Airborne intelligent voice call processing system based on working mode redundancy design

Abstract

The embodiment of the invention relates to the technical field of airborne voice communication, in particular to an airborne intelligent voice communication processing system based on a working mode redundancy design, which comprises an input module provided with four microphone inputs, an ADC (Analog to Digital Converter) conversion module, a signal processing module, a control module, a DAC (Digital to Analog Converter) conversion module and an output module provided with three earphone outputs, communication connection is established between the control module and the upper computer. The method comprises the following steps: determining a current working mode, determining a connected microphone according to the current working mode, receiving an analog audio signal of the connected microphone, converting the analog audio signal into a digital audio signal through an ADC conversion module, determining the signal processing module or an upper computer to carry out sound mixing, noise reduction, squelch and automatic gain processing, converting the digital audio signal through a DAC conversion module, and outputting the digital audio signal. And selecting an output earphone and outputting. According to the system, the reliability, stability, adaptability and communication quality of airborne voice communication are comprehensively improved, and the requirements of high-safety communication in multiple fields such as civil aviation and the like can be met.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of airborne voice call technology, and in particular to an airborne intelligent voice call processing system based on a redundant working mode design. Background Art

[0002] Inflight voice communication is a core communication method for ensuring aircraft flight safety and mission execution. It is primarily used to transmit commands between cockpit crew members, exchange information between pilots and ground control systems, and, in special scenarios, facilitate collaborative communication between the cockpit and passenger cabin. Its core functions are achieved through audio acquisition, signal processing, data transmission, and audio output. Establishing a stable, clear, and real-time voice communication link is directly related to decision-making efficiency and emergency response capabilities during flight. In the civil aviation sector, the reliability, anti-interference capability, and adaptability of inflight voice communication systems are listed as key performance indicators. Maintaining effective, high-quality communications is particularly important in emergencies such as extreme weather, equipment failure, and malicious threats.

[0003] However, the current airborne voice communication system has obvious deficiencies in stability and functional redundancy design under complex working conditions, and mainly has the following shortcomings.

[0004] First, there is a lack of multi-dimensional redundancy mechanisms. Traditional airborne voice communication systems mostly use a single working mode, which can easily lead to communication link interruption when the core processing module fails.

[0005] Second, the input and output configurations lack flexibility. Traditional onboard voice communication systems use fixed selection logic for microphone input and headphone output channels, making it difficult to dynamically adjust according to actual scenarios. This makes it impossible to simultaneously activate multiple microphones to capture multiple voices or distribute information through multiple headphones as needed. Third, signal processing has limited adaptability. Traditional onboard voice communication systems mostly only have mixing, noise reduction, and gain processing, which can easily lead to problems such as voice signal distortion, noise suppression failure, and loss of detailed information. This results in low call clarity in complex environments. Fourth, data transmission reliability is a weakness. Traditional onboard voice communication systems rely on a single protocol (such as a serial port) to communicate with the host computer and lack a two-way confirmation mechanism. When data transmission is lost or delayed, rapid verification and retransmission are impossible, which can easily lead to command misinterpretation. Furthermore, in scenarios where master-slave devices work together, if the interaction logic between the slave device and the master system is not well designed, signal transmission conflicts or processing delays may occur, reducing the real-time nature of communication. The above problems make it difficult for traditional airborne voice communication systems to meet the application requirements of high reliability and high adaptability when dealing with multiple working conditions switching, core component failures, and complex electromagnetic environments. It is urgent to improve the fault tolerance and scenario adaptability of the airborne voice communication system through multi-mode redundant design and intelligent control logic. Summary of the Invention In view of this, the embodiments of the present application propose an airborne intelligent voice call processing system based on working mode redundant design. Through hardware redundant configuration based on working mode, dynamic mode switching, signal layered noise reduction processing, and collaborative mechanism optimization, the reliability, stability, adaptability and communication quality of airborne voice calls are comprehensively improved, which can meet the high-security communication needs of multiple fields such as civil aviation, and provide a scalable modular solution for the upgrade of airborne voice communication systems.

[0006] In order to achieve the above-mentioned purpose, an embodiment of the present application proposes an airborne intelligent voice call processing system based on a working mode redundancy design, the system comprising: an input module provided with four-way microphone input, an ADC conversion module, a signal processing module, a control module, a DAC conversion module and an output module provided with three-way headphone output, the four-way microphones are respectively a first microphone, a second microphone, a third microphone and a fourth microphone, the three-way headphone are respectively a first headphone, a second headphone and a third headphone, a communication connection is established between the control module and the host computer; the control module confirms the current working mode, the current working mode is normal mode, emergency mode or follower mode, the host computer fails in the emergency mode, and the signal processing module fails in the follower mode; if the current working mode is normal mode, the control module performs input selection in the first microphone, the second microphone and the third microphone, receives the analog audio signal of the connected microphone, converts it into a digital audio signal by the ADC conversion module, and inputs it into the signal processing module for mixing, noise reduction, squelch and automatic gain processing, and the control module The module transmits the processed audio signal to the host computer through the SPI protocol for confirmation, and converts the audio signal received from the host computer through the SPI protocol through the DAC conversion module and outputs it through the first earphone; if the current working mode is the emergency mode, the analog audio signals of the first microphone, the second microphone and the third microphone are received at the same time, and after being converted into digital audio signals by the ADC conversion module, all are input into the signal processing module for mixing, noise reduction, squelch and automatic gain processing, and the processed audio signal is converted by the DAC conversion module and output through the second earphone; if the current working mode is the follower mode, the analog audio signal of the fourth microphone is received, and after being converted into a digital audio signal by the ADC conversion module, the control module transmits the digital audio signal to the host computer through the SPI protocol, and the host computer sends it to the backup intelligent voice call processing system for mixing, noise reduction, squelch and automatic gain processing, and the processed audio signal is returned to the control module through the SPI protocol, and then converted by the DAC conversion module and output through the third earphone.

