Computer case lamp controller based on voice recognition

Abstract

The invention discloses a computer case lamp control based on voice recognition, which comprises a main control module, a double-MIC noise reduction, a PC host, an RGB lamp strip and an expansion module, and is characterized in that the main control module is a core part of the system and is responsible for coordinating and controlling the operation of the whole voice recognition and lamp control system; the dual-MIC noise reduction is a key technical point for improving speech recognition, and the dual-MIC noise reduction is a dual-microphone noise reduction technology. According to the computer case lamp controller based on voice recognition, advanced voice recognition based on a local model and an acoustic model are adopted, the voice recognition capability irrelevant to a loudspeaker (SI) can be created and applied, an expensive command data collection process is not needed, and dependence on network connection is not needed, so that voice information of a user is better protected; moreover, the response speed of local speech recognition is higher, and a local speech recognition solution allows a user to perform customization and optimization according to specific requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of computer case lighting control, in particular to computer case lighting control based on voice recognition. Background Art

[0002] The lights of the computer case are peripheral products of the computer, which are used to improve the appearance of the computer case. By adding RGB light strips inside the case or on the cooling fan, and then controlling the color and mode of the light strips through the control system, different lighting effects can be achieved.

[0003] In the prior art, a Chinese patent application numbered CN201610836822.2 discloses an LED light controller, including a power supply circuit, a dimming control circuit, a general control circuit, an LED drive circuit, and an LED combination lamp; the power supply circuit is connected to the general control circuit, the dimming control circuit is connected to the general control circuit, and the LED drive circuit is connected to the general control circuit and the LED combination lamp, respectively.

[0004] As another example in the prior art, a Chinese patent with application number CN201110173026.2 discloses a computer case music colored light, which is arranged on a computer case and flashes along with music. The computer case has an audio chip inside. The computer case music colored light includes an amplifier circuit, a monostable trigger, a single-chip unit, a drive circuit and a light-emitting unit. The amplifier circuit is used to amplify the audio signal output by the audio chip. The monostable trigger is connected to the amplifier circuit to control the single-chip unit to output a pulse width modulation signal that changes according to the output of the amplifier circuit. The drive circuit outputs a changing current under the control of the pulse width modulation signal to drive the light-emitting unit to emit light.

[0005] Based on the above materials, it can be seen that the light strips in the prior art generally control the lighting effects through computer software. However, in actual use, it is necessary to click and control through the software program on the computer interface. When performing complex computer operations (such as games, drawing, etc.), it is cumbersome to call up the control software for control, which affects the ongoing operations. Summary of the invention

[0006] The purpose of the present invention is to provide a computer case light control based on voice recognition to solve the problem of cumbersome software and mouse control proposed in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: a computer case lighting control based on voice recognition, comprising a main control module, dual MIC noise reduction, a PC host, an RGB light strip and an expansion module, characterized in that:

[0008] The main control module is the core part of the system, responsible for coordinating and controlling the operation of the entire speech recognition and lighting control system;

[0009] The dual MIC noise reduction is a key technical point to improve speech recognition. Dual MIC noise reduction is the most common noise reduction technology used on a large scale. It collects environmental noise through the cooperation of two microphones and suppresses background noise with advanced noise reduction algorithms.

[0010] The PC host is linked with the software on the PC side, and the main control module communicates with the PC host through the USB HID protocol and Win11 D Lighting, and uses ASUS Aura Sync for lighting effect control;

[0011] The RGB light strip is installed in the computer case and is a colorful lighting device;

[0012] The expansion module includes Bluetooth and WIFI interfaces, and both the Bluetooth and WIFI interfaces are integrated on the main control module.

