Auditory Environmental Perception Health Promotion System

Abstract

This invention provides an auditory environmental perception health promotion system, comprising: a sensing device, a processing device, an interactive device, and a treatment device. The sensing device receives sound signals from the surrounding environment or senses physiological characteristics of the user. The processing device stores multiple unfriendly voiceprint features and physiological modalities. When the processing device determines that a sound signal matches one of the unfriendly voiceprint features or that a physiological feature differs from a physiological modality, the processing device generates a noise reduction command signal. The interactive device is equipped with an application program that can receive and obtain matching audio from an audio medium based on the noise reduction command signal. The treatment device can play the audio. Therefore, when noise is detected, audio can be used to reduce the impact of noise on the user and improve the user's discomfort caused by noise.

Description

Technical Field

[0001] This invention relates to the field of noise reduction, and more particularly to an auditory environmental perception health promotion system that can reduce the impact of noise on users by using audio when noise is detected, thereby improving the user's discomfort caused by noise. Background Technology

[0002] From a physical perspective, noise is a chaotic sound with irregular and disordered frequency and intensity variations. However, if we analyze it further using the characteristics of time domain modulation frequency, noise is mostly a signal with high-frequency modulation characteristics. Noise can cause psychological or physiological discomfort. Psychologically, noise can cause unpleasant, uncomfortable, or irritable feelings, which can affect a person's conversation, thinking, work, study, or rest. Physiologically, excessive exposure to noise levels exceeding legal limits can cause hearing loss over a long period.

[0003] Conversely, audio or background sounds that help us relax typically have lower frequencies and stable, periodic patterns in their time domain modulation frequency (TMF) analysis. For example, the sound of ocean waves or flowing water contains rhythmic patterns with lower modulation frequencies. These frequency characteristics are also related to the frequency characteristics of our brain waves. This is why background audio or music that promotes focus or sleep often incorporates these lower-frequency sounds, which indirectly helps us relax.

[0004] Furthermore, although noise is a subjective experience, and everyone's perception of noise varies depending on their feelings and habits, prolonged exposure to noise can indirectly affect a person's physical and mental health. Besides causing psychological distress, noise can also lead to varying degrees of hearing loss without the person realizing it. For example, prolonged exposure to noise levels above 85 decibels can affect hearing, and prolonged exposure to noise levels above 120 decibels can cause deafness. Therefore, to reduce the impact of noise on the surrounding environment and humans, standard instruments are needed for detection, and noise levels should be controlled when they exceed the standard to prevent noise from affecting people's lives. Noise can also impact cardiovascular health; clinical research data shows a high correlation between cardiovascular health and exposure to noise environments.

[0005] Noise is usually detected by a noise meter, which quantifies the sound and uses a standard decibel value to determine whether noise is generated. However, a noise meter can only detect whether noise is present, but cannot suppress or reduce the noise. The noise will continue to affect the listener, causing discomfort. Summary of the Invention

[0006] To address the aforementioned issues, this invention provides an auditory environment perception health promotion system that can activate the noise reduction function on the device when it detects external auditory environment exposure to excessive noise, and use specific audio content to reduce the impact of noise on the user and improve the user's discomfort caused by noise; or detect irritability caused by psychological factors, and then remind and, with the user's authorization, activate specific audio presets to soothe the mood.

[0007] One embodiment of the present invention provides an auditory environmental perception health promotion system, comprising: a sensing device that receives a sound signal from the surrounding environment or senses a physiological feature of a user; and a processing device coupled to the sensing device, the processing device having a database and an analysis module coupled to each other. The database stores a plurality of unfriendly voiceprint features and a physiological modality. The analysis module receives the sound signal and performs signal processing and feature conversion on the sound signal to generate an environmental voiceprint feature. The analysis module determines whether the environmental voiceprint feature matches each of the unfriendly voiceprint features in the database. When the environmental voiceprint feature matches one of the unfriendly voiceprint features... An analysis module generates a noise reduction command signal; or the analysis module receives physiological features and processes and transforms these features to generate a current physiological feature model. The analysis module compares the current physiological feature model with the physiological modality. When the analysis module determines that the current physiological feature model is different from the normal physiological modality, the analysis module generates a noise reduction command signal; an interactive device, whose processing device and an audio medium are coupled, the interactive device is equipped with an application that can receive the noise reduction command signal and obtain a matching audio from a plurality of audio from the audio medium according to the noise reduction command signal; and a client device coupled to the interactive device, the client device being able to play audio.

