Voice processing system, method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a voice processing system, method and device, electronic equipment and a storage medium. The system comprises a voice receiving assembly, a baseband chip and a microcontroller connected between the voice receiving assembly and the baseband chip. The voice receiving assembly is used for receiving a voice signal input by a user and sending the voice signal to the microcontroller so as to timely process the voice signal of the user; the microcontroller is used for receiving the voice signal sent by the voice receiving assembly; carrying out keyword detection on the voice signal; under the condition that the voice signal comprises the target keyword, the voice signal is sent to the baseband chip, so that a voice signal switching mechanism is added, a transmission path of the voice signal is cut off, the voice signal is effectively isolated from being monitored and utilized by a background, and the privacy of a user is protected; the baseband chip is used for receiving the voice signal sent by the microcontroller; and the voice signal is processed, so that the voice signal of the user can be processed under the condition that the user needs to carry out voice control.

Description

Technical Field

[0001] The present invention relates to the field of communication protection technology, and in particular to a voice processing system, method, device, electronic equipment and storage medium. Background Art

[0002] In recent years, the application of voice assistants has developed rapidly, especially in the form of voice-controlled home assistants (such as Google Home, Siri, and Tmall Genie). These products allow users to do things through voice command software. For example, users can play music, play videos, control home appliances, and so on by simply issuing commands to the smart voice assistant. In order for the voice assistant to always respond to the user's voice commands, the voice assistant generally stays in the background and silently monitors the user's voice. In this process, the microphone hardware and circuit parts that silently monitor the voice are always turned on 24 hours a day to serve the voice software. Even if the user trusts the service provider or manufacturer that provides the voice assistant, it is still impossible to avoid the microphone hardware being used by it to implement silent monitoring, and the user's privacy is at risk of being leaked. Summary of the invention

[0003] In order to solve the above problems, the embodiments of the present invention disclose a speech processing system, method, device, electronic device and storage medium.

[0004] In a first aspect, an embodiment of the present invention provides a voice processing system, the system comprising: a voice receiving component, a microcontroller and a baseband chip; the microcontroller is connected between the voice receiving component and the baseband chip;

[0005] The voice receiving component is used to receive a voice signal input by a user and send the voice signal to the microcontroller;

[0006] The microcontroller is used to receive the voice signal sent by the voice receiving component; perform keyword detection on the voice signal; and if the voice signal includes a target keyword, send the voice signal to the baseband chip so that the baseband chip processes the voice signal;

[0007] The baseband chip is used to receive the voice signal sent by the microcontroller and process the voice signal.

[0008] Optionally, the microcontroller is used to convert the voice signal into a narrowband signal for keyword detection; when the voice signal includes a target keyword, convert the voice signal into a broadband signal and send it to the baseband chip.

[0009] Optionally, the microcontroller is used to convert the time domain signal corresponding to the voice signal through fast Fourier transform to obtain spectrum information; compare the spectrum information with target spectrum information corresponding to the target keyword; and when the spectrum information includes the target spectrum information, send the voice signal to the baseband chip.

[0010] Optionally, the baseband chip is also used to obtain an update keyword input by a user; send the update keyword to the microcontroller so that the microcontroller uses the update keyword to replace the target keyword; and convert the time domain signal corresponding to the update keyword through a fast Fourier transform to obtain updated spectrum information.

[0011] Optionally, the system further includes: a voice assistant component; the voice assistant component is connected to the baseband chip;

[0012] The voice assistant component is used to receive the voice signal sent by the baseband chip and process the voice signal.

[0013] In a second aspect, an embodiment of the present invention provides a speech processing method, which is applied to a microcontroller, and the method includes:

[0014] Receiving a voice signal input by a user sent by a voice receiving component;

[0015] Performing keyword detection on the voice signal;

[0016] In the case that the voice signal includes the target keyword, the voice signal is sent to a baseband chip so that the baseband chip processes the voice signal.

[0017] Optionally, the performing keyword detection on the voice signal includes:

[0018] Converting the speech signal into a narrowband signal for keyword detection;

[0019] When the voice signal includes the target keyword, sending the voice signal to the baseband chip includes:

[0020] In the case that the voice signal includes the target keyword, the voice signal is converted into a broadband signal and sent to the baseband chip.

[0021] Optionally, the performing keyword detection on the voice signal includes:

[0022] The time domain signal corresponding to the speech signal is converted by fast Fourier transform to obtain spectrum information;

[0023] comparing the spectrum information with target spectrum information corresponding to the target keyword;

[0024] When the voice signal includes the target keyword, sending the voice signal to the baseband chip includes:

[0025] In a case where the spectrum information includes the target spectrum information, the voice signal is sent to the baseband chip.