[0007] In order to achieve the above-mentioned purpose, the embodiment of the present application also proposes an onboard intelligent voice call processing method based on working mode redundancy design, the method comprising: confirming the current working mode, the current working mode is normal mode, emergency mode or follower mode, the host computer fails in emergency mode, and the onboard signal processing module fails in follower mode; if the current working mode is normal mode, input selection is performed in the first microphone, the second microphone and the third microphone, the analog audio signal of the connected microphone is received, and after being converted into a digital audio signal by ADC, the onboard signal processing module performs mixing, noise reduction, squelch and automatic gain processing, transmits the processed audio signal to the host computer via SPI protocol for confirmation, and converts the audio signal received from the host computer via SPI protocol into digital audio signal by DAC. After that, it is output through the first earphone; if the current working mode is the emergency mode, the analog audio signals of the first microphone, the second microphone and the third microphone are received at the same time, and after being converted into digital audio signals by ADC, all are input into the onboard signal processing module for mixing, noise reduction, squelch and automatic gain processing, and the processed audio signal is converted by DAC and output through the second earphone; if the current working mode is the follower mode, the analog audio signal of the fourth microphone is received, and after being converted into a digital audio signal by ADC, the digital audio signal is transmitted to the host computer through the SPI protocol, and the host computer sends it to the backup intelligent voice call processing system for mixing, noise reduction, squelch and automatic gain processing, and the processed audio signal is transmitted back through the SPI protocol, and then converted by DAC and output through the third earphone.

[0008] In order to achieve the above-mentioned purpose, an embodiment of the present application also proposes an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned onboard intelligent voice call processing method based on working mode redundancy design.

[0009] In order to achieve the above-mentioned purpose, an embodiment of the present application also proposes a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the above-mentioned airborne intelligent voice call processing method based on working mode redundancy design.

[0010] The airborne intelligent voice call processing system proposed in this application, which is based on a redundant working mode design, has the following advantages compared with traditional airborne voice call systems.

[0011] First, a multi-dimensional redundant architecture was built, which significantly improved the system's fault tolerance.

[0012] This application achieves self-healing of the communication link in the event of a core component failure through a two-layer design of "hardware channel redundancy" and "working mode redundancy." At the hardware level, the independent channel configuration of four microphone inputs and three headphone outputs breaks the traditional fixed mapping relationship, avoiding input interruption caused by a single channel failure. The ADC conversion module and the DAC conversion module serve as common signal conversion modules, and can adapt to the signal flow in different modes through the logical scheduling of the control module. At the operating mode level, the dynamic switching mechanism between the three modes creates complementary redundancy. Normal mode relies on the coordinated operation of the control module, signal processing module, and host computer, ensuring data transmission accuracy through bidirectional verification of the SPI protocol. Emergency mode, activated if the host computer fails, directly feeds the full-channel signal from the first to the third microphone into the signal processing module. After processing, it is output through the second headphone, thus avoiding heavy dependence on the host computer. Follower mode, initiated if the signal processing module fails, transmits the signal collected by the fourth microphone directly to the host computer through the control module for processing, and then outputs through the third headphone, replacing the signal processing module's functionality. This precise matching mechanism of operating modes enables the system to maintain communication functionality even if any single core component fails, improving fault tolerance by at least three times. Second, dynamically adapt to communication requirements in multiple scenarios to enhance the adaptability of system working conditions.

[0013] This application achieves seamless switching from routine flight to emergency scenarios through modular design, meeting the communication characteristics requirements of different mission stages.

[0014] In normal mode, the input gating function flexibly selects any channel from the first to the third microphone to connect based on crew operational requirements. This control module's logic reduces invalid signal input and reduces processing load. Furthermore, the SPI protocol's bidirectional interaction mechanism ensures that audio signals are verified by the host computer. This allows for secondary verification of commands in high-security scenarios such as civil aviation control, reducing the risk of miscommunication. In response to extreme scenarios where the host computer fails, the emergency mode adopts a "full input" strategy. The signals from the first microphone to the third microphone are all mixed and processed and then output through the second earphone. This ensures that the crew can receive voice commands from multiple parties at the same time in emergency situations (such as engine failure and extreme weather), shortening the decision-making response time.

[0015] The follower mode is suitable for multi-machine collaboration or task expansion scenarios. The fourth microphone serves as a dedicated input and is synchronized with the voice through centralized processing by the host computer.

[0016] The coverage of the three modes basically covers the entire scenario of aircraft from normal operation to emergency response, and the scenario adaptability is improved by more than 60% compared with traditional systems. Third, optimize the signal processing link to improve audio communication quality.

[0017] This application maximizes the signal processing efficiency under different working conditions through layered processing and patterned scheduling. In normal mode, the mixing, noise reduction, squelch and automatic gain processing of the signal processing module and the secondary confirmation of the host computer form a "double optimization" to ensure the clarity of the output audio. The full-channel mixing processing in emergency mode is based on the principle of "real-time priority". Through the independent calculation of the signal processing module, the mixing delay of the multi-microphone signal is controlled within 50ms to meet the needs of instant transmission of emergency instructions. The follower mode transfers the signal processing task to the host computer, and uses the stronger computing power of the host computer to achieve voice optimization in complex scenarios, which can improve the communication consistency within the formation. In addition, this application further ensures the sound quality through physical isolation of the headphone output. The first to third headphones correspond to output links of different modes, respectively, avoiding crosstalk between audio signals from different sources and effectively solving the problem of sudden silence or noise interference. Fourth, strengthen the system coordination mechanism and improve data transmission and control efficiency.

[0018] The SPI protocol communication link between the control module and the host computer increases the transmission rate by more than three times compared to traditional serial communication. A bidirectional verification mechanism enables real-time detection and retransmission of packet loss, ensuring the transmission integrity of each frame of audio data. Furthermore, the control module, as the core logic unit for mode switching, rapidly completes mode switching based on pre-set judgment conditions, eliminating delays caused by manual intervention.

[0019] In terms of human-machine collaboration, the multi-mode design aligns with the crew's operating habits. The gating logic in normal mode simplifies routine operations. The full-channel output in emergency mode meets the information acquisition needs in emergency situations. The dedicated channel in follower mode facilitates device access during mission expansion. This compatible design significantly improves the crew's voice communication efficiency and reduces the risk of misoperation. To summarize, this application comprehensively improves the reliability, adaptability, and communication quality of airborne voice calls through hardware redundant configuration, dynamic mode switching, signal layered processing, and collaborative mechanism optimization, and can meet the high-security communication needs of multiple fields such as civil aviation. Its technical solution is significantly innovative in redundant design concepts and multi-scenario adaptation logic, and provides a scalable modular solution for the upgrade of airborne voice communication systems.

