, and a characteristic setting unit that refers to the output characteristic selected by the control unit in the characteristic memory unit and sets the output characteristic of the output sound, wherein the reaction information is voice information uttered by the user.

[0007] The preference reflection method of the present disclosure is a preference reflection method executed by a preference reflection device for audio equipment to reflect a user's preferences in the audio equipment, which selects an output characteristic that specifies the output level for each frequency in the output sound based on reaction information that reflects the user's reaction to the output sound of the audio equipment, refers to the selected output characteristic, and sets the output characteristic of the output sound, wherein the reaction information is voice information produced by the user. Effect of the Invention

[0008] According to the present disclosure, output characteristics according to the acoustic preferences of each individual user, rather than fixed output characteristics, can be reflected in the output sound of an audio device, thereby making it possible to further increase user satisfaction. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram of an audio system including a preference reflecting device for audio equipment according to the present disclosure. [Figure 2A] FIG. 2A is a frequency response graph showing the output characteristics of an audio device of the prior art. [Figure 2B] FIG. 2B is a frequency characteristic graph of the audio equipment preference reflecting device of this embodiment. [Diagram 3] FIG. 3 is a block diagram classifying functions of the control unit of the audio equipment preference reflecting device. [Figure 4] FIG. 4 is a flowchart including the steps of an example of a preference reflecting method executed by the audio equipment preference reflecting device. [Diagram 5] FIG. 5 is a flowchart including the steps of another example of a preference reflecting method executed by the audio equipment preference reflecting device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] (Inventor's knowledge) For audio equipment such as radios and car stereos, the acoustic characteristics that affect the characteristics of the output sound are set at the time of shipment. Setting such acoustic characteristics requires a lot of trial and error, such as whether to prioritize a setting that reduces noise even at the expense of lowering sound quality, or vice versa.

[0011] Up until now, settings have had to rely on inferences based on insufficient information such as the designer's sensory evaluation, customer satisfaction scores surveyed in advance, etc. Therefore, it has not been possible to fully reflect in audio equipment detailed settings that match the preferences and environment of individual users.

[0012] Hereinafter, the audio equipment preference reflecting device and the preference reflecting method according to the present disclosure will be described in detail with reference to the drawings. FIG. 1 shows a block diagram of an audio system 100 including an audio equipment preference reflecting device 10 according to an embodiment. The audio system 100 is a system capable of outputting a sound that reflects a user's preferences, and includes the audio equipment preference reflecting device 10, a microphone 21, a camera 23, and an audio equipment 30. The audio system 100 is mounted on a vehicle such as a car, and can output a sound that matches the preferences of a user aboard the vehicle, but the installation location of the audio system is not particularly limited.

[0013] The audio equipment preference reflecting device 10 is a device for reflecting the preferences of a user in the audio equipment 30, and includes a control unit 11, a characteristic storage unit 13, a characteristic setting unit 15, a message output unit 17, and an input unit 19. The control unit 11 is configured with an arithmetic device such as a processor, and performs various processes to control the operation of the audio equipment preference reflecting device 10. The characteristic storage unit 13 is configured with a storage device such as a memory. The characteristic storage unit 13 stores, for example, output characteristics corresponding to the pattern of the output sound of the audio equipment 30. When the audio equipment 30 includes a radio receiving unit 35 described later, the characteristic storage unit 13 also stores characteristics corresponding to the radio receiving settings. The radio receiving settings are, for example, settings related to audio high cut settings and bandwidth control. The characteristic setting unit 15 is configured with various hardware circuits and the like. The characteristic setting unit 15 is configured with, for example, a DSP (Digital Signal Processor) circuit. The characteristic setting unit 15 sets the output sound of the audio device 30 in accordance with the output characteristics. In this case, if the audio device 30 includes a radio receiving unit 35 (described later), "setting the output sound of the audio device 30 in accordance with the output characteristics" includes changing the reception settings of the radio receiving unit 35.

[0014] Message output unit 17 is composed of an audio output device such as a speaker and a display device such as a liquid crystal display, and sends out a message asking for an evaluation of the output sound of audio equipment 30. Input unit 19 is composed of input devices such as a touch panel and switches, and an audio input device such as a microphone, and accepts a response entered by the user to the message output by message output unit 17.