[0026] Optionally, the method further comprises:

[0027] receiving an update keyword input by the user and sent by the baseband chip;

[0028] Replace the target keyword with the updated keyword;

[0029] The time domain signal corresponding to the update keyword is converted by fast Fourier transform to obtain updated spectrum information.

[0030] Optionally, sending the voice signal to a baseband chip so that the baseband chip processes the voice signal includes:

[0031] The voice signal is sent to the baseband chip so that the baseband chip processes the voice signal, and the voice signal is sent to the voice assistant component so that the voice assistant component processes the voice signal.

[0032] In a third aspect, an embodiment of the present invention provides a speech processing device, applied to a microcontroller, the device comprising:

[0033] A voice signal receiving module, used to receive a voice signal input by a user sent by a voice receiving component;

[0034] A voice signal detection module, used for performing keyword detection on the voice signal;

[0035] The voice signal sending module is used to send the voice signal to the baseband chip when the voice signal includes the target keyword, so that the baseband chip processes the voice signal.

[0036] Optionally, the voice signal detection module includes:

[0037] A narrowband signal detection submodule, used for converting the speech signal into a narrowband signal for keyword detection;

[0038] The voice signal sending module comprises:

[0039] The broadband signal sending submodule is used to convert the voice signal into a broadband signal and send it to the baseband chip when the voice signal includes the target keyword.

[0040] Optionally, the voice signal detection module includes:

[0041] A fast Fourier transform submodule, used for converting the time domain signal corresponding to the speech signal through fast Fourier transform to obtain spectrum information;

[0042] A spectrum information comparison submodule, used to compare the spectrum information with target spectrum information corresponding to the target keyword;

[0043] The voice signal sending module comprises:

[0044] The voice signal sending submodule is used to send the voice signal to the baseband chip when the spectrum information includes the target spectrum information.

[0045] Optionally, the device further comprises:

[0046] An update keyword receiving module, used for receiving the update keyword input by the user and sent by the baseband chip;

[0047] A target keyword replacement module, used to replace the target keyword with the update keyword;

[0048] The spectrum information updating module is used to convert the time domain signal corresponding to the update keyword through fast Fourier transform to obtain updated spectrum information.

[0049] Optionally, the voice signal sending module includes:

[0050] The voice assistant component processing submodule is used to send the voice signal to the baseband chip so that the baseband chip processes the voice signal, and send the voice signal to the voice assistant component so that the voice assistant component processes the voice signal.

[0051] In a fourth aspect, the present invention shows an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned speech processing method when executing the computer program.

[0052] In a fifth aspect, the present invention shows a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned speech processing method are implemented.

[0053] The embodiments of the present invention include the following advantages:

[0054] The voice processing system of the embodiment of the present invention includes: a voice receiving component, a microcontroller and a baseband chip; the microcontroller is connected between the voice receiving component and the baseband chip; the voice receiving component is used to receive the voice signal input by the user and send the voice signal to the microcontroller, so as to make corresponding processing for the user's voice signal in time; the microcontroller is used to receive the voice signal sent by the voice receiving component; perform keyword detection on the voice signal; when the voice signal includes the target keyword, send the voice signal to the baseband chip, thereby adding a voice signal switch mechanism, cutting off the propagation path of the voice signal, effectively isolating the voice signal from being used by background monitoring, and protecting user privacy; the baseband chip is used to receive the voice signal sent by the microcontroller; process the voice signal, so that the user's voice signal can be processed when the user needs to perform voice control. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 is a structural block diagram of a speech processing system according to an embodiment of the present invention;

[0057] Figure 2 is a flow chart of the steps of a speech processing method according to an embodiment of the present invention;

[0058] Figure 3 is a logic diagram of a speech processing method according to an embodiment of the present invention;

[0059] Figure 4 It is a structural block diagram of a speech processing device according to an embodiment of the present invention.

[0060] Description of reference numerals:

[0061] Voice receiving component 11, microcontroller 12, baseband chip 13. DETAILED DESCRIPTION

[0062] A baseband chip is an integrated circuit chip used to process low-frequency signals. It is usually used for digital signal processing, demodulation, encoding, etc. The operating frequency of a baseband chip is usually between tens of kilohertz and hundreds of megahertz. For example, the baseband chip in a mobile phone usually operates in the range of hundreds of megahertz. Voice recording is generally the result of microphone signal processing through a baseband chip.

[0063] In general digital circuit design, microphone signals are often directly connected to the baseband chip end, and the microphone hardware is available for voice software to call at any time. With the popularity of smart devices, more and more terminals are equipped with voice assistant functions, which can help users use voice to control conveniently. Generally, the foreground application calling the microphone is the first priority. After the foreground call is completed, the voice assistant begins to use the microphone to silently monitor the user's voice in the background, waiting for voice commands to implement instructions. In the background silent state, due to the design of the physical architecture, the microphone is always connected to the baseband, forming a natural monitoring system. Any sound in the environment will be picked up by the microphone without reservation. If it is used by the voice assistant, it will increase the user's security risk. For example, the content of the conversation is extracted for advertising services, digital portraits of users, etc. Whether the voice information is used depends entirely on the ethics of the service provider.