[0020] Optionally, SPI protocol communication is established between the control module and the ADC conversion module and the DAC conversion module, SPI protocol communication and UART serial port communication are established between the control module and the host computer, SPI protocol communication and I2S communication are established between the control module and the signal processing module, and I2S communication is established between the signal processing module and the ADC conversion module and the DAC conversion module.

[0021] Optionally, after confirming the current working mode, the control module generates a control signal based on the current working mode and sends the control signal to the signal processing module and the host computer; wherein, if the current working mode is the normal mode, the control module generates a normal control signal; if the current working mode is the emergency mode, the control module generates an emergency control signal; if the current working mode is the follower mode, the control module generates a follower control signal.

[0022] Optionally, the signal processing module is specifically composed of a mixing unit, a noise reduction unit, a squelch unit and an automatic gain unit; the mixing unit is used to perform framing and FFT transformation on the digital audio signal output by the ADC conversion module, determine the main spectrum in each complex spectrum, optimize the phase of each complex spectrum based on the main spectrum, and calculate the spectral entropy of each complex spectrum at the same time, assign dynamic spectral entropy weights to each complex spectrum based on the spectral entropy, and then combine the auditory masking compensation factor to perform spectrum synthesis on each complex spectrum after phase optimization, and obtain the mixed audio signal after IFFT transformation and overlap elimination; the noise reduction unit is used to pre-emphasize, frame and FFT transformation on the mixed audio signal output by the mixing unit, and perform phase synthesis based on the amplitude spectrum and phase spectrum of each frame signal. Feature extraction is performed to obtain the multimodal features of each frame signal, and the multimodal features of each frame signal are input into the pre-trained noise reduction model for noise reduction processing to obtain the audio signal after noise reduction processing; the noise reduction unit is used to extract features of the audio signal after noise reduction processing output by the noise reduction unit to obtain energy features including subband energy and differential energy, and through dynamic subband GMM modeling, the noise reduction decision is optimized based on the energy features by Bayesian decision to obtain the audio signal after noise reduction processing; the automatic gain unit is used to perform long-term static gain, medium-term dynamic compression and short-term transient protection on the audio signal after noise reduction processing output by the noise reduction unit to realize automatic gain processing, obtain the audio signal after automatic gain, and transmit it to the control module or DAC conversion module.

[0023] Optionally, a BIT self-test unit is also provided in the signal processing module; the BIT self-test unit is used to instruct the MCU of the control module to detect whether the input and output of each module and unit of the airborne intelligent voice call processing system are normal, detect whether the ADC conversion module and the DAC conversion module are working normally, and detect whether the system power supply is normal by sending a sinusoidal signal. After generating self-test information, the self-test information is uploaded to the host computer through UART serial port communication.

[0024] Optionally, the control module is also used to determine whether the audio signal after noise reduction processing contains human voice through a sound activation detection algorithm. If it does not contain human voice, it is necessary to start the squelch unit to perform squelch processing; if it contains human voice, the automatic gain unit directly performs automatic gain processing.

[0025] Optionally, the system also includes a pre-output filtering module; the pre-output filtering module is used to perform pre-output filtering on the noise reduction analog audio signal output by the DAC conversion module to obtain a filtered noise reduction analog audio signal, and based on the current working mode, select to output through the first earphone, the second earphone or the third earphone; the pre-output filtering module adopts a multi-order high-pass filtering and low-pass filtering cascade architecture, including two groups of high-pass filters and two groups of low-pass filters, the two groups of high-pass filters are respectively a 300Hz high-pass filter and a 290Hz high-pass filter, and the two groups of low-pass filters are respectively a 4KHz low-pass filter and a 6.48KHz low-pass filter. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related technologies, the following is a brief introduction to the drawings required for use in the embodiments of the present application or the description of the related technologies. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0027] Figure 1 This is a structural diagram of an onboard intelligent voice call processing system based on working mode redundancy design provided in one embodiment of the present application; Figure 2 This is a signal flow diagram in an onboard intelligent voice call processing system based on a working mode redundancy design provided in one embodiment of the present application; Figure 3 is a structural diagram of a pre-output filtering module provided in one embodiment of the present application; Figure 4 is a schematic diagram of system initialization provided in one embodiment of the present application; Figure 5 is a flowchart of an onboard intelligent voice call processing method based on working mode redundancy design provided in another embodiment of the present application; Figure 6 is a comparative schematic diagram of a simulation experiment provided in another embodiment of the present application; Figure 7 It is a structural diagram of an electronic device provided in another embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, each embodiment of the present application will be described in detail below with reference to the accompanying drawings. However, it will be understood by those skilled in the art that in each embodiment of the present application, many technical details are proposed to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present application. The various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0029] An embodiment of the present application proposes an airborne intelligent voice call processing system based on a redundant working mode design. The implementation details of the airborne intelligent voice call processing system based on a redundant working mode design proposed in this embodiment are described in detail below. The following content is only the implementation details provided for easy understanding and is not necessary for the implementation of this solution.

[0030] The specific structure of the onboard intelligent voice call processing system based on the working mode redundancy design proposed in this embodiment can be as follows: Figure 1 As shown, it includes: an input module 10 with four microphone inputs, an ADC conversion module 20, a signal processing module 30, a control module 40, a DAC conversion module 50 and an output module 60 with three headphone outputs, the four microphones are respectively a first microphone 11, a second microphone 12, a third microphone 13 and a fourth microphone 14, the three headphones are respectively a first headphone 61, a second headphone 62 and a third headphone 63, and a communication connection is established between the control module 40 and the host computer 70.

[0031] The following is a detailed introduction to the various components and signal flow of an onboard intelligent voice call processing system based on a working mode redundancy design proposed in this embodiment. The signal flow of an onboard intelligent voice call processing system based on a working mode redundancy design proposed in this embodiment can be as follows: Figure 2 shown.

[0032] The control module 40 is used to confirm the current working mode, which is one of the normal mode, the emergency mode and the follower mode. In the emergency mode, the host computer 70 fails, and in the follower mode, the signal processing module 30 fails.

[0033] If the current working mode is normal mode, the control module 40 selects the input in the first microphone 11, the second microphone 12 and the third microphone 13, receives the analog audio signal of the connected microphone, converts it into a digital audio signal through the ADC conversion module 20, and inputs it into the signal processing module 30 for mixing, noise reduction, squelch and automatic gain processing. The control module 40 transmits the processed audio signal to the host computer 70 for confirmation through the SPI protocol, and converts the audio signal received from the host computer 70 through the SPI protocol through the DAC conversion module 50 and outputs it through the first earphone 61.