[0008] Through the above, the present invention can detect whether noise is generated in the environment, and when noise is detected, obtain appropriate audio from the audio medium according to the sound characteristics of the noise, and reduce the impact of noise on the user by playing the audio, thereby improving the user's discomfort caused by noise.

[0009] Furthermore, the present invention can detect whether the user has a tendency to be irritable and restless, and when it detects that the physiological characteristics are abnormal for a long time, it will remind the user and obtain appropriate audio from the audio media with the user's authorization. The playback of the audio will reduce the user's irritability and improve the discomfort caused by the user's irritability.

[0010] In one embodiment, the sensing device is provided with a capture threshold. When the sensing device determines that the sound signal has reached the capture threshold, the sensing device generates a processing signal and transmits the sound signal to the processing device according to the processing signal. In this way, it can enter a sleep state in a friendly environment to achieve the effect of energy saving.

[0011] In one embodiment, the application has an account module and a setting module. The account module provides the ability to create an account. The setting module provides the corresponding account information to set the environmental soundprint feature as a noise feature. The setting module transmits the noise feature to the database of the processing device and saves it as the unfriendly soundprint feature. In this way, users can set noise standards according to their own situation, so that the analysis results can be closer to the user's needs.

[0012] In one embodiment, the database stores a plurality of noise pattern features, each unfriendly voiceprint feature corresponding to at least one row of noise pattern features; the noise reduction command signal contains a search command and at least one row of noise pattern features corresponding to the unfriendly voiceprint feature; the processing device is coupled to the audio media, and the analysis module is coupled to the audio media according to the search command of the noise reduction command signal, and obtains the audio matching the noise reduction pattern features from each audio of the audio media according to the noise reduction pattern features of the noise reduction command signal; thereby, noise can be effectively reduced through audio.

[0013] In one embodiment, the environmental soundprint features have a frequency feature and a time feature; the analysis module performs a weight configuration operation on the frequency feature, time feature and the matched unfriendly soundprint features. When the result of the weight configuration operation reaches a noise reduction threshold, the analysis module generates a noise reduction command signal; thereby, through weight configuration, the analysis information results can be made closer to the user's needs.

[0014] In one embodiment, the application has a preference module; the preference module provides a preferred audio information to be set according to the corresponding account information, and the acquisition module can acquire matching audio from the audio media according to the noise reduction instruction signal and the preferred audio information; thereby, by referring to the user's preferences, the acquired audio can be made more suitable for the user.

[0015] In one embodiment, the interactive device has a positioning module that generates a location signal; the preference module has a matching unit and a labeling unit, the matching unit provides setting preference audio information; the labeling unit integrates the location signal with the acquired audio to form a status information; thereby, it is possible to record and understand the user's audio selection and preference habits in different noise environments, so as to intelligently obtain audio suitable for the user.

[0016] In one embodiment, the application has an interaction module that provides a like / dislike option. This like / dislike option can be triggered to generate a like / dislike signal. The interaction module can integrate the like / dislike signal with the audio played by the user device to form a like / dislike information. The interaction module stores the like / dislike information along with the corresponding account information. The acquisition module can obtain matching audio from the audio media based on the noise reduction command signal, the preferred audio information, and the like / dislike information. In this way, the user's audio likes and dislikes can be recorded and understood to obtain a higher probability of audio matching suitable for the user in different environments. Attached Figure Description

[0017] Figure 1 This is a block diagram of the system architecture of the present invention;

[0018] Figure 2 This is a block diagram of the application of this invention;

[0019] Figure 3 This is a flowchart of the sound signal processing of the present invention;

[0020] Figure 4 This is a flowchart of the physiological characteristic processing of the present invention;

[0021] Figure 5 This is a schematic diagram of environmental acoustic signature features of the present invention, representing a noisy environment;

[0022] Figure 6 This is a schematic diagram of the physiological characteristics of the present invention;

[0023] Figure 7 This is a schematic diagram of the current physiological characteristic model of the present invention;

[0024] Figure 8 This is a schematic diagram of the cochlear conversion model of the present invention.