[0015] The microphone 21 detects the user's voice in response to the output sound, and the camera 23 captures the user's facial expression, movement, attitude, etc., which reflect the user's reaction to the output sound. The user's voice detected by the microphone 21 and the user's facial expression, movement, attitude, etc., captured by the camera 23 are reaction information, which is the user's reaction to the output sound. Furthermore, the microphone 21 also detects radio noise, so-called auditory noise, picked up from a speaker constituting an output unit 33 of the audio device 30 described later, in the surrounding environment of the audio system 100. Note that the surrounding environment of the audio system 100 corresponds to the interior space of the vehicle when the audio system 100 is mounted in a vehicle. The auditory noise is noise containing various frequency components in an audio band, for example, 20 Hz to 20 kHz. The microphone 21 and the camera 23 are connected to the audio device preference reflecting device 10 via a predetermined interface, but the audio device preference reflecting device 10 may have the microphone 21 and the camera 23 built in.

[0016] The audio device 30 is an entertainment device that includes an operation unit 31, an output unit 33, a radio receiving unit 35, and an audio sound source unit 37, and can output sounds from various sound sources including radio such as AM radio and FM radio, various storage media such as CDs, and various audio data via a network. The operation unit 31 is composed of an input device such as a touch panel and a switch, and an audio input device such as a microphone, and accepts operation inputs of the audio device 30 by a user, such as volume control, radio channel switching, equalizer adjustment, etc. The output unit 33 is composed of an amplifier, a speaker, etc., and outputs sound. The radio receiving unit 35 receives radio, which is one of the sound sources, and outputs data such as the field strength and multipath environment of the received radio waves to the audio device preference reflecting device 10. The audio sound source unit 37 outputs data of audio devices other than radio, such as various storage media such as CDs, and various audio data via a network, to the audio device preference reflecting device 10.

[0017] The audio equipment preference reflecting device 10 can be connected to a network such as an external cloud system via a wired or wireless communication interface.

[0018] FIG. 2A shows a frequency characteristic graph showing output characteristics according to user preferences for a conventional audio device. The frequency characteristic graph is a graph with frequency on the horizontal axis and volume level on the vertical axis, visually showing output characteristics that define the output level for each frequency in the output sound of the audio device. Each person perceives sound differently. For example, some users may perceive high-pitched sounds as loud, while other users may not perceive the same high-pitched sounds as loud. Such preferences of each user are called preferences. Differences in preferences are expressed as differences in the shapes of the frequency characteristic graphs.

[0019] As shown in Fig. 2A, in the conventional technology, a single frequency response graph is prepared based on information such as the designer's sensory evaluation, customer satisfaction scores surveyed in advance, etc., and audio equipment outputs sound with fixed output characteristics that follow this frequency response graph. However, as mentioned above, sound preferences differ from person to person, and fixed output characteristics are not necessarily preferable for some people. For example, the output of the high-frequency range in the area circled by the dashed line in Fig. 2A may sound harsh to some people.

[0020] 2B shows a frequency characteristic graph in the preference reflecting device 10 for audio equipment of this embodiment. The preference reflecting device 10 for audio equipment of this embodiment stores a plurality of output characteristics corresponding to the pattern of the output sound of the audio equipment 30 in the characteristic storage unit 13 in advance, detects the customer's preference, and then selects a frequency characteristic graph that is an appropriate output characteristic according to the detected preference by the control unit 11. In response to this selection, the characteristic setting unit 15 sets the output characteristic of the output sound of the audio equipment 30. In selecting the output characteristic, the control unit 11 can use artificial intelligence (AI) equipped with a learned learning model that has undergone machine learning to estimate the user's reaction to the output sound.

[0021] FIG. 2B shows an example of a plurality of frequency characteristic graphs and their selection. In the frequency characteristic graph of this example, a plurality of preset types are prepared in advance, such as a high-quality type having a characteristic of leaving a certain degree of the waveform in the high-frequency range, a noise-oriented type having a characteristic of reducing noise by cutting the sound in the high-frequency range, and a medium-quality type having characteristics intermediate between the high-quality type and the noise-oriented type, and are stored in the characteristic storage unit 13. When the user of the audio device 30 feels that the output sound due to the output characteristics of the high-quality type is noisy, the audio device preference reflection device 10 switches the output characteristics of the high-quality type to the output characteristics of the medium-quality type or the output characteristics of the noise-oriented type. Of course, the user can also update the output characteristics at any time.