[0064] The present invention proposes a voice processing system, the purpose of which is to protect the privacy and security of user's voice. In order to achieve this goal, the embodiment of the present invention connects a microcontroller between a voice receiving component and a baseband chip, receives a voice signal sent by the voice receiving component through the microcontroller, performs keyword detection on the voice signal, and sends the voice signal to the baseband chip when the voice signal includes the target keyword, thereby adding a voice signal switch mechanism, cutting off the propagation path of the voice signal, effectively isolating the voice signal from being used by background monitoring, and protecting user privacy.

[0065] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0066] Reference Figure 1 , shows a structural block diagram of a speech processing system according to an embodiment of the present invention, the system may specifically include: a speech receiving component 11, a microcontroller 12 and a baseband chip 13; the microcontroller 12 is connected between the speech receiving component 11 and the baseband chip 13;

[0067] In the embodiment of the present invention, Figure 1As shown, the voice processing system may include a voice receiving component, a microcontroller and a baseband chip. Among them, the voice receiving component may include a microphone, an audio interface, a voice recognition chip, etc., and the number of voice receiving components may be one or more. The microcontroller may be a single-chip system that integrates a microprocessor (CPU), a memory (RAM, ROM, Flash, etc.), an input / output interface (I / O), a timer, a communication interface (such as UART, SPI, I2C, etc.) and other peripherals, and is used to control and process various tasks. The baseband chip is one of the core components in a mobile communication device (such as a smart phone, a tablet computer, an Internet of Things device, etc.), which is responsible for processing signal processing tasks related to wireless communication, and is mainly used for operations such as modulation and demodulation, signal encoding, decoding, data transmission and reception, and is the key hardware for realizing wireless communication functions. In the embodiment of the present invention, the microcontroller is arranged between the voice receiving component and the baseband chip, which can be used as a switch for transmitting voice signals to the baseband chip, cutting off the voice propagation path, isolating the voice signal from being used by the background of the mobile communication device, and protecting user privacy.

[0068] The voice receiving component 11 is used to receive a voice signal input by a user and send the voice signal to the microcontroller 12;

[0069] In an embodiment of the present invention, the voice receiving component can receive the voice signal input by the user and send the voice signal to the microcontroller. Taking the microphone as an example, the microphone can convert sound waves into electrical signals. Specifically, when the sound propagates through the air, sound waves will vibrate, and the diaphragm inside the microphone (such as a capacitive or dynamic type) will vibrate with the sound waves. The vibration of the diaphragm will change the capacitance or resistance in the circuit, thereby generating an electrical signal corresponding to the sound wave vibration. The collected electrical signal is an analog signal, and the quality of the analog signal can be improved by amplification, filtering and noise reduction processing for subsequent voice signal processing.

[0070] The microcontroller 12 is used to receive the voice signal sent by the voice receiving component 11; perform keyword detection on the voice signal; and when the voice signal includes a target keyword, send the voice signal to the baseband chip 13 so that the baseband chip 13 processes the voice signal;

[0071] In an embodiment of the present invention, the microcontroller can receive the voice signal sent by the voice receiving component and perform keyword detection on the voice signal. Specifically, the voice signal can be compared with the wake-up word information (i.e., the target keyword) in the microcontroller by writing a fast Fourier transform program to the microcontroller, and act as a physical switch for the microphone signal in the design architecture. When the voice signal includes the target keyword, the voice signal is sent to the baseband chip, thereby adding a voice signal switch mechanism, cutting off the propagation path of the voice signal, effectively isolating the voice signal from being used by background monitoring, and protecting user privacy.

[0072] The baseband chip 13 is used to receive the voice signal sent by the microcontroller 12 and process the voice signal.

[0073] In the embodiment of the present invention, the baseband chip can receive the voice signal sent by the microcontroller and process the voice signal. Specifically, the baseband chip can demodulate and decode the received voice signal to restore the voice data.

[0074] The voice processing system of the embodiment of the present invention includes: a voice receiving component, a microcontroller and a baseband chip; the microcontroller is connected between the voice receiving component and the baseband chip; the voice receiving component can receive the voice signal input by the user, and send the voice signal to the microcontroller, so as to make corresponding processing for the user's voice signal in time; the microcontroller can receive the voice signal sent by the voice receiving component; perform keyword detection on the voice signal; when the voice signal includes the target keyword, send the voice signal to the baseband chip, thereby adding a voice signal switch mechanism, cutting off the propagation path of the voice signal, effectively isolating the voice signal from being used by the background monitoring, and protecting the user's privacy; the baseband chip can receive the voice signal sent by the microcontroller; process the voice signal, so that the user's voice signal can be processed when the user needs to perform voice control. The embodiment of the present invention realizes user privacy protection by physically controlling the microphone and other hardware through the combination of software and hardware, focusing on privacy security, considering unique user scenarios, focusing on privacy security in silent scenarios, preventing monitoring and peeping, and having strong ability to cut off voice signal transmission.