[0034] If the current working mode is the emergency mode, the analog audio signals of the first microphone 11, the second microphone 12 and the third microphone 13 are received at the same time, converted into digital audio signals by the ADC conversion module 20, and all are input into the signal processing module 30 for mixing, noise reduction, squelch and automatic gain processing. The processed audio signals are converted by the DAC conversion module 50 and output through the second earphone 62.

[0035] If the current working mode is the follower mode, the analog audio signal of the fourth microphone 14 is received, and after being converted into a digital audio signal by the ADC conversion module 20, the control module 40 transmits the digital audio signal to the host computer 70 through the SPI protocol. The host computer 70 performs mixing, noise reduction, squelch and automatic gain processing, and returns the processed audio signal to the control module 40 through the SPI protocol, and then after conversion by the DAC conversion module 50, it is output through the third earphone 63.

[0036] like Figure 2 As shown, SPI protocol communication is established between the control module 40 and the ADC conversion module 20 and the DAC conversion module 50. SPI protocol communication and UART serial port communication are established between the control module 40 and the host computer 70. SPI protocol communication and I2S communication are established between the control module 40 and the signal processing module 30. I2S communication is established between the signal processing module 30 and the ADC conversion module 20 and the DAC conversion module 50.

[0037] like Figure 2 As shown, after confirming the current working mode, the control module 40 needs to generate a control signal based on the current working mode and send the control signal to the signal processing module 30 and the host computer 70. Specifically, if the current working mode is the normal mode (mode 1), the control module 40 generates a normal control signal (mode 1 key signal); if the current working mode is the emergency mode (mode 2), the control module 40 generates an emergency control signal (mode 2 key signal); if the current working mode is the follower mode (mode 3), the control module 40 generates a follower control signal (mode 3 key signal).

[0038] The onboard intelligent voice call processing system based on the working mode redundancy design proposed in this embodiment further includes a pre-output filtering module, which is used to perform pre-output filtering on the noise reduction analog audio signal output by the DAC conversion module 50 to obtain the filtered noise reduction analog audio signal and select the first earphone 61, the second earphone 62 or the third earphone 63 for output based on the current working mode. The pre-output filtering module adopts a multi-order high-pass filter and low-pass filter cascade architecture, such as Figure 3 As shown, the filter comprises two sets of high-pass filters (300Hz and 290Hz), and two sets of low-pass filters (4kHz and 6.48kHz). By precisely setting the cutoff frequencies of filter circuits of varying order, a highly targeted audio signal filtering channel can be constructed. This effectively isolates the target audio frequency band (100Hz to 4.5kHz) while simultaneously filtering out non-target noise, such as low-frequency environmental noise (such as equipment hum and low-frequency interference from ambient vibration) and high-frequency clutter (such as high-frequency noise from electromagnetic radiation), ensuring audio signal purity. The AIP4558S8 operational amplifier (op amp) is used for the filter configuration. Its low noise and high gain-bandwidth product make it ideal for audio signal amplification and filtering. It balances signal transmission efficiency with amplitude stability, preventing signal attenuation and distortion, and ensuring high audio signal quality after filtering.

[0039] like Figure 1 As shown, the signal processing module 30 is specifically composed of a mixing unit 31 , a noise reduction unit 32 , a squelch unit 33 and an automatic gain unit 34 .

[0040] The mixing unit 31 is used to perform framing and FFT transformation on the digital audio signal output by the ADC conversion module 20, determine the main spectrum in each complex spectrum, optimize the phase of each complex spectrum based on the main spectrum, and calculate the spectral entropy of each complex spectrum. Based on the spectral entropy, a dynamic spectral entropy weight is assigned to each complex spectrum. Then, combined with the auditory masking compensation factor, the complex spectrum after phase optimization is spectrally synthesized. Finally, after IFFT transformation and overlap elimination, the audio signal after mixing is obtained.

[0041] The noise reduction unit 32 is used to pre-emphasize, frame and perform FFT transformation on the audio signal after mixing processing output by the mixing unit 31, perform feature extraction based on the amplitude spectrum and phase spectrum of each frame signal, obtain the multimodal features of each frame signal, input the multimodal features of each frame signal into the pre-trained noise reduction model for noise reduction processing, and obtain the audio signal after noise reduction processing.

[0042] The squelch unit 33 is used to extract energy features from the noise-reduced audio signal output by the noise reduction unit 32, obtaining energy features including subband energy and differential energy. Subsequently, a Bayesian decision optimization squelch decision is performed based on the energy features using dynamic subband GMM modeling, thereby obtaining a squelched audio signal. It should be noted that whether the squelch unit 33 is enabled is determined by the control module 40. The control module 40 can use a sound activation detection algorithm to determine whether the noise-reduced audio signal contains human voices. If not, the squelch unit 33 needs to be enabled for squelch processing. If human voices are present, the automatic gain unit 34 directly performs automatic gain processing.

[0043] The automatic gain unit 34 is used to perform long-term static gain, medium-term dynamic compression and short-term transient protection on the audio signal after noise reduction processing output by the noise reduction unit 33 to achieve automatic gain processing, obtain the audio signal after automatic gain, and transmit it to the control module or DAC conversion module 50.

[0044] The working principles of the audio mixing unit 31 , the noise reduction unit 32 , the squelch unit 33 and the automatic gain unit 34 are described in detail below.

[0045] For the audio mixing unit 31, the digital audio signal obtained after ADC conversion is road, is an integer greater than 1, The digital audio signal is recorded as , .

[0046] for The mixing unit 31 needs to perform frame processing according to the preset frame length and overlap rate (1024 frames, Hanning window, 50% overlap rate), and then perform FFT transformation on each frame signal to obtain The complex spectrum, The corresponding complex spectrum is recorded as , Indicates frequency.

[0047] Next, The complex spectrum with the largest energy among the complex spectrums is taken as the main spectrum , respectively calculated The complex spectrum and The phase offset between them is calculated based on their respective phase offsets. The complex spectrum of the two paths is mixed non-uniformly in phase to align the phases and obtain the complex spectrum after phase optimization.

[0048] The first The complex spectrum after phase optimization is recorded as , It is expressed by the formula: ; ; ; in, express The phase, express The phase, express and The phase shift between Indicates the center frequency of the sensitive frequency band (1KHz to 4KHz). Indicates the maximum frequency.