[0022] 3 is a block diagram classifying functions of the control unit 11 of the audio equipment preference reflection device 10. The control unit 11 judges whether the output sound of the audio equipment 30 is preferable for the user, i.e., whether it matches the user's preferences, based on information obtained from the microphone 21, the camera 23, and the audio equipment 30, and selects the output characteristic shown in the frequency characteristic graph shown in FIG. 2B according to the judgment result, and in some cases changes the previously set output characteristic.

[0023] Specifically, the control unit 11 captures voice information emitted by the user detected by the microphone 21 as user reaction information, and selects output characteristics stored in the characteristic storage unit 13 based on the voice information. The control unit 11 selects output characteristics stored in the characteristic storage unit 13 based on noise in the surrounding environment detected by the microphone 21. Furthermore, the control unit 11 captures imaging information including face information and action information of the user obtained by capturing an image of the user by the camera 23 as user reaction information, and selects output characteristics stored in the characteristic storage unit 13 based on the imaging information.

[0024] Regarding noise in the surrounding environment from the microphone 21, it may be determined whether the noise is harsh to the user's ears or not harsh, for example, a light noise. Regarding voice information emitted by the user, the emotion of the user may be determined based on the tone of the voice. Furthermore, regarding image information including facial expressions and actions shown by the user, the emotion of the user may be determined based on the facial expressions and actions.

[0025] Various methods can be used for such a judgment, and for example, an artificial intelligence (AI) equipped with a trained model that has been subjected to machine learning to estimate a user's reaction to the output sound of the audio device 30 can be used. The AI ​​may make a judgment of good or bad using a binary classification in which the output when input information of a predetermined format is input to the trained model takes only two values, A or B. The AI ​​may also classify the output when input information of a predetermined format is input to the trained model into multiple classes such as seven, ABCDEFG, and judge the class ABG as "good" and the class CEF as "bad", etc. Alternatively, the AI ​​may be configured so that the output when input information of a predetermined format is input to the trained model is a single scalar value, and this scalar value may be used as a score to judge, for example, a score of 80 or more as "good" and a score of less than 80 as "bad". "Good" means a comfortable state for the user, and "bad" means a state that is not comfortable for the user, for example, a state where the user thinks that the noise of the radio is loud.

[0026] The characteristic storage unit 13 can store a trained model of AI. The control unit 11 can perform AI judgment by inputting the above-mentioned noise, voice information, face information, motion information, etc., after forming them into a predetermined format into the trained model stored in the characteristic storage unit 13. The trained model may be updated. The audio equipment preference reflecting device 10 uploads the acquired information related to the user's preferences to a server or the like via a cloud system. The destination device, such as the server, further performs machine learning, and the updated trained model is downloaded by the audio equipment preference reflecting device 10, and the downloaded trained model can be used thereafter.

[0027] Furthermore, the control unit 11 captures the user's operation on the operation unit 31 of the audio equipment 30 as reaction information, and selects the output characteristic stored in the characteristic storage unit 13 based on the operation. Such operations include, for example, switching the radio channel, adjusting the equalizer of the audio equipment 30, etc. Channel switching is an expression of the user's feeling that he / she does not like the currently set channel, and equalizer adjustment is an expression of the user's feeling that he / she does not like the currently set equalizer setting, and both are understood to reflect the user's feelings regarding the output sound of the audio equipment 30.

[0028] Furthermore, the control unit 11 selects the output characteristics stored in the characteristic storage unit 13 based on at least one of data such as the field strength or the multipath environment of the radio reception radio waves obtained from the radio reception unit 35. The indicators such as the field strength and the multipath environment are measures for evaluating the quality of the output sound, and are understood to affect the user's feelings about the output sound of the audio device 30 and reflect the user's feelings. The multipath environment also includes multipath noise and the like, and is an indicator of the level of deterioration of the radio wave condition. Even if this indicator is large, it may not be a harsh noise, and the AI ​​judgment of the noise detected by the microphone 21 compensates for this. Conversely, even if only the AI ​​judgment of the noise detected by the microphone 21 is used as a judgment indicator, it may be the content of the radio broadcast itself, so the state of the radio waves received by the radio reception unit 35 itself can also be used as a judgment indicator.