[0075] In one embodiment, the microcontroller 12 is used to convert the voice signal into a narrowband signal for keyword detection; when the voice signal includes a target keyword, the voice signal is converted into a broadband signal and sent to the baseband chip 13.

[0076] In the embodiment of the present invention, the microcontroller uses a narrowband signal when performing keyword detection. When the voice signal includes the target keyword, the microcontroller can send the voice signal to the baseband chip via a broadband signal. Among them, the narrowband signal has a narrow bandwidth and a low transmission rate, thereby having low cost and low power consumption; the broadband signal has a wide bandwidth, thereby supporting a higher data transmission rate.

[0077] In one embodiment, the microcontroller 12 is used to convert the time domain signal corresponding to the voice signal through fast Fourier transform to obtain spectrum information; compare the spectrum information with the target spectrum information corresponding to the target keyword; and when the spectrum information includes the target spectrum information, send the voice signal to the baseband chip 13.

[0078] In an embodiment of the present invention, the microcontroller can convert the time domain signal corresponding to the voice signal through fast Fourier transform to obtain spectrum information; compare the spectrum information with the target spectrum information corresponding to the target keyword; and send the voice signal to the baseband chip when the spectrum information includes the target spectrum information. Since the time domain signal keeps changing within a time period and cannot be used for comparison, the microcontroller can obtain fixed spectrum information by converting it into a frequency domain signal.

[0079] Exemplarily, the microcontroller can convert the time domain signal T1 of the wake-up word "Xiao Ge Xiao Ge" into the target spectrum information F1 of "Xiao Ge Xiao Ge" through Fourier transform in advance, and compare the target spectrum information F1 to see whether the voice information received by the microphone contains the spectrum. The microcontroller performs a fast Fourier transform on the received real-time voice signal (time domain) to obtain the spectrum information, and then compares the spectrum information with the target spectrum information. If the spectrum information includes the target spectrum information, the voice signal is sent to the baseband chip. If the spectrum information does not include the target spectrum information, the microcontroller can continue to perform voice detection. Since the microcontroller does not switch to the baseband link when the switch is on, the baseband processor cannot get the voice information from the microphone.

[0080] In one embodiment, the baseband chip 13 is also used to obtain an update keyword input by a user; send the update keyword to the microcontroller 12 so that the microcontroller 12 replaces the target keyword with the update keyword; and convert the time domain signal corresponding to the update keyword through a fast Fourier transform to obtain updated spectrum information.

[0081] In an embodiment of the present invention, the baseband chip can obtain the update keyword input by the user, and send the update keyword to the microcontroller, so that the microcontroller replaces the target keyword with the update keyword, and converts the time domain signal corresponding to the update keyword through fast Fourier transform to obtain updated spectrum information. Since the microcontroller is connected to the baseband chip, the baseband chip can update the wake-up word to the microcontroller through the communication interface, so the user can flexibly configure the wake-up word at the software layer. When a new wake-up word is imported, the microcontroller can convert the time domain signal corresponding to the update keyword through fast Fourier transform to obtain updated spectrum information for storage.

[0082] In one embodiment, the voice processing system also includes: a voice assistant component (not shown in the figure); the voice assistant component is connected to the baseband chip 13; the voice assistant component is used to receive the voice signal sent by the baseband chip 13; and process the voice signal.

[0083] In an embodiment of the present invention, the voice processing system may further include: a voice assistant component, which is connected to the baseband chip, can receive the voice signal sent by the baseband chip, and process the voice signal. Among them, the voice assistant and the baseband chip play different roles in processing voice signals, and their processing methods, goals and functions are different. The voice assistant can realize functions such as voice recognition, voice synthesis and voice control, such as converting voice signals into text (speech recognition), or converting text into speech (speech synthesis), and performing operations according to instructions. The baseband chip can realize the transmission and reception of voice signals, and ensure the efficient transmission and reception of voice signals in wireless communication through modulation and demodulation, encoding and decoding, channel coding, multiple access technology, etc. The voice assistant relies on deep learning and AI technology, while the baseband chip relies on communication protocols and modulation and demodulation technology. In an embodiment of the present invention, the voice assistant and the baseband chip can work together to realize voice communication and voice interaction functions.