[0049] While performing phase optimization, it is also necessary to calculate the dynamic spectral entropy weight and auditory masking compensation factor. The spectral entropy is , , for Any frequency point in Frequency The critical frequency band centered at It is the normalized energy probability. The higher the spectral entropy, the more complex the frequency band information is and the more details need to be retained. The lower the entropy value, the more concentrated the energy is (such as pure tone).

[0050] Then based on ,calculate Corresponding dynamic spectral entropy weight : ; in, is the preset spectral entropy threshold (generally set to 0.8), For a preset slope factor (generally set to 5.0), the dynamic spectral entropy weight allocated to the high spectral entropy region approaches 1, and the dynamic spectral entropy weight allocated to the low spectral entropy region approaches 0.

[0051] While calculating the dynamic spectral entropy weights, the MPEG psychoacoustic model is used to calculate The masking threshold of the complex spectrum is The maximum value of the masking threshold of the complex spectrum is used as the global masking threshold. The masking threshold is denoted as , the global masking threshold is recorded as , .

[0052] Then, based on the following formula, calculate Compensation factor corresponding to the complex spectrum: ; in, express The corresponding compensation factor is improved after being compensated by the auditory masking compensation factor.

[0053] At this point, the dynamic spectral entropy weights, compensation factors, and phase-optimized complex spectra are all ready. The mixing unit 31 performs spectrum synthesis based on the dynamic spectral entropy weights, compensation factors, and phase-optimized complex spectra using the following formula to obtain the final spectrum synthesis result. ; in, Represents the final spectrum synthesis result.

[0054] Finally, the final spectrum synthesis result is subjected to IFFT transformation and window overlap elimination operations in sequence to obtain the mixed audio signal. .

[0055] The mixing processing proposed in this embodiment assigns a larger dynamic spectral entropy weight to the high spectral entropy area, thereby achieving detail preservation. For masked weak signals, it is compensated by the auditory masking compensation factor, effectively avoiding the occurrence of distortion problems. The phase optimization design avoids the problem of monophony and has good compatibility.

[0056] When performing noise reduction processing, the noise reduction unit 32 first performs pre-processing on the mixed audio signal, including pre-emphasis (implemented by a first-order filter), framing (frame length 25ms, frame shift 10ms, Hamming window) and FFT transformation, and extracts the amplitude spectrum. and phase spectrum , then based on and Multimodal feature extraction is performed to obtain 34-dimensional multimodal features. The 34-dimensional multimodal features include 16-dimensional MFCC, 8-dimensional first-order difference ΔMFCC, 8-dimensional second-order difference ΔΔMFCC, 1-dimensional logarithmic energy and 1-dimensional phase value (Δ represents the first-order difference, ΔΔ represents the second-order difference).

[0057] Next, the multimodal features of each frame signal are input into the denoising model consisting of CNN spatial feature branch, LSTM temporal feature branch, fusion layer and fully connected layer for denoising processing.

[0058] The denoising model captures the spectrogram spatial features in the multimodal features through the CNN spatial feature branch, models the temporal dependency features in the multimodal features through the LSTM temporal feature branch, and then performs feature splicing and fusion of the spectrogram spatial features and temporal dependency features through the fusion layer to obtain the fused features. Finally, the fully connected layer outputs the denoised audio signal based on the fused features. The denoised audio signal is recorded as .

[0059] If squelch processing is determined to be necessary, the squelch unit 33 performs frame processing (20ms frame length, 10ms frame shift) and feature extraction on the noise-reduced audio signal, obtaining a 48-dimensional energy feature. The 48-dimensional energy feature includes a 24-dimensional Mel subband energy feature and a 24-dimensional differential energy feature. The differential energy feature is the difference between the subband energy feature of the current frame and the subband energy feature of the previous frame.

[0060] After obtaining the 48-dimensional energy features, the 48-dimensional energy features are divided into 6 groups according to the frequency band. Each group of energy features is independently modeled using a Gaussian mixture model (GMM) to obtain speech GMM and noise GMM. Each GMM contains four Gaussian components (this choice can balance computational complexity and accuracy).

[0061] The first The speech GMM corresponding to the group energy feature is recorded as , will The noise GMM corresponding to the group energy feature is recorded as , .

[0062] The noise GMM is trained using the data from the silence period (the first 0.5s), and the speech GMM is trained based on the pure speech library (TIMIT) to obtain the model parameters of the noise GMM and speech GMM.

[0063] Next, the subband likelihood ratio of each set of energy features is calculated using the following formula: ; in, represents the subband characteristics, Indicates the Subband likelihood ratio of group energy features, represents a Gaussian distribution, 、 、 express For the The model parameters of the Gaussian components (i.e. weights, means, covariances), 、 、 express For the The model parameters of the Gaussian components.

[0064] Then, the following formula is used to update the speech prior probability and noise prior probability of the current frame according to the squelch decision result of the previous frame: ; ; in, Indicates the current frame, Indicates the previous frame, represents the speech prior probability of the current frame, represents the noise prior probability of the current frame, represents the prior probability of speech in the previous frame, is the preset smoothing factor, Indicates the squelch decision result of the previous frame, Indicates that the previous frame is a speech frame, Indicates that the previous frame is a noise frame.

[0065] Then, based on the speech prior probability and noise prior probability of the current frame and the subband likelihood ratio of each set of energy features, the following formula is used to make a squelch decision for the current frame and obtain the squelch decision result for the current frame: ; ; in, Indicates the squelch decision threshold that is dynamically adjusted with the signal-to-noise ratio. Indicates the initial squelch decision threshold, represents the threshold adjustment factor, Indicates the signal-to-noise ratio (given by the host computer through UART serial port communication), Indicates the squelch decision result of the current frame. Indicates that the current frame is a speech frame. Indicates that the current frame is a noise frame.

[0066] Finally, the noise frame is attenuated in the frequency domain (-20dB gain), and a 10ms fade-in and fade-out window is applied at the switching boundary between the speech frame and the noise frame to achieve a smooth transition. Finally, the audio signal after the squelch is output, which effectively avoids the occurrence of "clicking" sounds. The audio signal after the squelch is recorded as , after sampling, it can be recorded as .