[0029] Furthermore, the control unit 11 selects the output characteristics stored in the characteristics storage unit 13 based on data on the sound source of an audio device other than a radio obtained from the audio sound source unit 37. The control unit 11 can directly detect the output characteristics of an audio device and use the detected characteristics to set the output characteristics.

[0030] The characteristic setting unit 15 is composed of various hardware circuits and the like, and sets the output sound of the audio device 30 in accordance with the output characteristics. The characteristic setting unit 15 includes various circuits related to the output sound, such as a frequency characteristic setting circuit and a high frequency filter circuit, and refers to the output characteristic selected by the control unit 11 in the characteristic storage unit 13, selects one from the characteristic storage unit 13, and sets the output sound accordingly.

[0031] The characteristic setting unit 15 sets the output sound of the audio device 30 in accordance with the output characteristics, and as described above, the change here includes changing the reception settings of radio waves by the radio receiving unit 35. The radio reception settings include, for example, three reception settings: bandwidth processing, high frequency range cutting processing, and low frequency range cutting processing.

[0032] Bandwidth processing is a process that controls the bandwidth of radio waves to be received according to the user's preferences. For example, in the case of FM radio, the narrower the intermediate frequency filter, the better the selection performance of the desired broadcast station in a weak electric field, and the less susceptible to ambient noise and neighboring broadcast stations. However, narrowing the bandwidth by cutting out the desired broadcast content will deteriorate the sound quality. The bandwidth is set according to the user's preferences, such as whether the user prioritizes noise reduction or sound quality. For a user who prioritizes noise reduction, the characteristic setting unit 15 sets the reception bandwidth of the radio receiving unit 35 to be relatively narrow, and for a user who prioritizes sound quality, the characteristic setting unit 15 sets the reception bandwidth of the radio receiving unit 35 to be relatively wide.

[0033] The high-frequency region cut processing is a process of changing the amount of high-frequency region cut processing in accordance with the user's preference. For example, when the radio reception radio wave is a weak electric field or when the multipath detection level is high, the radio reception unit 35 can reduce noise by increasing the amount of high-frequency region cut processing. The characteristic setting unit 15 can change, for example, the increase amount of the high-frequency region cut processing, or the electric field strength and multipath detection level that are thresholds for starting to increase the amount of high-frequency region cut processing, in accordance with the user's preference. For example, when the reception electric field strength becomes 30 dBu or less, the characteristic setting unit 15 changes the amount of high-frequency region cut processing of the radio reception unit 35 in accordance with the reception electric field strength and the user's preference. Alternatively, for example, when the multipath detection level is high, the characteristic setting unit 15 changes the amount of high-frequency region cut processing of the radio reception unit 35 in accordance with the user's preference. Note that the multipath detection level becomes high from a reception electric field strength of about 60-70 dBu, which is a relatively high value, so the characteristic setting unit 15 changes the amount of high-frequency region cut processing of the radio reception unit 35 in accordance with the reception electric field strength.

[0034] The low-frequency region cutting process is a process according to the user's preference, and is performed to suppress the sound becoming unclear due to the high-frequency region cutting process. However, the amount of processing in the low-frequency region cutting process is not determined according to the amount of processing in the high-frequency region cutting process, and the two are generally controlled independently.

[0035] The settings for the above-mentioned bandwidth processing, high-frequency region cutting processing, and low-frequency region cutting processing can be changed independently, but which one is given priority according to the user's preference varies depending on the conditions of the receiving electric field, etc. For example, in the case of a weak electric field, the processing to narrow the bandwidth can be given priority.

[0036] 4 is a flowchart showing the steps of a preference reflection method for reflecting a user's preferences in an audio device, performed by the audio device preference reflection device 10. Note that this example shows the steps when the sound source of the audio device 30 is a radio.

[0037] The control unit 11 determines whether the received radio wave corresponds to at least one of a weak electric field and a multipath environment based on data on the electric field strength from the radio receiving unit 35 (step S101). A weak electric field may be defined as an electric field having an output value below a predetermined value, such as a predetermined dBu or dBm value. For example, the control unit 11 may determine that an output value of 30 dBu or less is a weak electric field.