[0013] Preferably, the chip of the main control module has two Cortex-M3 cores, and the two cores process in parallel. Core0 first performs a series of necessary initializations, and then creates an RTOS general task, and then creates three tasks, USBTask, RGB Task, and VR Task, in the general task. The main task of USB Task is the subsequent firmware online upgrade function and connecting to Win11 D lighting. The main task of RGB Task is RGB mode selection and sending instructions to Core1. If there is no voice command to select, it will be selected according to the priority of D Lighting>Aura Sync>Local. The main task of VR Task is to recognize the user's voice command; Core1 also first performs a series of necessary initializations, and then waits for Core0 instructions. If an instruction is received, it executes the corresponding program, otherwise it will wait.

[0014] Preferably, the dual MIC noise reduction is used in conjunction with voice recognition, wherein the voice recognition uses an MCU with an integrated audio codec module, the I2C bus is used to transmit control signals, and the I2S bus is used to transmit digital audio signals, converting user voice into machine-understandable text and instructions. In the computer chassis lighting control system, voice recognition allows users to control the switch, brightness, and color of RGB lights through voice commands.

[0015] Preferably, the speech recognition includes:

[0016] Sound collection: collect user's voice signals through microphone;

[0017] Preprocessing: preprocess the collected speech signals, including removing noise and enhancing signals;

[0018] Feature extraction: extract information that can represent speech features from the preprocessed speech signal. The extracted speech feature information includes spectrum and fundamental frequency.

[0019] Pattern matching: Matching the extracted speech features with the pre-stored speech model to identify what the user said;

[0020] Command execution: Execute corresponding lighting control commands according to the recognized content.

[0021] Preferably, the dual MIC noise reduction is based on two microphone arrays and advanced noise reduction algorithms to reduce or eliminate ambient noise. One main microphone is close to the speaker and is used to collect a mixed signal containing user voice and ambient noise. The other secondary microphone is far away from the speaker and is used to collect ambient noise. By comparing and algorithmically processing the signals collected by the two microphones, the user voice can be extracted and the ambient noise can be suppressed.

[0022] Preferably, the dual MIC noise reduction algorithm adopts an adaptive filtering algorithm, which includes three modules: filtering structure, performance criterion and adaptive algorithm. The filtering structure determines the signal processing method, the performance criterion is used to evaluate the filtering effect, and the adaptive algorithm adjusts the filter parameters according to the performance criterion.

[0023] Preferably, the data format of the RGB light strip is ARGB, that is, addressable RGB, which has a built-in control chip to control each LED lamp bead individually. The RGB light strip can achieve more complex lighting effects through programming.

[0024] Preferably, the Win11 D lighting is a native RGB lighting effect management tool developed by Microsoft for the Windows 11 system, which includes:

[0025] API call: Control RGB devices by calling system API. API allows applications to communicate with underlying hardware to achieve precise control of lighting effects.

[0026] HID LampArray standard: supports RGB devices that comply with the HID LampArray standard. HID is used to define the communication protocol between computers and external devices. LampArray is a subset of the HID standard and is specifically used to control lighting devices.

[0027] System settings integration: The overall functions are integrated into the system settings of Windows 11, and users can directly access and control RGB lighting effects through the system settings application.

[0028] Compared with the prior art, the beneficial effects of the present invention are: the computer case light control based on voice recognition adopts a new structural design. This product adopts advanced local model-based voice recognition. Based on the acoustic model, it can create application speaker-independent (SI) voice recognition capabilities without the need for expensive command data collection processes and without relying on network connections. Therefore, the user's voice information is better protected, and the local voice recognition has a faster response speed. The local voice recognition solution allows users to customize and optimize according to specific needs. It can be trained and optimized for specific languages, dialects or accents to improve recognition accuracy and adaptability. Using the corresponding tools on the software, you can easily and quickly create your own voice command model simply through text input. And it also has keyword recognition function, high noise resistance, adjustable sensitivity, voice quality assessment, and support for more than 30 common languages. The specific contents are as follows:

[0029] 1. Dual MIC noise reduction improves voice recognition accuracy: In the complex environment inside the chassis, noise generated by hardware such as chassis fans and graphics card fans often causes great interference to voice recognition, resulting in misrecognition of user voice commands or inaccurate response. An innovative dual MIC noise reduction solution is adopted. Through the design of dual microphone arrays, this solution can more effectively capture the user's voice and use advanced noise reduction algorithms to suppress background noise. This not only significantly improves the accuracy of voice recognition, but also ensures that even in a noisy chassis environment, the user's voice commands can be clearly and accurately captured and recognized, making the voice recognition accuracy rate reach an excellent performance of more than 95%.