[0084] The voice receiving component of the voice processing system of the embodiment of the present invention can receive the voice signal input by the user, and send the voice signal to the microcontroller, so as to timely process the user's voice signal accordingly; the microcontroller can receive the voice signal sent by the voice receiving component; perform keyword detection on the voice signal; when the voice signal includes the target keyword, send the voice signal to the baseband chip, thereby adding a voice signal switch mechanism, cutting off the propagation path of the voice signal, effectively isolating the voice signal from being used by the background monitoring, and protecting the user's privacy; the baseband chip can receive the voice signal sent by the microcontroller; process the voice signal, so that the user's voice signal can be processed when the user needs to perform voice control. The embodiment of the present invention realizes user privacy protection by physically controlling the microphone and other hardware through the combination of software and hardware, focusing on privacy security, considering unique user scenarios, focusing on privacy security in silent scenarios, preventing eavesdropping and peeping, and having a strong ability to cut off voice signal transmission.

[0085] Reference Figure 2 , shows a flow chart of the steps of a speech processing method according to an embodiment of the present invention, which is applied to a microcontroller. The method may specifically include the following steps:

[0086] Step 201, receiving a voice signal input by a user sent by a voice receiving component;

[0087] In an embodiment of the present invention, a microcontroller can receive a voice signal input by a user sent by a voice receiving component. Among them, the voice receiving component can include a microphone, an audio interface, a voice recognition chip, etc., and the number of voice receiving components can be one or more. The microcontroller can be a single-chip system that integrates a microprocessor (CPU), a memory (RAM, ROM, Flash, etc.), an input / output interface (I / O), a timer, a communication interface (such as UART, SPI, I2C, etc.) and other peripherals, and is used to control and process various tasks. The baseband chip is one of the core components in a mobile communication device (such as a smart phone, a tablet computer, an Internet of Things device, etc.), which is responsible for processing signal processing tasks related to wireless communication, and is mainly used for operations such as modulation and demodulation, signal encoding, decoding, data transmission and reception, and is the key hardware for realizing wireless communication functions. In an embodiment of the present invention, a microcontroller is arranged between the voice receiving component and the baseband chip, which can be used as a switch for transmitting voice signals to the baseband chip, cutting off the voice propagation path, isolating the voice signal from being used by the background of the mobile communication device, and protecting user privacy.

[0088] Step 202, performing keyword detection on the voice signal;

[0089] Step 203: When the voice signal includes the target keyword, the voice signal is sent to the baseband chip so that the baseband chip processes the voice signal.

[0090] In one embodiment, the step of performing keyword detection on the voice signal and sending the voice signal to a baseband chip when the voice signal includes a target keyword may further include the following sub-steps:

[0091] Sub-step S11, converting the speech signal into a narrowband signal for keyword detection;

[0092] Sub-step S12, when the voice signal includes the target keyword, converting the voice signal into a broadband signal and sending it to the baseband chip.

[0093] In the embodiment of the present invention, the microcontroller uses a narrowband signal when performing keyword detection. When the voice signal includes the target keyword, the microcontroller can send the voice signal to the baseband chip via a broadband signal. Among them, the narrowband signal has a narrow bandwidth and a low transmission rate, thereby having low cost and low power consumption; the broadband signal has a wide bandwidth, thereby supporting a higher data transmission rate.

[0094] In one embodiment, the step of performing keyword detection on the voice signal and sending the voice signal to a baseband chip when the voice signal includes a target keyword may further include the following sub-steps:

[0095] Sub-step S21, converting the time domain signal corresponding to the speech signal by fast Fourier transform to obtain spectrum information;

[0096] Sub-step S22, when the spectrum information includes the target spectrum information, sending the voice signal to the baseband chip.

[0097] In an embodiment of the present invention, the microcontroller can convert the time domain signal corresponding to the voice signal through fast Fourier transform to obtain spectrum information; compare the spectrum information with the target spectrum information corresponding to the target keyword; and send the voice signal to the baseband chip when the spectrum information includes the target spectrum information. Since the time domain signal keeps changing within a time period and cannot be used for comparison, the microcontroller can obtain fixed spectrum information by converting it into a frequency domain signal.

[0098] Exemplarily, the microcontroller can convert the time domain signal T1 of the wake-up word "Xiao Ge Xiao Ge" into the target spectrum information F1 of "Xiao Ge Xiao Ge" through Fourier transform in advance, and compare the target spectrum information F1 to see whether the voice information received by the microphone contains the spectrum. The microcontroller performs a fast Fourier transform on the received real-time voice signal (time domain) to obtain the spectrum information, and then compares the spectrum information with the target spectrum information. If the spectrum information includes the target spectrum information, the voice signal is sent to the baseband chip. If the spectrum information does not include the target spectrum information, the microcontroller can continue to perform voice detection. Since the microcontroller does not switch to the baseband link when the switch is on, the baseband processor cannot get the voice information from the microphone.