[0067] The automatic gain unit 34 needs to perform long-term static gain, medium-term dynamic compression, and short-term transient protection on the audio signal after squelch processing (or the audio signal after noise reduction processing) to achieve automatic gain processing and obtain an audio signal after automatic gain.

[0068] First, a long-term static gain is calculated based on the target level (conversation comfort level, -26 dBFS) and the average energy of the squelched audio signal. The long-term static gain is updated only during noisy segments to avoid semantic distortion.

[0069] Subsequently, a compressor is used to perform mid-time dynamic compression, determine the mid-time dynamic gain, and determine the upper limit of the dynamic gain of the speech segment and the upper limit of the dynamic gain of the noise segment. The upper limit of the dynamic gain of the speech segment is 15dB, and the upper limit of the dynamic gain of the noise segment is 6dB.

[0070] The compressor has an attack time of 20ms to prevent sudden gain changes, a release time of 500ms to achieve natural decay, a compression ratio of 2 to 1, and a compression threshold of -30dB. No compression is performed below -30dB.

[0071] Next, when the instantaneous energy of the audio signal after the squelch process is greater than 4 times the average energy and the zero-crossing rate is greater than 3 times the sampling rate, short-time transient protection is performed to determine short-time transient linear attenuation.

[0072] The total gain is then calculated based on the long-term static gain, medium-term dynamic gain, dynamic gain ceiling, and short-term transient linear attenuation using the following formula: ; ; ; in, represents the long-term static gain, Indicates the target level, Represents the average energy of the audio signal after squelch processing, represents the mid-time dynamic gain, Indicates the upper limit of dynamic gain, Represents short-time transient linear attenuation, Indicates the freeze adjustment time. Indicates the total gain.

[0073] In getting Then, through the following formula, To perform smoothing: ; in, represents the total gain after smoothing, Indicates the sampling point.

[0074] Finally, use And anti-clipping processing mechanism, the audio signal after squelch processing Perform automatic gain processing to obtain the audio signal after automatic gain , It is expressed by the formula: ; ; in, Represents a symbolic function.

[0075] like Figure 1 As shown, a BIT self-test unit 35 is also provided in the signal processing module.

[0076] The BIT self-test unit 35 is used to instruct the MCU of the control module 40 to detect whether the input and output of each module and unit of the onboard intelligent voice call processing system are normal, whether the ADC conversion module 20 and the DAC conversion module 50 are working properly, and whether the system power supply is normal by sending a sinusoidal signal. After generating self-test information, the self-test information is uploaded to the host computer 70 through the UART serial port communication. The process of BIT self-test and initialization can be as follows: Figure 4 shown.

[0077] The onboard intelligent voice call processing system based on working mode redundancy design proposed in this embodiment has the following advantages compared with traditional onboard voice call systems.

[0078] First, a multi-dimensional redundant architecture was built, which significantly improved the system's fault tolerance.

[0079] This embodiment achieves self-healing of the communication link in the event of a core component failure through a dual-layer design of "hardware channel redundancy" and "operating mode redundancy." At the hardware level, the independent channel configuration of four microphone inputs and three headphone outputs breaks the traditional fixed mapping relationship, preventing input interruption caused by a single channel failure. The ADC and DAC conversion modules serve as common signal conversion modules, and the control module's logical scheduling can adapt the signal flow in different modes. At the operating mode level, the dynamic switching mechanism between the three modes creates complementary redundancy. Normal mode relies on the coordinated operation of the control module, signal processing module, and host computer, ensuring data transmission accuracy through bidirectional verification of the SPI protocol. Emergency mode, activated if the host computer fails, directly feeds the full-channel signal from the first to the third microphone into the signal processing module. After processing, it is output through the second headphone, thus avoiding heavy dependence on the host computer. Follower mode, initiated if the signal processing module fails, transmits the signal collected by the fourth microphone directly to the host computer through the control module for processing, and then outputs through the third headphone, replacing the signal processing module's functionality. This precise matching mechanism of operating modes enables the system to maintain communication functionality even if any single core component fails, improving fault tolerance by at least three times. Second, dynamically adapt to communication requirements in multiple scenarios to enhance the adaptability of system working conditions.

[0080] This embodiment achieves seamless switching from routine flight to emergency scenarios through modular design, meeting the communication characteristics requirements of different mission stages.

[0081] In normal mode, the input gating function flexibly selects any channel from the first to the third microphone to connect based on crew operational requirements. This control module's logic reduces invalid signal input and reduces processing load. Furthermore, the SPI protocol's bidirectional interaction mechanism ensures that audio signals are verified by the host computer. This allows for secondary verification of commands in high-security scenarios such as civil aviation control, reducing the risk of miscommunication. In response to extreme scenarios where the host computer fails, the emergency mode adopts a "full input" strategy. The signals from the first microphone to the third microphone are all mixed and processed and then output through the second earphone. This ensures that the crew can receive voice commands from multiple parties at the same time in emergency situations (such as engine failure and extreme weather), shortening the decision-making response time.

[0082] The follower mode is suitable for multi-machine collaboration or task expansion scenarios. The fourth microphone serves as a dedicated input and is synchronized with the voice through centralized processing by the host computer.

[0083] The coverage of the three modes basically covers the entire scenario of aircraft from normal operation to emergency response, and the scenario adaptability is improved by more than 60% compared with traditional systems. Third, optimize the signal processing link to improve audio communication quality.

[0084] This embodiment maximizes the signal processing efficiency under different working conditions through layered processing and patterned scheduling. In normal mode, the mixing, noise reduction, squelch and automatic gain processing of the signal processing module and the secondary confirmation of the host computer form a "double optimization" to ensure the clarity of the output audio. The full-channel mixing processing in emergency mode is based on the principle of "real-time priority". Through the independent calculation of the signal processing module, the mixing delay of the multi-microphone signal is controlled within 50ms to meet the needs of instant transmission of emergency instructions. The follower mode transfers the signal processing task to the host computer, and uses the stronger computing power of the host computer to achieve voice optimization in complex scenarios, which can improve the communication consistency within the formation. In addition, this embodiment further ensures sound quality through physical isolation of the headphone output. The first to third headphones correspond to output links of different modes, respectively, avoiding crosstalk between audio signals from different sources and effectively solving the problem of sudden silence or noise interference. Fourth, strengthen the system coordination mechanism and improve data transmission and control efficiency.