[0030] 2. Win11 D-Lighting technology is an innovative feature launched by Microsoft in the Windows 11 operating system. It is used in various computer cases that require personalized lighting control. However, there are very few PC peripheral products that support win11 D-Lighting on the market. Only a few companies (such as ASUS) are making them. There is no very mature solution on the market. As the first batch of products that support D-Lighting, it is necessary to open the underlying protocol of D-Lighting through USB. With the continuous advancement of technology and the continuous changes in user needs, Win11 D-Lighting technology will continue to develop and improve.

[0031] 3. Reduce design difficulty and cost: Most of the voice recognition solutions on the market currently use plug-in solutions, which greatly increases the peripheral circuit and design difficulty. It not only increases the cost, but also occupies the volume of the chassis. By using integrated voice recognition chips, the design difficulty and cost are significantly reduced, the circuit design is simplified, and the demand for peripheral components is reduced, thereby effectively saving hardware and subsequent maintenance costs.

[0032] 4. Rich expansion functions: For the single control method on the market, this product can simultaneously support local voice control, win11 D Lighting, Aura Sync control and other third-party software (such as SignalRGB), screen expansion, and automatically adjust the color of the chassis light according to the content displayed on the screen, such as game scenes, video playback or picture display. It can also expand Bluetooth and other wired / wireless connections, cooperate with APP software for control, and can also connect the chassis fan for separate control to achieve PWM temperature control and speed regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a block diagram of a computer case lighting control system based on speech recognition according to the present invention;

[0034] Figure 2 This is the computer case light control software flow chart based on voice recognition of the present invention Figure I ;

[0035] Figure 3 This is the computer case light control software flow chart based on voice recognition of the present invention Figure II ;

[0036] Figure 4 This is the computer case light control software flow chart based on voice recognition of the present invention Figure III ;

[0037] Figure 5 This is the computer case light control software flow chart based on voice recognition of the present invention Figure IV ;

[0038] Figure 6 This is the main flow chart of speech recognition of the present invention;

[0039] Figure 7 This is a flow chart of the adaptive filtering system of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Example 1: Please refer to Figure 1-Figure 7 The present invention provides a technical solution: a computer case lighting control based on voice recognition, including a main control module, dual MIC noise reduction, a PC host, an RGB light strip and an expansion module:

[0042] The main control module is the core part of the system, responsible for coordinating and controlling the operation of the entire speech recognition and lighting control system;

[0043] Dual MIC noise reduction is a key technical point to improve speech recognition. Dual MIC noise reduction is the most common noise reduction technology used on a large scale. It collects environmental noise through the cooperation of two microphones and suppresses background noise with advanced noise reduction algorithms.

[0044] The PC host is linked with the PC software. The main control module communicates with the PC host through the USB HID protocol and Win11 DLighting, and uses ASUS Aura Sync for lighting effect control.

[0045] RGB light strips are installed in computer cases and are a colorful lighting device;

[0046] The expansion module includes Bluetooth and WIFI interfaces, and both Bluetooth and WIFI interfaces are integrated on the main control module.