[0038] Furthermore, the control unit 11 judges whether the radio wave reception conditions are a multipath environment, i.e., multipath wave propagation, based on data on the multipath environment from the radio receiving unit 35. The judgment of whether the radio wave reception conditions are a multipath environment can be made based on whether the multipath detection level is a predetermined value or more, for example, 10 dB or more. If the radio wave reception conditions are not a weak electric field or multipath environment (step S101: No), there is no need to change the output setting, so no further processing is performed and the process returns to step S101.

[0039] If the radio wave reception condition is at least one of a weak electric field and a multipath environment (step S101: Yes), the control unit 11 determines the level of noise based on the AI-based determination information on the noise in the surrounding environment detected by the microphone 21 (step S103). For example, if the AI ​​determines that the noise is unlikely to be unpleasant to the user (step S103: No), there is no need to change the output setting, so no further processing is performed and the process returns to step S101.

[0040] As an example, suppose that the AI ​​determines that the noise in the surrounding environment detected by the microphone 21 has a 10% possibility of being very harsh, an 80% possibility of being harsh, a 7% possibility of being medium, and a 3% possibility of being light. For the harsh and very harsh noises, the control unit 11 determines that the noise is likely to be harsh to the user (step S103: Yes). For the medium and light noises, the control unit 11 determines that the noise is not likely to be harsh to the user (step S103: No). In the above example, the noise has the highest possibility of being harsh, at 80%, so the control unit 11 determines that the noise is likely to be harsh to the user (step S103: Yes).

[0041] When the control unit 11 determines that the noise may be unpleasant to the user (step S103: Yes), the control unit 11 determines whether the user has operated the operation unit 31 to change the radio channel (step S104). When the control unit 11 detects a channel change, that is, when the control unit 11 detects that the user has changed the channel because he does not like the current channel (step S104: Yes), the control unit 11 sends a message to the user via the message output unit 17 to ask for his / her evaluation of the output sound of the audio device 30 (step S106). The content of the message may be, for example, "Is the radio noise too loud? Would you like to change the settings?", which asks for the user's evaluation of the output sound, and the content of the message can be set appropriately. In response to the sent message, the user inputs a response via the input unit 19 or ignores the message. When the control unit 11 does not receive a response from the user to the message (step S106: No), that is, when the user's response to the message is negative or there is no response, there is no need to change the output settings, so no further processing is performed and the process returns to step S101. When the input unit 19 is an input device such as a touch panel or a switch, the user manually operates the input unit 19 to answer. When the input unit 19 is a voice input device such as a microphone, the user inputs the answer by voice.

[0042] If the user responds in agreement with the message (step S106: Yes), the control unit 11 selects an appropriate output characteristic stored in the characteristic storage unit 13, and the characteristic setting unit 15 refers to the output characteristic selected by the control unit 11 in the characteristic storage unit 13 and sets the output characteristic of the output sound (step S107). This setting varies depending on the user's reaction, but for example, if the user's reaction is that noise or high-pitched sounds are harsh to the ears, the control unit 11 can select an output characteristic with a lower output level in the high-frequency range compared to the output characteristic already set, as in the example of FIG. 2B. In other words, if the output characteristic already set by the characteristic setting unit 15 is a high-sound quality type or a medium-sound quality type and this characteristic is to be changed, the control unit 11 selects a noise-emphasizing output characteristic having a characteristic of reducing noise by cutting high-pitched sounds, and the characteristic setting unit 15 sets the noise-emphasizing output characteristic. As a result, the output unit 33 outputs a sound with a lower output level in the high-frequency range compared to before, and the user is less likely to feel that noise or high-pitched sounds are harsh to the ears.

[0043] If no channel switching by the operation unit 31 is detected in step S104 (step S104: No), the control unit 11 further determines whether or not the user has adjusted the equalizer or operated the volume by operating the operation unit 31 (step S105). If equalizer adjustment or volume operation by the operation unit 31 is detected (step S105: Yes), the process proceeds to the above-mentioned step S106, and the control unit 11 sends a message to the user via the message output unit 17, asking for an evaluation of the output sound of the audio device 30.