[0025] Label Explanation:

[0026] 1. Audio media; 100. Auditory environment perception health promotion system; 10. Sensing device; 11. First detection module; 12. Second detection module; 20. Processing device; 21. Database; 22. Analysis module; 30. Interactive device; 31. Application program; 311. Acquisition module; 312. Account module; 313. Setting module; 314. Preference module; 314a. Coordination unit; 314b. Labeling unit; 315. Positioning module; 316. Fusion module; 316a. Audio library; 316b. Mixing unit; 317. Interactive module; 40. Treatment device. Detailed Implementation

[0027] To facilitate the explanation of the central idea of ​​the invention as stated in the above-described description of the invention, specific embodiments are provided below. The various objects in the embodiments are depicted according to a scale, size, deformation, or displacement suitable for illustration, rather than being drawn to the scale of actual components.

[0028] The singular forms “a,” “an,” and “the” used herein also include the plural forms unless the context clearly indicates otherwise. Furthermore, it should be understood that, when used in this specification, the terms “comprising” and / or “including” specify the presence of the stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, and / or components.

[0029] Furthermore, it should be understood that when an element is indicated as being "on," "electrically connected to," or "coupled to" another element, it may be directly on, electrically connected to, or coupled to the other element, or intermediate elements may be present. Conversely, when an element is indicated as being "directly on," "directly electrically connected to," or "directly coupled to" another element, no intermediate elements are present. In all diagrams, the same numbers denote the same elements. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items, as stated above.

[0030] Please see Figures 1 to 8 As shown, the present invention provides an auditory environmental perception health promotion system 100, which includes:

[0031] A sensing device 10 receives an audio signal from the environment or senses a physiological feature of the user; wherein the sensing device 10 can simultaneously acquire audio signals and physiological features, or receive only one of audio signals and sense physiological features, depending on the needs of the present application.

[0032] Furthermore, the sensing device 10 can receive sound signals and sense physiological characteristics using the same sensor or different sensors. In this embodiment of the invention, the sensing device 10 has a first detection module 11 and a second detection module 12. The first detection module 11 can be a microphone or other sound receiving element, and the first detection module 11 is used to receive sound signals from the surrounding environment. The second detection module 12 senses the physiological characteristics of the user, wherein the physiological characteristics can be heartbeat sounds, cardiovascular voiceprints, or other physiological states of the user. The user's physiological state can be comfortable, anxious, or restless due to physical or psychological states, which will cause the second detection module 12 to sense different physiological characteristics. In other embodiments, the second detection module 12 can be a type of wearable device, such as a bracelet, wristband, etc., but the invention is not limited thereto.

[0033] A processing device 20, coupled to a sensing device 10, includes a database 21 and an analysis module 22, both coupled to each other. The analysis module 22 receives sound signals from a first detection module 11 of the sensing device 10. The analysis module 22 processes the sound signals through signal processing and feature conversion to generate an environmental sound signature. Figure 5 These are the environmental acoustic signatures generated in noisy environments.

[0034] Furthermore, the signal processing amplifies and adjusts the gain of the sound signal; the feature transformation utilizes spectral temporal transformation, which can be cochlear wavelet transformation or Fourier transformation; in this embodiment of the invention, the feature transformation utilizes cochlear wavelet transformation.

[0035] Please refer to Figure 8 The basic principle of cochlear basal wavelet transform is based on the response characteristics of the basilar membrane, the main receptor in the cochlea, to sound signals. This response creates basal wavelets that express the characteristics of sound. Its key value lies in the fact that human sound perception is non-linear. Therefore, by utilizing basal wavelets that mimic the basilar membrane's sound perception characteristics, the dynamic characteristics of sound can be more accurately depicted, while also reflecting frequency response and exhibiting non-uniform frequency characteristics. This allows for easier differentiation between noise and speech features through cochlear basal wavelet transform. This enables backend processing to more efficiently distinguish between comfortable and unpleasant sound characteristics, facilitating subsequent assessments of whether a user has been exposed to unpleasant sound environments for too long and providing music to reduce the impact of noise.

[0036] Database 21 stores multiple unfriendly voiceprint features. Analysis module 22 determines whether the environmental voiceprint features match each of the unfriendly voiceprint features in database 21. When the environmental voiceprint features match one of the unfriendly voiceprint features, analysis module 22 generates a noise reduction command signal.