[0047] The chip of the main control module has two Cortex-M3 cores, and the two cores process in parallel. Core0 first performs a series of necessary initializations, and then creates an RTOS general task, and then creates three tasks in the general task: USB Task, RGBTask, and VR Task. The main task of USB Task is the subsequent firmware online upgrade function and connecting to Win11 Dlighting. The main task of RGB Task is RGB mode selection and sending instructions to Core1. If there is no voice command to select, it will be selected according to the priority of D Lighting>Aura Sync>Local. The main task of VR Task is to recognize the user's voice commands; Core1 also performs a series of necessary initializations first, and then waits for Core0 instructions. If an instruction is received, the corresponding program will be executed, otherwise it will keep waiting.

[0048] Dual MIC noise reduction is used in conjunction with voice recognition, which uses an MCU with an integrated audio codec module. The I2C bus is used to transmit control signals, and the I2S bus is used to transmit digital audio signals, converting user voice into machine-understandable text and instructions. In the computer chassis lighting control system, voice recognition allows users to control the switch, brightness, and color of RGB lights through voice commands.

[0049] Speech recognition includes:

[0050] Sound collection: The user's voice signal is collected through the microphone. The main microphone (MIC1) is close to the speaker and is used to collect a mixed signal containing the user's voice and environmental noise. The collected signal is recorded as S1, where S1 = V (voice) + N1 (environmental noise). The secondary microphone (MIC2) is far away from the speaker and is mainly used to collect environmental noise. The collected signal is recorded as S2, where S2 ≈ N2 (environmental noise), and because the sound source is far away, N1 ≈ N2;

[0051] Preprocessing: The collected voice signals are preprocessed, including noise removal and signal enhancement. The collected signals are filtered to remove unnecessary frequency components, such as high-frequency noise or low-frequency interference, and the DC component in the signal is removed to avoid affecting subsequent processing. The signals collected by the main microphone and the auxiliary microphone are subjected to difference processing, that is, S1-S2 is calculated. Since N1≈N2, the environmental noise part of the difference-processed signal will be greatly suppressed, while the user voice part is relatively retained. The difference-processed signal is enhanced to improve the clarity of the user's voice. The adaptive filtering algorithm is applied to filter the signal collected by the main microphone according to the environmental noise signal collected by the auxiliary microphone. The adaptive filtering algorithm can adjust the parameters of the filter in real time to suppress the environmental noise to the greatest extent. Based on the statistical characteristics of the noise, the noise is modeled and predicted, so as to separate the noise component from the original signal. The noise-reduced signal is subjected to voice enhancement processing to improve the clarity and intelligibility of the voice signal. Speech enhancement technologies include dynamic range compression and spectrum shaping, which remove residual noise that may be generated during the noise reduction process to further improve speech quality, and output the noise-reduced and post-processed signal to subsequent processing modules, such as speech recognition modules or audio playback modules;

[0052] Feature extraction: extract information that can represent speech features from the preprocessed speech signal. The extracted speech feature information includes spectrum and fundamental frequency.

[0053] Pattern matching: Matching the extracted speech features with the pre-stored speech model to identify what the user said;

[0054] Command execution: Execute corresponding lighting control commands according to the recognized content.

[0055] Dual MIC noise reduction is based on two microphone arrays and advanced noise reduction algorithms to reduce or eliminate surrounding noise. One of the main microphones is close to the speaker and is used to collect a mixed signal containing user voice and environmental noise. The other secondary microphone is far away from the speaker and is used to collect environmental noise. By comparing and processing the signals collected by the two microphones with algorithms, the user voice can be extracted and the environmental noise can be suppressed.

[0056] The noise reduction elimination algorithm of dual MIC noise reduction adopts an adaptive filtering algorithm. The adaptive filtering algorithm includes three modules: filtering structure, performance criterion and adaptive algorithm. The filtering structure determines the signal processing method, the performance criterion is used to evaluate the filtering effect, and the adaptive algorithm adjusts the filter parameters according to the performance criterion.

[0057] The data format of the RGB light strip is ARGB, which means addressable RGB. It has a built-in control chip that controls each LED lamp bead individually. The RGB light strip can achieve more complex lighting effects through programming.