[0044] If no equalizer adjustment or volume operation by the operation unit 31 is detected (step S105: No), the control unit 11 judges whether the user's emotions are positive or not toward the output sound of the audio device 30, in this example, the sound of the radio, based on the AI ​​judgment information on the user's voice detected by the microphone 21 (step S108). If it is judged that the reaction to the voice is positive (step S108: Yes), there is no need to change the output settings, so no further processing is performed and the process returns to step S101. Examples of detecting a positive reaction include when humming is detected, or when the tone of the voice is higher than normal.

[0045] If the control unit 11 does not obtain a positive reaction to the voice (step S108: No), the control unit 11 further determines whether the user's emotion is negative toward the output sound of the audio device 30, that is, toward the sound of the radio in this example, based on the AI-based determination information regarding the user's voice detected by the microphone 21 (step S109). If the control unit 11 obtains a negative reaction to the voice (step S109: Yes), the process proceeds to the above-mentioned step S106, and the control unit 11 sends the user a message via the message output unit 17 asking the user to evaluate the output sound of the audio device 30. An example of a negative reaction is when a negative statement such as "noisy" or "not so good" is detected (for example, three or more times per day).

[0046] If the control unit 11 does not obtain a negative reaction to the sound (step S109: No), it further determines whether the user's emotions are positive toward the output sound of the audio device 30, in this example, the sound of the radio, i.e., whether the emotions are positive or not, based on the AI-based determination information of the image of the user captured by the camera 23 (step S110). If the control unit 11 obtains a positive reaction (step S110: Yes), there is no need to change the output settings, so no further processing is performed and the process returns to step S101. Examples of detecting a positive reaction include detecting a smile, detecting a state in which the body is moving, and detecting the rhythm of the movement.

[0047] If the control unit 11 does not obtain a positive reaction to the image captured by the camera (step S110: No), the control unit 11 further determines whether the user's emotion is negative or not toward the output sound of the audio device 30, that is, the sound of the radio in this example, based on the AI-based determination information on the image of the user captured by the camera 23 (step S111). If the control unit 11 obtains a negative reaction to the sound (step S111: Yes), the process proceeds to the above-mentioned step S106, and the control unit 11 sends the user a message via the message output unit 17 asking the user to evaluate the output sound of the audio device 30. If the control unit 11 does not obtain a negative reaction (step S111: No), there is no need to change the output setting, so no further process is performed and the process returns to step S101. An example of a negative reaction detection is a case where an unpleasant facial expression is detected (for example, three or more times per day).

[0048] According to the present disclosure, output characteristics according to the preferences of each individual user, rather than fixed output characteristics, can be reflected in the output sound of an audio device, thereby making it possible to further increase user satisfaction.

[0049] Particularly in this embodiment, as in steps S104 to S106, a user operation such as channel switching or equalizer adjustment using the operation unit 31 is one piece of response information, and when the operation occurs, the control unit 11 can send the user a message asking for their evaluation of the output sound via the message output unit 17. Therefore, it is possible to determine whether or not to change the output characteristics after confirming the user's preference for the output sound, and it is possible to more appropriately determine whether or not to change the settings of the output characteristics.

[0050] In this embodiment, as in steps S108 and S109, voice information uttered by the user and acquired from the microphone 21 is one type of reaction information, and the user's preferences can be easily acquired. If the voice information is positive, the control unit 11 does not change the output characteristics that have already been set, and if the voice information is negative, the control unit 11 can send the user a message asking for an evaluation of the output sound via the message output unit 17. Therefore, it is possible to determine whether or not to change the output characteristics after confirming the user's preferences for the output sound, and it is possible to more appropriately determine whether or not to change the settings of the output characteristics.

[0051] Furthermore, in this embodiment, as in steps S110 and S111, imaging information obtained by imaging the user from the camera 23 is one type of reaction information, and the user's preferences can be easily obtained. If the imaging information is positive, the control unit 11 does not change the output characteristics that have already been set, and if the imaging information is negative, the control unit 11 can send the user a message asking for an evaluation of the output sound via the message output unit 17. Thus, it is possible to determine whether or not to change the output characteristics after confirming the user's preferences for the output sound, and it is possible to more appropriately determine whether or not to change the settings of the output characteristics.

[0052] In this embodiment, when the audio device 30 is a radio, the control unit 11 captures at least one of the electric field strength of the radio's received radio waves or the multipath environment of the received radio waves in addition to the user's response information, as in step S101. Then, the control unit 11 selects the output characteristic in the subsequent step. Therefore, it can be said that the control unit 11 can select the output characteristic stored in the characteristic storage unit 13 based on at least one of the electric field strength of the radio's received radio waves or the multipath environment of the received radio waves.