[0037] The environmental soundprint features have a frequency feature and a time feature; the analysis module 22 performs a weight configuration operation on the frequency feature, time feature and the matched unfriendly soundprint features. When the result of the weight configuration operation reaches a noise reduction threshold, the analysis module 22 generates a noise reduction command signal; in this embodiment of the invention, the noise reduction threshold is 1.

[0038] Further explanation: The frequency and duration of environmental sound signatures will affect whether the analysis module 22 considers them as noise. When different sounds are generated, the analysis module 22 needs to analyze and process them in real time. Since other factors in the environment may interfere with the accuracy of the judgment, the accuracy of the analysis can be improved through weight configuration calculation. Furthermore, a noise reduction command signal can be generated as soon as the noise is confirmed to occur.

[0039] Example 1: When the sound of a fire truck is continuously generated in the environment, the frequency characteristics of the environmental soundprint feature generated by this sound signal are high and the time characteristics are continuous. Moreover, it matches the unfriendly soundprint feature in the database 21. At this time, the analysis module 22 regards the weight values ​​of the frequency feature, time feature and the matched unfriendly soundprint feature as the highest. Through weight configuration calculation, the calculation result reaches the noise reduction threshold value of 1, and then a noise reduction command signal can be generated.

[0040] Example 2: When there is a continuous sound of vehicles passing by in the environment, the frequency characteristics of the environmental soundprint generated by this sound signal are low and there is no match for the non-friendly soundprint characteristics in database 21. However, the time characteristics are continuous. The analysis module 22 increases the weight of the time characteristics and performs calculations through weight configuration. When the calculation result reaches the noise reduction threshold value of 1, a noise reduction command signal can be generated.

[0041] Database 21 further stores a physiological modality; analysis module 22 is capable of receiving physiological characteristics (such as...) received by the second detection module 12 of sensing device 10. Figure 6 As shown, the physiological feature is a cardiovascular voiceprint. The analysis module 22 processes the physiological features through signal processing and feature transformation to generate a current physiological feature model (such as...). Figure 7 As shown), the analysis module 22 can obtain physiological modalities from the database 21 and compare the current physiological feature model with the physiological modalities. When the analysis module 22 determines that the current physiological feature model is different from the physiological modalities, it indicates that the user is currently in a state of anxiety or restlessness, and the analysis module 22 will generate a noise reduction command signal. It should be noted that the physiological modalities are the physiological features captured when a person is in a calm and non-anxious state.

[0042] An interactive device 30 is coupled to a processing device 20 and an audio medium 1. The interactive device 30 is equipped with an application 31. The application 31 has an acquisition module 311. The acquisition module 311 of the application 31 can receive a noise reduction command signal and, according to the noise reduction command signal, acquire a matching audio from a plurality of audios in the audio medium 1. The audio medium 1 can be an audio streaming platform (e.g., Spotify, Apple Music, KKBOX, YouTube, YouTube Premium, QQMusic, NetEase Music, etc.) or a media database built into the interactive device 30.

[0043] In one embodiment of the present invention, the database 21 of the processing device 20 stores a plurality of noise pattern features, each unfriendly voiceprint feature corresponding to at least one row of noise pattern features, and the noise reduction command signal contains a search command and at least one row of noise pattern features corresponding to the unfriendly voiceprint feature; the processing device 20 is coupled to the audio medium 1, and the analysis module 22 is coupled to the audio medium 1 according to the search command of the noise reduction command signal, and obtains the audio matching the noise reduction pattern features from each audio of the audio medium 1 according to the noise reduction pattern features of the noise reduction command signal, and the processing device 20 can transmit the obtained audio to the acquisition module 311 of the application 31; thereby, the voiceprint features of the audio and the sound signal can be fused together, thereby achieving the effect of suppressing the sound signal.

[0044] Please see Figure 2 As shown, the application 31 has an account module 312, a settings module 313, and a preference module 314. The account module 312 provides the ability to create an account, which is considered as a member created by the user. The settings module 313 provides the ability to set the environmental soundprint feature as a noise feature according to the account information. The settings module 313 transmits the noise feature to the database 21 of the processing device 20 and saves it as a non-friendly soundprint feature. The preference module 314 provides the ability to set a preferred audio information according to the account information. The acquisition module 311 can acquire the matching audio from the audio media 1 according to the noise reduction command signal and the preferred audio information.