[0085] The SPI protocol communication link between the control module and the host computer increases the transmission rate by more than three times compared to traditional serial communication. A bidirectional verification mechanism enables real-time detection and retransmission of packet loss, ensuring the transmission integrity of each frame of audio data. Furthermore, the control module, as the core logic unit for mode switching, rapidly completes mode switching based on pre-set judgment conditions, eliminating delays caused by manual intervention.

[0086] In terms of human-machine collaboration, the multi-mode design aligns with the crew's operating habits. The gating logic in normal mode simplifies routine operations. The full-channel output in emergency mode meets the information acquisition needs in emergency situations. The dedicated channel in follower mode facilitates device access during mission expansion. This compatible design significantly improves the crew's voice communication efficiency and reduces the risk of misoperation. In summary, this embodiment comprehensively improves the reliability, adaptability, and communication quality of airborne voice calls through hardware redundancy configuration, dynamic mode switching, signal layer processing, and collaborative mechanism optimization. It can meet the high-security communication requirements of multiple fields such as civil aviation. Its technical solution has significant innovations in redundant design concepts and multi-scenario adaptation logic, providing a scalable modular solution for upgrading airborne voice communication systems.

[0087] It is worth mentioning that all modules involved in this embodiment are logical modules. In actual applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, to highlight the innovation of this application, this embodiment does not include units that are not closely related to solving the technical problem proposed by this application. However, this does not mean that other units do not exist in this embodiment.

[0088] Another embodiment of the present application proposes an onboard intelligent voice call processing method based on a redundant working mode design. The following describes the implementation details of the onboard intelligent voice call processing method based on a redundant working mode design proposed in this embodiment. The following content is only provided for ease of understanding and is not required for the implementation of this solution.

[0089] The specific process of the onboard intelligent voice call processing method based on working mode redundancy design proposed in this embodiment can be as follows: Figure 5 As shown, including: Step 81, confirming the current working mode, which is the normal mode, the emergency mode or the follower mode. In the emergency mode, the host computer fails, and in the follower mode, the onboard signal processing module fails.

[0090] Step 82: If the current working mode is normal mode, input selection is performed in the first microphone, the second microphone, and the third microphone. The analog audio signal of the connected microphone is received, converted into a digital audio signal by the ADC, and then mixed, noise reduced, muted, and automatically gained by the onboard signal processing module. The processed audio signal is transmitted to the host computer via the SPI protocol for confirmation. The audio signal received from the host computer via the SPI protocol is converted by the DAC and output through the first earphone.

[0091] Step 83: If the current working mode is emergency mode, the analog audio signals of the first microphone, the second microphone, and the third microphone are received simultaneously. After being converted into digital audio signals by ADC, all of them are input into the onboard signal processing module for mixing, noise reduction, squelch, and automatic gain processing. The processed audio signals are converted by DAC and output through the second earphone.

[0092] Step 84: If the current working mode is the follower mode, the analog audio signal of the fourth microphone is received, converted into a digital audio signal by the ADC, and then transmitted to the host computer through the SPI protocol. The host computer sends the digital audio signal to the backup intelligent voice call processing system for mixing, noise reduction, squelch and automatic gain processing, and the processed audio signal is returned through the SPI protocol, and then converted by the DAC and output through the third earphone.

[0093] The step division of the various methods above is only for clear description. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application; adding insignificant modifications or introducing insignificant designs to the algorithm or process without changing the core design of the algorithm and process are all within the scope of protection of this application.

[0094] It is not difficult to find that this embodiment is a method embodiment corresponding to the above-mentioned system embodiment, and this embodiment can be implemented in conjunction with the above-mentioned system embodiment. The relevant technical details and technical effects mentioned in the above-mentioned system embodiment are still valid in this embodiment, and to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the above-mentioned system embodiment.

[0095] In an implementation example, we conducted a simulation experiment on an onboard intelligent voice call processing system based on a working mode redundancy design proposed in this embodiment, in which the cascade processing effect of mixing, noise reduction, squelch, and automatic gain can be as follows: Figure 6 As shown, the cascade processing architecture designed in this application greatly improves call quality and suppresses strong noise in complex environments.

[0096] Another embodiment of the present application provides an electronic device, the structure of which is as follows: Figure 7 As shown, it includes: at least one processor 91; and a memory 92 communicatively connected to the at least one processor 91; wherein the memory 92 stores instructions that can be executed by the at least one processor 91, and the instructions are executed by the at least one processor 91 to enable the at least one processor 91 to execute an onboard intelligent voice call processing method based on working mode redundancy design as described in the above method embodiment.

[0097] The memory and processor are connected using a bus. The bus can include any number of interconnected buses and bridges, connecting various circuits within one or more processors and the memory. The bus can also connect various other circuits, such as peripherals, voltage regulators, and power management circuits. These are well known in the art and will not be described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, providing a means for communicating with various other devices over a transmission medium.

[0098] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0099] Another embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement an onboard intelligent voice call processing method based on working mode redundancy design as described in the above method embodiment.

[0100] That is, those skilled in the art will understand that all or part of the steps in the above-described method embodiments can be implemented by instructing the relevant hardware through a program. The program is stored in a storage medium and includes a number of instructions for causing a device (which may be a single-chip microcomputer or chip) or a processor to execute all or part of the steps in the method embodiments described herein. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0101] It will be understood by those skilled in the art that the above embodiments are specific embodiments for implementing the present application, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. An onboard intelligent voice call processing system based on working mode redundancy design, characterized in that: The system includes: an input module provided with four microphone inputs, an ADC conversion module, a signal processing module, a control module, a DAC conversion module, and an output module provided with three headphone outputs, wherein the four microphones are respectively a first microphone, a second microphone, a third microphone, and a fourth microphone, and the three headphones are respectively a first headphone, a second headphone, and a third headphone, and a communication connection is established between the control module and the host computer; The control module confirms the current working mode, which can be normal mode, emergency mode or follower mode. In the emergency mode, the host computer fails, and in the follower mode, the signal processing module fails. If the current working mode is normal mode, the control module selects the input in the first microphone, the second microphone and the third microphone, receives the analog audio signal of the connected microphone, converts it into a digital audio signal by the ADC conversion module, and inputs it into the signal processing module for mixing, noise reduction, squelch and automatic gain processing. The control module transmits the processed audio signal to the host computer for confirmation through the SPI protocol, converts the audio signal received from the host computer through the SPI protocol by the DAC conversion module, and outputs it through the first earphone; If the current working mode is emergency mode, the analog audio signals from the first microphone, the second microphone, and the third microphone are received simultaneously, converted into digital audio signals by the ADC conversion module, and all are input into the signal processing module for mixing, noise reduction, squelch, and automatic gain processing. The processed audio signals are converted by the DAC conversion module and output through the second earphone; If the current working mode is follower mode, the analog audio signal of the fourth microphone is received, converted into a digital audio signal by the ADC conversion module, and then the control module transmits the digital audio signal to the host computer through the SPI protocol, and the host computer sends it to the backup intelligent voice call processing system for mixing, noise reduction, squelch and automatic gain processing, and the processed audio signal is returned to the control module through the SPI protocol, and then converted by the DAC conversion module and output through the third earphone.