[0099] In one embodiment, the step of sending the voice signal to a baseband chip so that the baseband chip processes the voice signal may further include the following sub-steps:

[0100] Sub-step S31, sending the voice signal to the baseband chip so that the baseband chip processes the voice signal, and sending the voice signal to the voice assistant component so that the voice assistant component processes the voice signal.

[0101] In an embodiment of the present invention, the voice assistant component is connected to the baseband chip, can receive the voice signal sent by the baseband chip, and process the voice signal. Among them, the voice assistant and the baseband chip play different roles in processing voice signals, and their processing methods, goals and functions are different. The voice assistant can realize functions such as voice recognition, speech synthesis and voice control, such as converting voice signals into text (speech recognition), or converting text into speech (speech synthesis), and performing operations according to instructions. The baseband chip can realize the transmission and reception of voice signals, and ensure the efficient transmission and reception of voice signals in wireless communication through modulation and demodulation, encoding and decoding, channel coding, multiple access technology, etc. The voice assistant relies on deep learning and AI technology, while the baseband chip relies on communication protocols and modulation and demodulation technology. In an embodiment of the present invention, the voice assistant and the baseband chip can work together to realize voice communication and voice interaction functions.

[0102] In one embodiment, the method further includes: receiving the update keyword input by the user and sent by the baseband chip; replacing the target keyword with the update keyword; and converting the time domain signal corresponding to the update keyword through fast Fourier transform to obtain update spectrum information.

[0103] In an embodiment of the present invention, the baseband chip can obtain the update keyword input by the user, and send the update keyword to the microcontroller, so that the microcontroller replaces the target keyword with the update keyword, and converts the time domain signal corresponding to the update keyword through fast Fourier transform to obtain updated spectrum information. Since the microcontroller is connected to the baseband chip, the baseband chip can update the wake-up word to the microcontroller through the communication interface, so the user can flexibly configure the wake-up word at the software layer. When a new wake-up word is imported, the microcontroller can convert the time domain signal corresponding to the update keyword through fast Fourier transform to obtain updated spectrum information for storage.

[0104] The microcontroller of the embodiment of the present invention is connected between the voice receiving component and the baseband chip; the microcontroller can receive the voice signal sent by the voice receiving component; perform keyword detection on the voice signal; when the voice signal includes the target keyword, send the voice signal to the baseband chip so that the baseband chip can receive the voice signal sent by the microcontroller; process the voice signal, thereby adding a voice signal switch mechanism, cutting off the propagation path of the voice signal, and effectively isolating the voice signal from being used by background monitoring, thereby protecting user privacy. The embodiment of the present invention realizes user privacy protection by physically controlling the microphone and other hardware through a combination of software and hardware, focusing on privacy security, considering unique user scenarios, focusing on privacy security in silent scenarios, preventing eavesdropping and peeping, and having a strong ability to cut off voice signal transmission.

[0105] Reference Figure 3 , shows a logic diagram of a speech processing method provided by an embodiment of the present invention, which is applied to a microcontroller. In order to enable those skilled in the art to better understand the embodiment of the present invention, the following is a Figure 3 The embodiments of the present invention are described as follows:

[0106] Step 301, determining whether the user calls the voice receiving component for voice control;

[0107] Step 302: If the user calls the voice receiving component for voice control, the voice signal is directly sent to the baseband chip;

[0108] Step 303: If the user does not call the voice receiving component for voice control, the voice signal is detected;

[0109] Step 304, determining whether the voice signal contains the target keyword;

[0110] Step 305: If the voice signal contains the target keyword, the voice signal is sent to the baseband chip;

[0111] Step 306: If the voice signal does not contain the target keyword, the propagation path of the voice signal is cut off.

[0112] The microcontroller of the embodiment of the present invention is connected between the voice receiving component and the baseband chip; the microcontroller can receive the voice signal sent by the voice receiving component; perform keyword detection on the voice signal; when the voice signal includes the target keyword, send the voice signal to the baseband chip so that the baseband chip can receive the voice signal sent by the microcontroller; process the voice signal, thereby adding a voice signal switch mechanism, cutting off the propagation path of the voice signal, and effectively isolating the voice signal from being used by background monitoring, thereby protecting user privacy. The embodiment of the present invention realizes user privacy protection by physically controlling the microphone and other hardware through a combination of software and hardware, focusing on privacy security, considering unique user scenarios, focusing on privacy security in silent scenarios, preventing eavesdropping and peeping, and having a strong ability to cut off voice signal transmission.

[0113] For the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0114] Reference Figure 4 , shows a structural block diagram of a speech processing device provided by an embodiment of the present invention, which is applied to a microcontroller and may specifically include the following modules:

[0115] The voice signal receiving module 401 is used to receive the voice signal input by the user sent by the voice receiving component;

[0116] A speech signal detection module 402, configured to perform keyword detection on the speech signal;

[0117] The voice signal sending module 403 is used to send the voice signal to the baseband chip when the voice signal includes the target keyword, so that the baseband chip processes the voice signal.