[0045] The interactive device 30 has a positioning module 315 that generates a position signal; the preference module 314 has a coordination unit 314a and a labeling unit 314b, the coordination unit 314a provides setting preference audio information; the position signal of the labeling unit 314b is integrated with the acquired audio to form a status information, so that the preference for audio can be recorded at different locations.

[0046] For example, when the user's location signal is displayed as a sports field, and the type of audio selected by the acquisition module 311 is dynamic audio, the status information will combine the sports field with the dynamic audio. In the future, when the user's location signal is a sports field, the acquisition module 311 will directly select dynamic audio from the audio media 1.

[0047] Application 31 has a fusion module 316, which has an audio library 316a and a mixing unit 316b. The audio library 316a stores a plurality of background audios, and the mixing unit 316b provides one of the background audios selected by the audio library 316a. The mixing unit 316b can receive the audio obtained by the acquisition module 311 and can fuse the selected background audio with the audio obtained by the acquisition module 311 to generate a new audio. The background audio can be natural sounds, ocean waves, white noise, wind, rain, flowing water, etc., and the background audio can be originally built into the audio library 316a or can be additionally created and stored in the audio library 316a by the user.

[0048] Among them, the mixing unit 316b works on a principle similar to mixing technology in recording engineering. It adjusts the background audio separately according to the frequency, dynamics, sound quality, positioning, reverberation and sound field of each individual original background audio, so that the background audio is optimized with each track, and then superimposed and output.

[0049] A client device 40 is coupled to an interactive device 30. An acquisition module 311 transmits audio to the client device 40, which can play the audio. In one embodiment of the present invention, the application 31 further includes an interaction module 317, which provides a like / dislike option that can be triggered to generate a like / dislike signal. The interaction module 317 can integrate the like / dislike signal with the audio played by the client device 40 to form like / dislike information. The interaction module 317 stores the like / dislike information corresponding to account information. The acquisition module 311 can acquire matching audio from the audio media 1 based on the noise reduction command signal, the preferred audio information, and the like / dislike information, and transmit the acquired audio to the client device 40 for playback.

[0050] Please see Figures 1 to 4To further explain: When the acquisition module 311 obtains a suitable audio file from the audio media 1 based on the current environment and plays it on the device 40, the interaction module 317 of the application 31 will generate a like / dislike option for the audio file. The user can make a selection based on their feelings about the audio file, and the selection result will generate like / dislike information. This audio file and like / dislike information will be integrated and stored in the account information. That is, when the user selects the like option, the acquisition module 311 will know that this audio file or even similar audio files are liked by the user. In the future, when selecting audio files on the audio media 1, it will use this as a reference to select audio files in this direction. Conversely, when the user selects the dislike option, the acquisition module 311 will know that this audio file or even similar audio files are disliked by the user. In the future, when selecting audio files on the audio media 1, it will use this as a reference to avoid selecting audio files in this direction.

[0051] In other possible embodiments of the present invention, the acquisition module 311 of the application 31 receives a noise reduction instruction signal and displays a reminder on the application 31 according to the noise reduction instruction signal (e.g., currently in a noisy environment or currently in an anxious or restless state). The application 31 also enables the treatment device 40 and connects it in series with the audio media 1 through user authorization. The audio media 1 acquires the matching audio and plays it through the treatment device 40. In this way, mood-improving actions can be provided, such as playing relaxing background audio to relieve stress, or prompting the user to wear noise-canceling headphones to reduce the impact of environmental noise on physical and mental discomfort. This can improve the impact of the user's irritability on their life and indirectly promote the user's hearing and cardiovascular health, or serve as a preventive screening for early health conditions.

[0052] It should be noted that the second detection module 12 continuously receives the user's physiological characteristics. After the audio played by the device 40 has improved the user's mood, the physiological characteristics received by the second detection module 12 will be converted by the processing device 20 to generate a current physiological characteristic model that conforms to the physiological modality. The processing device 20 will generate an improved signal and transmit the improved signal to the application 31 of the interactive device 30. The application 31 will display the improved signal.