[0058] Win11 D lighting is a native RGB lighting management tool developed by Microsoft for Windows 11 system, including:

[0059] API call: Control RGB devices by calling system API. API allows applications to communicate with underlying hardware to achieve precise control of lighting effects.

[0060] HID LampArray standard: supports RGB devices that comply with the HID LampArray standard. HID is used to define the communication protocol between computers and external devices. LampArray is a subset of the HID standard and is specifically used to control lighting devices.

[0061] System settings integration: The overall functions are integrated into the system settings of Windows 11, and users can directly access and control RGB lighting effects through the system settings application.

[0062] Embodiment 2: Supports user voice to autonomously switch between D Lighting, Aura Sync and Local modes. Both D Lighting and Aura Sync modes have master control detection function. D Linghting determines whether to enter D Lighting mode by detecting whether a USB device exists. Aura Sync mode captures signals through the IO port of the main control module. When the Aura Sync signal is captured, it enters Aura Sync mode. If neither of them is available, it enters Local mode.

[0063] It supports separate control of multiple channels. Each master control module IO can output independent signals. It adopts dual-core working mode to synchronously process the original data of the RGB light strip and send the data. Core0 processes the data of each RGB light strip into the data sent by Core1, and Core1 writes the RGB data into the GPIO register to achieve low-latency transmission. According to verification, the master control module can support separate control of up to 26 channels, which can achieve more complex and diverse lighting effects.

[0064] Example 3: In this product, the noise reduction and cancellation algorithm adopts the adaptive filtering algorithm. The adaptive filtering algorithm is an advanced signal processing technology. It can adaptively adjust its own parameters through automatic iteration when the prior knowledge of signal characteristics is incomplete or the signal statistical characteristics change, so as to meet the requirements of a certain criterion, such as the least mean square error (LMS) criterion, so as to achieve optimal filtering. The adaptive filtering system generally includes three modules: filtering structure, performance criterion, and adaptive algorithm. The filtering structure determines the signal processing method, the performance criterion is used to evaluate the filtering effect, and the adaptive algorithm adjusts the filter parameters according to the performance criterion. The least mean square error (LMS) is based on the Wiener filtering theory and adopts an algorithm for estimating the gradient vector using instantaneous values, and updates the weight coefficients of the adaptive filter by minimizing the energy of the error signal.

[0065] Design an Nth-order filter with its parameter being w(n), then the filter output is

[0066]

[0067] The desired output is d(n), then the error signal can be defined as:

[0068] e(n) = d(n) - y(n) = d(n) - w T (n)x(n)

[0069] Our goal is to minimize the error e(n). Adopting the least mean square error criterion, minimize the objective function: J(w)

[0070] J(w) = E{|e(n)| 2} = E{|d(n) - w T (n)x(n)| 2}

[0071] Calculate the derivative of the objective function J(w) with respect to w, and set the derivative to 0:

[0072]

[0073] Then the update formula for the filter coefficients can be written as:

[0074]

[0075] In the above formula, μ is the step size factor. The larger the value of μ, the faster the algorithm converges, but the larger the steady-state error; the smaller the value of μ, the slower the algorithm converges, but the smaller the steady-state error. To ensure the steady-state convergence of the algorithm, μ should be in the following range: 0 < u < 1 / λmax, where λmax is the maximum eigenvalue of the autocorrelation matrix of the input signal.

[0076] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Computer case lighting control based on voice recognition, including main control module, dual MIC noise reduction, PC host, RGB light strip and expansion module, characterized by: The main control module is the core part of the system, responsible for coordinating and controlling the operation of the entire speech recognition and lighting control system; The dual MIC noise reduction is a key technical point to improve speech recognition. Dual MIC noise reduction is the most common noise reduction technology used on a large scale. It collects environmental noise through the cooperation of two microphones and suppresses background noise with advanced noise reduction algorithms. The PC host is linked with the software on the PC side, and the main control module communicates with the PC host through the USB HID protocol and Win11D Lighting, and uses ASUS's Aura Sync for lighting effect control; The RGB light strip is installed in the computer case and is a colorful lighting device; The expansion module includes Bluetooth and WIFI interfaces, and both the Bluetooth and WIFI interfaces are integrated on the main control module.