[0118] In the embodiment of the present invention, the speech signal detection module 402 includes:

[0119] A narrowband signal detection submodule, used for converting the speech signal into a narrowband signal for keyword detection;

[0120] The voice signal sending module 403 includes:

[0121] The broadband signal sending submodule is used to convert the voice signal into a broadband signal and send it to the baseband chip when the voice signal includes the target keyword.

[0122] The microcontroller uses narrowband signals for keyword detection. When the voice signal includes the target keyword, the microcontroller can send the voice signal to the baseband chip via broadband signals. The narrowband signal has a narrow bandwidth and a low transmission rate, which results in low cost and low power consumption; the broadband signal has a wide bandwidth, which supports a higher data transmission rate.

[0123] In the embodiment of the present invention, the speech signal detection module 402 includes:

[0124] A fast Fourier transform submodule, used for converting the time domain signal corresponding to the speech signal through fast Fourier transform to obtain spectrum information;

[0125] A spectrum information comparison submodule, used to compare the spectrum information with target spectrum information corresponding to the target keyword;

[0126] The voice signal sending module 403 includes:

[0127] The voice signal sending submodule is used to send the voice signal to the baseband chip when the spectrum information includes the target spectrum information.

[0128] Among them, the microcontroller can convert the time domain signal corresponding to the voice signal through fast Fourier transform to obtain spectrum information; compare the spectrum information with the target spectrum information corresponding to the target keyword; when the spectrum information includes the target spectrum information, the voice signal is sent to the baseband chip. Since the time domain signal keeps changing within the time period and cannot be used for comparison, the microcontroller can obtain fixed spectrum information by converting it into a frequency domain signal.

[0129] Exemplarily, the microcontroller can convert the time domain signal T1 of the wake-up word "Xiao Ge Xiao Ge" into the target spectrum information F1 of "Xiao Ge Xiao Ge" through Fourier transform in advance, and compare the target spectrum information F1 to see whether the voice information received by the microphone contains the spectrum. The microcontroller performs a fast Fourier transform on the received real-time voice signal (time domain) to obtain the spectrum information, and then compares the spectrum information with the target spectrum information. If the spectrum information includes the target spectrum information, the voice signal is sent to the baseband chip. If the spectrum information does not include the target spectrum information, the microcontroller can continue to perform voice detection. Since the microcontroller does not switch to the baseband link when the switch is on, the baseband processor cannot get the voice information from the microphone.

[0130] In an embodiment of the present invention, the device further includes:

[0131] An update keyword receiving module, used for receiving the update keyword input by the user and sent by the baseband chip;

[0132] A target keyword replacement module, used to replace the target keyword with the update keyword;

[0133] The spectrum information updating module is used to convert the time domain signal corresponding to the update keyword through fast Fourier transform to obtain updated spectrum information.

[0134] Among them, the baseband chip can obtain the update keyword input by the user, and send the update keyword to the microcontroller, so that the microcontroller replaces the target keyword with the update keyword, and converts the time domain signal corresponding to the update keyword through fast Fourier transform to obtain the updated spectrum information. Since the microcontroller is connected to the baseband chip, the baseband chip can update the wake-up word to the microcontroller through the communication interface, so the user can flexibly configure the wake-up word at the software layer. When a new wake-up word is imported, the microcontroller can convert the time domain signal corresponding to the update keyword through fast Fourier transform to obtain the updated spectrum information for storage.

[0135] In the embodiment of the present invention, the voice signal sending module 403 includes:

[0136] The voice assistant component processing submodule is used to send the voice signal to the baseband chip so that the baseband chip processes the voice signal, and send the voice signal to the voice assistant component so that the voice assistant component processes the voice signal.

[0137] Among them, the voice assistant component is connected to the baseband chip, can receive the voice signal sent by the baseband chip, and process the voice signal. Among them, the voice assistant and the baseband chip play different roles in processing voice signals, and their processing methods, goals and functions are different. The voice assistant can realize functions such as voice recognition, speech synthesis and voice control, such as converting voice signals into text (speech recognition), or converting text into speech (speech synthesis), and performing operations according to instructions. The baseband chip can realize the transmission and reception of voice signals, and ensure the efficient transmission and reception of voice signals in wireless communication through modulation and demodulation, encoding and decoding, channel coding, multiple access technology, etc. The voice assistant relies on deep learning and AI technology, while the baseband chip relies on communication protocols and modulation and demodulation technology. In an embodiment of the present invention, the voice assistant and the baseband chip can work together to realize voice communication and voice interaction functions.