2. The airborne intelligent voice call processing system based on working mode redundancy design according to claim 1 is characterized in that: SPI protocol communication is established between the control module and the ADC conversion module and DAC conversion module, SPI protocol communication and UART serial port communication are established between the control module and the host computer, SPI protocol communication and I2S communication are established between the control module and the signal processing module, and I2S communication is established between the signal processing module and the ADC conversion module and DAC conversion module.

3. The airborne intelligent voice call processing system based on working mode redundancy design according to claim 1 is characterized in that: After confirming the current working mode, the control module generates a control signal based on the current working mode and sends the control signal to the signal processing module and the host computer; Among them, if the current working mode is normal mode, the control module generates a normal control signal; if the current working mode is emergency mode, the control module generates an emergency control signal; if the current working mode is follower mode, the control module generates a follower control signal.

4. The airborne intelligent voice call processing system based on working mode redundancy design according to claim 1 is characterized in that: The signal processing module is specifically composed of a mixing unit, a noise reduction unit, a squelch unit, and an automatic gain unit; The mixing unit is used to perform framing and FFT transformation on the digital audio signal output by the ADC conversion module, determine the main spectrum in each complex spectrum, optimize the phase of each complex spectrum based on the main spectrum, and simultaneously calculate the spectral entropy of each complex spectrum. Based on the spectral entropy, dynamic spectral entropy weights are assigned to each complex spectrum. Then, combined with the auditory masking compensation factor, the complex spectrum after phase optimization is synthesized. After IFFT transformation and overlap elimination, the mixed audio signal is obtained; The noise reduction unit is used to perform pre-emphasis, framing, and FFT transformation on the mixed audio signal output by the mixing unit, extract features based on the amplitude spectrum and phase spectrum of each frame signal to obtain multimodal features of each frame signal, input the multimodal features of each frame signal into a pre-trained noise reduction model for noise reduction processing, and obtain a noise-reduced audio signal; The squelch unit is used to extract features from the denoised audio signal output by the denoising unit, obtaining energy features including subband energy and differential energy. The squelch unit then uses dynamic subband GMM modeling to perform Bayesian decision optimization based on the energy features to obtain the squelched audio signal. The automatic gain unit is used to perform long-term static gain, medium-term dynamic compression and short-term transient protection on the audio signal after noise reduction output by the noise reduction unit to achieve automatic gain processing, obtain the audio signal after automatic gain, and transmit it to the control module or DAC conversion module.

5. The airborne intelligent voice call processing system based on working mode redundancy design according to claim 4 is characterized in that: The signal processing module is also equipped with a BIT self-test unit; The BIT self-test unit is used to instruct the MCU of the control module to send sinusoidal signals to detect whether the input and output of each module and unit of the onboard intelligent voice call processing system are normal, whether the ADC conversion module and DAC conversion module are working properly, and whether the system power supply is normal. After generating self-test information, the self-test information is uploaded to the host computer through UART serial port communication.

6. The onboard intelligent voice call processing system based on working mode redundancy design according to claim 4 is characterized in that: The control module is also used to determine whether the audio signal after noise reduction processing contains human voice through the sound activation detection algorithm. If it does not contain human voice, the squelch unit needs to be started to perform squelch processing. If it contains human voice, the automatic gain unit directly performs automatic gain processing.

7. An onboard intelligent voice call processing system based on working mode redundancy design according to any one of claims 1 to 5, characterized in that: The system also includes a pre-output filtering module; The pre-output filtering module is used to perform pre-output filtering on the noise reduction analog audio signal output by the DAC conversion module to obtain a filtered noise reduction analog audio signal, and select to output it through the first earphone, the second earphone or the third earphone based on the current working mode; The pre-output filtering module adopts a multi-order high-pass filtering and low-pass filtering cascade architecture, including two sets of high-pass filters and two sets of low-pass filters. The two sets of high-pass filters are a 300Hz high-pass filter and a 290Hz high-pass filter, and the two sets of low-pass filters are a 4KHz low-pass filter and a 6.48KHz low-pass filter.

8. An onboard intelligent voice call processing method based on working mode redundancy design, characterized in that: The method comprises: Confirm the current working mode, which can be normal mode, emergency mode or follower mode. In emergency mode, the host computer fails, and in follower mode, the onboard signal processing module fails. If the current working mode is normal mode, input selection is performed in the first microphone, the second microphone, and the third microphone, and the analog audio signal of the connected microphone is received. After being converted into a digital audio signal by the ADC, the onboard signal processing module performs mixing, noise reduction, squelch, and automatic gain processing. The processed audio signal is transmitted to the host computer via the SPI protocol for confirmation. The audio signal received from the host computer via the SPI protocol is converted by the DAC and output through the first earphone; If the current working mode is emergency mode, the analog audio signals from the first microphone, the second microphone, and the third microphone are received simultaneously, converted into digital audio signals by the ADC, and all are input into the onboard signal processing module for mixing, noise reduction, squelch, and automatic gain processing. The processed audio signals are converted by the DAC and output through the second earphone; If the current working mode is follower mode, the analog audio signal of the fourth microphone is received, converted into a digital audio signal by ADC, and then transmitted to the host computer through the SPI protocol. The host computer sends it to the backup intelligent voice call processing system for mixing, noise reduction, squelch and automatic gain processing, and the processed audio signal is returned through the SPI protocol, and then converted by DAC and output through the third earphone.

9. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; In which, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the onboard intelligent voice call processing method based on working mode redundancy design as described in claim 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it can implement the onboard intelligent voice call processing method based on working mode redundancy design as described in claim 8.

Images