[0053] In this embodiment, the control unit 11 captures the noise in the surrounding environment in addition to the user's reaction information, as in step S103. Then, the control unit 11 selects the output characteristic in the subsequent step. Therefore, it can be said that the control unit 11 can select the output characteristic stored in the characteristic storage unit 13 based on the noise in the surrounding environment.

[0054] When the sound source of the acoustic device 30 is an audio device other than a radio, for example, various audio data from a storage medium such as a CD or a network, steps S101 and S104 can be omitted. FIG. 5 shows a flowchart illustrating the procedure of a preference reflection method for such a sound source. The control unit 11 judges the level of noise based on the AI-determined information on the noise in the surrounding environment detected by the microphone 21 (step S103). For example, when the AI ​​determines that the noise is unlikely to be unpleasant to the user (step S103: No), the control unit 11 further judges whether the user has adjusted the equalizer or operated the volume by operating the operation unit 31 (step S105). The other processes are the same as those shown in FIG. 4.

[0055] As described above, the audio equipment preference reflecting device 10 for reflecting the user's preferences in the audio equipment 30 includes a characteristic storage unit 13 for storing output characteristics that define the output level for each frequency in the output sound of the audio equipment 30, a control unit 11 for selecting the output characteristics stored in the characteristic storage unit 13 based on reaction information reflecting the user's reaction to the output sound, and a characteristic setting unit 15 for setting the output characteristics of the output sound by referring to the output characteristics selected by the control unit 11 in the characteristic storage unit 13. This makes it possible to reflect output characteristics according to the preferences of each individual user, rather than fixed output characteristics, in the output sound of the audio equipment 30, thereby further increasing user satisfaction.

[0056] The reaction information is a user's operation on the operation unit 31 of the audio device 30, and when the operation occurs, the control unit 11 sends the user a message asking for their evaluation of the output sound via the message output unit 17. This makes it possible to determine whether or not to change the output characteristics after confirming the user's preference for the output sound, and makes it possible to more appropriately determine whether or not to change the settings of the output characteristics.

[0057] The reaction information is voice information emitted by the user. If the voice information is positive, the control unit 11 does not change the output characteristics that have already been set. If the voice information is negative, the control unit 11 sends the user a message via the message output unit 17 asking the user to evaluate the output sound. This makes it possible to obtain the user's preferences based on the voice information emitted by the user and set the output characteristics of the output sound. In addition, it is possible to determine whether or not to change the output characteristics after confirming the user's preferences for the output sound, and therefore it is possible to more appropriately determine whether or not to change the settings of the output characteristics.

[0058] The reaction information is imaging information obtained by imaging the user. If the imaging information is positive, the control unit 11 does not change the output characteristics that have already been set. If the imaging information is negative, the control unit 11 sends the user a message via the message output unit 17 asking for their evaluation of the output sound. This makes it possible to obtain the user's preferences based on the imaging information and set the output characteristics of the output sound. In addition, it is possible to determine whether or not to change the output characteristics after confirming the user's preferences for the output sound, and therefore it is possible to more appropriately determine whether or not to change the settings of the output characteristics.

[0059] Based on the reaction information as well as noise in the surrounding environment, the control unit 11 selects the output characteristic stored in the characteristic storage unit 13. This makes it possible to select the output characteristic based on noise in the surrounding environment.

[0060] The acoustic device 30 is a radio, and the control unit 11 selects the output characteristic stored in the characteristic storage unit 13 based on at least one of the field strength of the radio's received radio waves or the multipath environment of the received radio waves in addition to the response information. This makes it possible to select the output characteristic based on at least one of the field strength of the radio's received radio waves or the multipath environment of the received radio waves.

[0061] When the control unit 11 changes the output characteristics, the control unit 11 selects output characteristics with a lower output level in the high frequency range compared to the output characteristics already set, thereby changing the output characteristics so that the user does not find the high frequency range harsh.

[0062] When the control unit 11 changes the output characteristics, the control unit 11 selects output characteristics with a lower output level in the low frequency range compared to the output characteristics already set, thereby making it possible to change the output characteristics so as to prevent the sound from becoming unclear to the user.