[0138] The microcontroller of the embodiment of the present invention is connected between the voice receiving component and the baseband chip; the microcontroller can receive the voice signal sent by the voice receiving component; perform keyword detection on the voice signal; when the voice signal includes the target keyword, send the voice signal to the baseband chip so that the baseband chip can receive the voice signal sent by the microcontroller; process the voice signal, thereby adding a voice signal switch mechanism, cutting off the propagation path of the voice signal, and effectively isolating the voice signal from being used by background monitoring, thereby protecting user privacy. The embodiment of the present invention realizes user privacy protection by physically controlling the microphone and other hardware through a combination of software and hardware, focusing on privacy security, considering unique user scenarios, focusing on privacy security in silent scenarios, preventing eavesdropping and peeping, and having a strong ability to cut off voice signal transmission.

[0139] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0140] An embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned speech processing method when executing the computer program.

[0141] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned speech processing method are implemented.

[0142] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0143] It should be understood by those skilled in the art that embodiments of the present invention may provide methods, devices or computer program products. Therefore, embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, embodiments of the present invention may take the form of a computer program product implemented on one or more machine-readable media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems) and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0145] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0147] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0148] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0149] The above is a detailed introduction to a speech processing system, method, device, electronic device and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for a person skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A speech processing system, characterized in that: The system comprises: a voice receiving component, a microcontroller and a baseband chip; the microcontroller is connected between the voice receiving component and the baseband chip; The voice receiving component is used to receive a voice signal input by a user and send the voice signal to the microcontroller; The microcontroller is used to receive the voice signal sent by the voice receiving component; perform keyword detection on the voice signal; and if the voice signal includes a target keyword, send the voice signal to the baseband chip so that the baseband chip processes the voice signal; The baseband chip is used to receive the voice signal sent by the microcontroller and process the voice signal.

2. The system according to claim 1, characterized in that The microcontroller is used to convert the voice signal into a narrowband signal for keyword detection; when the voice signal includes the target keyword, the voice signal is converted into a broadband signal and sent to the baseband chip.

3. The system according to claim 1, characterized in that The microcontroller is used to convert the time domain signal corresponding to the voice signal into spectrum information through fast Fourier transform; compare the spectrum information with the target spectrum information corresponding to the target keyword; and send the voice signal to the baseband chip when the spectrum information includes the target spectrum information.

4. The system according to claim 3, characterized in that The baseband chip is also used to obtain the update keyword input by the user; send the update keyword to the microcontroller so that the microcontroller uses the update keyword to replace the target keyword; and convert the time domain signal corresponding to the update keyword through fast Fourier transform to obtain update spectrum information.

5. The system according to claim 1, characterized in that Also includes: A voice assistant component; the voice assistant component is connected to the baseband chip; The voice assistant component is used to receive the voice signal sent by the baseband chip; The speech signal is processed.

6. A speech processing method, characterized in that: Applied to a microcontroller, the method comprises: Receiving a voice signal input by a user sent by a voice receiving component; Performing keyword detection on the voice signal; In the case that the voice signal includes the target keyword, the voice signal is sent to a baseband chip so that the baseband chip processes the voice signal.

7. The method according to claim 6, characterized in that The performing keyword detection on the voice signal comprises: Converting the speech signal into a narrowband signal for keyword detection; When the voice signal includes the target keyword, sending the voice signal to the baseband chip includes: In the case that the voice signal includes the target keyword, the voice signal is converted into a broadband signal and sent to the baseband chip.

8. The method according to claim 6, characterized in that The performing keyword detection on the voice signal comprises: The time domain signal corresponding to the speech signal is converted by fast Fourier transform to obtain spectrum information; comparing the spectrum information with target spectrum information corresponding to the target keyword; When the voice signal includes the target keyword, sending the voice signal to the baseband chip includes: In a case where the spectrum information includes the target spectrum information, the voice signal is sent to the baseband chip.

9. The method according to claim 8, characterized in that The method further comprises: receiving an update keyword input by the user and sent by the baseband chip; Replace the target keyword with the updated keyword; The time domain signal corresponding to the update keyword is converted by fast Fourier transform to obtain updated spectrum information.

10. The method according to claim 6, characterized in that The sending the voice signal to the baseband chip so that the baseband chip processes the voice signal includes: The voice signal is sent to the baseband chip so that the baseband chip processes the voice signal, and the voice signal is sent to the voice assistant component so that the voice assistant component processes the voice signal.

11. A speech processing device, characterized in that: Applied to a microcontroller, the device comprises: A voice signal receiving module, used to receive a voice signal input by a user sent by a voice receiving component; A voice signal detection module, used for performing keyword detection on the voice signal; The voice signal sending module is used to send the voice signal to the baseband chip when the voice signal includes the target keyword, so that the baseband chip processes the voice signal.

12. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of a speech processing method as described in any one of claims 6 to 10 are implemented.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a speech processing method as described in any one of claims 6 to 10 are implemented.

Images