[0053] In this embodiment of the invention, the sensing device 10, processing device 20, interactive device 30, and client device 40 can be individual devices, or two or more of them can be integrated together. When the sensing device 10, processing device 20, interactive device 30, and client device 40 are individual devices, the sensing device 10 is a microphone, sound detector, acoustic sensor, or other type of sound receiving device; the processing device 20 is hosted on a cloud server; the interactive device 30 is a mobile terminal device or other type of interactive interface device, and the interactive device 30 is connected to the processing device 20 via the Internet through an application 31. The interactive device 30 is coupled to the sensing device 10, and the application 31 receives ambient sound signature features and transmits them to the processing device 20; the client device 40 is an earphone, a sound player, or a speaker.

[0054] In one embodiment of the present invention, the sensing device 10 and the treatment device 40 are separate devices, while the processing device 20 and the interactive device 30 are integrated together. The sensing device 10 is a microphone, a sound detector, an acoustic sensor or other type of sound receiving device; the processing device 20 and the interactive device 30 are integrated into a mobile terminal device; and the treatment device 40 is an earphone, a sound player or a speaker.

[0055] In another embodiment of the present invention, the sensing device 10 and the treatment device 40 are integrated together, and the processing device 20 and the interaction device 30 are integrated together, wherein the sensing device 10 and the treatment device 40 are earphones; and the processing device 20 and the interaction device 30 are integrated into a mobile terminal device.

[0056] In another embodiment of the present invention, the sensing device 10 and the client device 40 are integrated, and the processing device 20 and the interaction device 30 are independent devices. The sensing device 10 and the client device 40 are earphones; the processing device 20 is mounted on a cloud server; and the interaction device 30 is a mobile terminal device or other type of interactive interface device.

[0057] In another embodiment of the present invention, the sensing device 10, the processing device 20, the interaction device 30 and the client device 40 are integrated with each other. In this embodiment, the sensing device 10, the processing device 20, the interaction device 30 and the client device 40 can be used in a mobile terminal device.

[0058] In summary, the present invention can achieve the following effects:

[0059] 1. The auditory environment perception health promotion system 100 of the present invention detects whether there is noise in the environment, and when noise is detected, obtains appropriate audio from audio media 1 according to the sound characteristics of the noise, and reduces the impact of noise on the user by playing the audio, thereby improving the user's discomfort caused by noise.

[0060] 2. The auditory environment perception health promotion system 100 of the present invention can detect whether the user has a tendency to be irritable and restless, and when it detects that the physiological characteristics are abnormal for a long time, it will remind the user and obtain appropriate audio from the audio media 1 with the user's authorization. The playback of the audio will reduce the user's irritability and improve the discomfort caused by the user's irritability.

[0061] 3. The auditory environment perception health promotion system 100 of the present invention can set a threshold for the sensing device 10 to determine whether to start detecting sound signals. In this way, it can enter a dormant state in a friendly environment to achieve the effect of energy saving.

[0062] 4. The auditory environment perception health promotion system 100 of the present invention provides the ability to set noise characteristics and transfer noise characteristics to non-friendly voiceprint characteristics; thereby, users can set noise standards according to their own conditions, so that the analysis results can be closer to the user's needs.

[0063] 5. The auditory environment perception health promotion system 100 of the present invention can obtain the audio that matches the noise reduction texture characteristics according to the noise reduction command signal; thereby, noise is suppressed and improved through audio.

[0064] 6. The auditory environment perception health promotion system 100 of the present invention can make the analysis information results more closely match the user's needs through weight configuration.

[0065] 7. The auditory environment perception health promotion system 100 of the present invention can make the acquired audio more suitable for the user by taking into account the user's preferences.

[0066] 8. The auditory environment perception health promotion system 100 of the present invention can record and understand the user's audio habits in different environments, so as to intelligently obtain audio suitable for the user.

[0067] 9. The auditory environment perception health promotion system 100 of the present invention can record and understand the user's audio preferences in order to obtain audio suitable for the user.

[0068] The embodiments described above are merely illustrative of the present invention and are not intended to limit the scope of the invention. All modifications or variations made without departing from the spirit of the present invention are within the scope of protection intended by the present invention.