[0063] When selecting the output characteristics, the control unit 11 uses artificial intelligence equipped with a trained model that has undergone machine learning to estimate the user's reaction to the output sound. This allows the output characteristics to be selected based on the judgment results of the artificial intelligence.

[0064] In a preference reflection method executed by the audio equipment preference reflection device 10 for reflecting user preferences in the audio equipment 30, output characteristics that define the output level for each frequency in the output sound are selected based on reaction information reflecting the user's reaction to the output sound of the audio equipment 30, and the selected output characteristics are referenced to set the output characteristics of the output sound. This makes it possible to reflect output characteristics according to the preferences of each individual user, rather than fixed output characteristics, in the output sound of the audio equipment 30, thereby further increasing user satisfaction.

[0065] The present invention is not limited to the above-described embodiment, and can be appropriately modified, improved, etc. In addition, the material, shape, size, numerical value, form, number, arrangement location, etc. of each component in the above-described embodiment are arbitrary as long as they can achieve the present invention, and are not limited. [Industrial Applicability]

[0066] According to the preference reflection device and preference reflection method for audio equipment disclosed herein, output characteristics according to the preferences of each individual user, rather than fixed output characteristics, can be reflected in the output sound of the audio equipment, making it possible to provide an audio equipment that can further improve user satisfaction. [Explanation of symbols]

[0067] 10 Preference reflection device for audio equipment 11 Control section 13 Characteristics memory section 15 Characteristics setting section 17 Message output section 19 Change instruction input section 21. Mike 23 Camera 30 Audio equipment 31 Operation section 33 Output section 35 Radio receiver 37 Audio source section 100 Sound System

Claims

1. A preference reflecting device for an audio device for reflecting a user's preferences in an audio device, a characteristic storage unit that stores an output characteristic that defines an output level for each frequency in an output sound of the audio device; A control unit that selects an output characteristic stored in the characteristic storage unit based on reaction information that reflects a user's reaction to an output sound; a characteristic setting unit that refers to the output characteristic selected by the control unit in the characteristic storage unit and sets the output characteristic of the output sound; Equipped with The reaction information is voice information uttered by the user. Preference reflection device for audio equipment.

2. 2. The audio equipment preference reflecting device according to claim 1, If the voice information is positive, the control unit does not change the output characteristics already set. Preference reflection device for audio equipment.

3. 2. The audio equipment preference reflecting device according to claim 1, If the voice information is negative, the control unit sends a message to the user via a message output unit, the message asking the user to evaluate the output sound. Preference reflection device for audio equipment.

4. The preference reflecting device for audio equipment according to any one of claims 1 to 3, The control unit selects the output characteristic stored in the characteristic storage unit based on the reaction information as well as noise in the surrounding environment. Preference reflection device for audio equipment.

5. The preference reflecting device for audio equipment according to any one of claims 1 to 4, the audio device is a radio, The control unit selects the output characteristic stored in the characteristic storage unit based on at least one of the electric field strength of the radio wave received by the radio and the multipath environment of the received radio wave in addition to the response information. Preference reflection device for audio equipment.

6. The preference reflecting device for audio equipment according to any one of claims 1 to 5, When the control unit changes the output characteristic, the control unit selects an output characteristic having a lower output level in a high frequency region compared to the output characteristic already set. Preference reflection device for audio equipment.

7. The preference reflecting device for audio equipment according to any one of claims 1 to 5, When the control unit changes the output characteristic, the control unit selects an output characteristic having a lower output level in a low frequency region compared to the output characteristic already set. Preference reflection device for audio equipment.

8. The preference reflecting device for audio equipment according to any one of claims 1 to 7, The control unit uses artificial intelligence equipped with a trained model that has undergone machine learning to estimate a user's response to the output sound when selecting the output characteristics. Preference reflection device for audio equipment.

9. A preference reflecting method executed by an audio equipment preference reflecting device for reflecting a user's preferences in an audio equipment, comprising: selecting an output characteristic that defines an output level for each frequency of the output sound based on response information that reflects a user's response to the output sound of the audio device; Refer to the selected output characteristics and set the output characteristics of the output sound. The reaction information is voice information uttered by the user. How to reflect preference.

Images