2. The computer case lighting control based on voice recognition according to claim 1 is characterized in that: The chip of the main control module has two Cortex-M3 cores, and the two cores process in parallel. Core0 first performs a series of necessary initializations, and then creates an RTOS general task, and then creates three tasks: USB Task, RGB Task, and VR Task in the general task. The main task of USB Task is the subsequent firmware online upgrade function and connecting to Win11 D lighting. The main task of RGB Task is RGB mode selection and sending instructions to Core1. If there is no voice command to select, it will be selected according to the priority of DLighting>Aura Sync>Local. The main task of VR Task is to recognize the user's voice command; Core1 also first performs a series of necessary initializations, and then waits for Core0 instructions. If an instruction is received, the corresponding program will be executed, otherwise it will keep waiting.

3. The computer case lighting control based on voice recognition according to claim 1 is characterized in that: The dual MIC noise reduction is used in conjunction with voice recognition, where voice recognition uses an MCU with an integrated audio codec module, the I2C bus is used to transmit control signals, and the I2S bus is used to transmit digital audio signals, converting user voice into machine-understandable text and instructions. In the computer chassis lighting control system, voice recognition allows users to control the switch, brightness, and color of RGB lights through voice commands.

4. The computer case lighting control based on voice recognition according to claim 1 is characterized in that: The speech recognition comprises: Sound collection: collect user's voice signals through microphone; Preprocessing: preprocess the collected speech signals, including removing noise and enhancing signals; Feature extraction: extract information that can represent speech features from the preprocessed speech signal. The extracted speech feature information includes spectrum and fundamental frequency. Pattern matching: Matching the extracted speech features with the pre-stored speech model to identify what the user said; Command execution: Execute corresponding lighting control commands according to the recognized content.

5. The computer case lighting control based on voice recognition according to claim 3 is characterized in that: The dual MIC noise reduction is based on two microphone arrays and advanced noise reduction algorithms to reduce or eliminate ambient noise. One main microphone is close to the speaker and is used to collect a mixed signal containing user voice and ambient noise. The other secondary microphone is far away from the speaker and is used to collect ambient noise. By comparing and processing the signals collected by the two microphones with algorithms, the user voice can be extracted and the ambient noise can be suppressed.

6. The computer case lighting control based on voice recognition according to claim 5 is characterized by: The dual MIC noise reduction algorithm adopts an adaptive filtering algorithm, which includes three modules: filtering structure, performance criterion and adaptive algorithm. The filtering structure determines the signal processing method, the performance criterion is used to evaluate the filtering effect, and the adaptive algorithm adjusts the filter parameters according to the performance criterion.

7. The computer case lighting control based on voice recognition according to claim 1 is characterized by: The data format of the RGB light strip is ARGB, which means addressable RGB. It has a built-in control chip that controls each LED lamp bead individually. The RGB light strip can achieve more complex lighting effects through programming.

8. The computer case lighting control based on voice recognition according to claim 2 is characterized by: Win11 Dlighting is a native RGB lighting management tool developed by Microsoft for Windows 11 system, which includes: API call: Control RGB devices by calling system API. API allows applications to communicate with underlying hardware to achieve precise control of lighting effects. HID LampArray standard: supports RGB devices that comply with the HID LampArray standard. HID is used to define the communication protocol between computers and external devices. LampArray is a subset of the HID standard and is specifically used to control lighting devices. System settings integration: The overall functions are integrated into the system settings of Windows 11, and users can directly access and control RGB lighting effects through the system settings application.

Images