Claims

1. An auditory environmental perception health promotion system, characterized in that, Include: A sensing device for receiving an audio signal from the environment or sensing a physiological characteristic of the user; A processing device coupled to a sensing device includes a database and an analysis module coupled to each other. The database stores a plurality of unfriendly voiceprint features and at least one row of noise pattern features associated with each of the unfriendly voiceprint features, as well as a physiological modality. The analysis module receives the sound signal and processes the sound signal through a signal processing and feature conversion to generate an environmental soundprint feature. The environmental soundprint feature has a frequency feature and a time feature. The analysis module determines whether the environmental soundprint feature matches each of the unfriendly voiceprint features in the database, and combines the frequency feature, the time feature, and the matched unfriendly voiceprint features... The analysis module performs a weighted configuration calculation on the friendly voiceprint features. When the result of the weighted configuration calculation reaches a noise reduction threshold, the analysis module generates a noise reduction command signal. The noise reduction command signal is used to instruct the subsequent acquisition of the corresponding audio based on at least one row of noise text features associated with the matched unfriendly voiceprint features. Alternatively, the analysis module receives the physiological features and processes them through the signal processing and feature transformation to generate a current physiological feature model. The analysis module compares the current physiological feature model with the physiological modality. When the current physiological feature model differs from the physiological modality, the analysis module generates the noise reduction command signal. An interactive device, wherein the processing unit is coupled to an audio medium, the interactive device carries an application configured to: receive a noise reduction command signal, and, based on the noise reduction command signal, obtain multiple candidate audios from a plurality of audios in the audio medium, perform feature transformation on each candidate audio to obtain its respective audio voiceprint features, and select a target audio that matches at least one set of noise voiceprint features; and A pair of devices is coupled to the interactive device, and the pair of devices can play the audio.

2. The auditory environment perception health promotion system as described in claim 1, characterized in that, The sensing device has a first detection module and a second detection module. The first detection module receives the sound signal in the environment. The second detection module senses the physiological characteristics of the user. The sensing device has a capture threshold. When the sensing device determines that the sound signal reaches the capture threshold, the sensing device generates a processing signal and transmits the sound signal to the processing device according to the processing signal.

3. The auditory environment perception health promotion system as described in claim 2, characterized in that, The application has an account module and a settings module. The account module provides the ability to create an account. The settings module provides the ability to set the environmental soundprint feature as a noise feature corresponding to the account information. The settings module transmits the noise feature to the database of the processing device and saves it as the unfriendly soundprint feature. The audio media can be an audio streaming platform or a media database built into the interactive device.

4. The auditory environment perception health promotion system as described in claim 1, characterized in that, The signal processing involves amplifying and adjusting the gain of the sound signal; the feature conversion utilizes time-frequency domain conversion, which includes cochlear basilar wavelet conversion, to simulate the nonlinear frequency response of the human ear basilar membrane to sound in order to form the environmental acoustic signature features.

5. The auditory environment perception health promotion system as described in claim 1 or 3, characterized in that, The database contains multiple rows of noise pattern features, with each unfriendly voiceprint feature corresponding to at least one row of noise pattern features; the noise reduction command signal contains a search command and at least one row of noise pattern features corresponding to the unfriendly voiceprint feature. The processing device is coupled to the audio media. The analysis module can control the application to couple with the audio media according to the search command, and obtain the target audio that matches the noise reduction pattern feature from each audio in the audio media according to the noise reduction pattern feature of the noise reduction command signal.

6. The auditory environment perception health promotion system as described in claim 3, characterized in that, The application has an acquisition module that can acquire the audio from the audio media according to the noise reduction command signal and transmit the audio to the receiving device. The application also has a preference module that provides a preference audio information to be set for the account information. The acquisition module can acquire the matching audio from the audio media according to the noise reduction command signal and the preference audio information.

7. The auditory environment perception health promotion system as described in claim 6, characterized in that, The interactive device has a positioning module that generates a location signal; the preference module has a coordination unit and a labeling unit, the coordination unit provides setting of the preferred audio information; the labeling unit integrates the location signal with the acquired audio to form a status information.

8. The auditory environment perception health promotion system as described in claim 6, characterized in that, The application has an interactive module that provides a like / dislike option, which can be triggered to generate a like / dislike signal. The interactive module can integrate the like / dislike signal with the audio played by the device to form a like / dislike information. The interactive module stores the like / dislike information corresponding to the account information. The acquisition module can obtain the matching audio from the audio media based on the noise reduction command signal, the preferred audio information, and the like / dislike information.

9. The auditory environment perception health promotion system as described in claim 6, characterized in that, The application has a fusion module with an audio library and a mixing unit. The audio library contains a plurality of background audios. The mixing unit selects one of the background audios from the audio library and merges it with the audio obtained by the acquisition module to generate a new audio.

Images