AI intelligent microphone

Abstract

The utility model relates to the technical field of microphones, in particular to an AI intelligent microphone, which comprises a laser ranging I C, a central control system I C, a human voice decoding I C, an AI processing I C, a wake-up switch and a power supply module. Whether a person is in front of the microphone or not can be detected through the laser ranging IC, if no person is in front of the microphone, the whole microphone is in a standby state, on the premise that a power source is turned on, if the person leaves and forgets to turn off the microphone, the microphone can automatically enter the standby state or the turn-off state in time, and the situation that the microphone works to transmit environment noise is avoided; a non-human voice (noise) part is eliminated, finally, a human voice signal is transmitted to the central control system I C, and the central control system I C is converted into UHF wireless transmission through audio processing of a chip of the central control system I C, so that transmission of other voices except human voices in a conference or other environments is intelligently eradicated, and it is guaranteed that only human voices are transmitted; and resonance sound transmission generated between the microphone and the sound equipment is effectively blocked in a human voice recognition mode.

Description

Technical Field

[0001] The utility model relates to the technical field of microphones, and in particular to an AI intelligent microphone. Background Art

[0002] A microphone (also known as a microphone, micro-phone, or handheld) is an energy conversion and transmission device that converts sound signals into electrical signals. In complex and changing environments, such as conference rooms, traditional conference microphones will transmit all sounds they can pick up, such as resonant sounds and ambient noise, and cannot clearly identify and transmit human voices. Furthermore, resonance between the speaker and the microphone is prone to occur and cannot be blocked automatically.

[0003] Secondly, the microphone is often forgotten to be turned off after use, and the microphone is likely to transmit noise in the environment and generate a large amount of ambient noise;

[0004] In summary, how to intelligently identify and clearly transmit human voices, and how to automatically put microphones into standby or shut down mode when not in use are technical problems that need to be urgently solved by those skilled in the art. Utility Model Content

[0005] In view of this, the purpose of the present invention is to provide an AI smart microphone to solve the technical problems in the prior art that the microphone cannot clearly recognize and transmit human voices, and cannot automatically turn off in time when the microphone is forgotten to be turned off after use.

[0006] The utility model is achieved through the following technical solutions:

[0007] An AI smart microphone, comprising a laser ranging IC, a central control system IC, a voice decoding IC, and an AI processing IC, wherein the central control system IC is connected to the laser ranging IC, the voice decoding IC is connected to the central control system IC, and the AI ​​processing IC is connected to the voice decoding IC and the central control system IC respectively;

[0008] It also includes a wake-up switch and a power supply module connected to the wake-up switch, and the power supply module is used to provide energy for the operation of the central control system IC.

[0009] Furthermore, the AI ​​processing IC includes a digital-to-analog converter connected to the voice decoding IC and a voice recognition module connected to the digital-to-analog converter.

[0010] Furthermore, the AI ​​processing IC also includes a filter and a spectrum subtractor respectively connected to the human voice recognition module, for eliminating non-human voices or noise.

[0011] Furthermore, the AI ​​processing IC also includes an amplifier, which is used to perform gain processing on the voice signal retained by the voice recognition module and transmit the sound signal to the central control system IC for transmission.

[0012] Furthermore, it also includes a display screen decoding IC and a display screen connected to the display screen decoding IC. The display screen decoding IC is used to decode the radio frequency, power and signal of the audio emitted by the central control system IC and display it on the display screen.

[0013] The beneficial effects of the present invention are:

[0014] When the AI ​​smart microphone of the present invention is in use, the wake-up switch can be used to turn on the power module to provide energy for the entire microphone system. At this time, the central control system IC first controls the laser ranging IC to turn on to detect whether there is anyone in front of the microphone. If no one is in front of the microphone, the entire microphone is in standby mode. If someone leaves and forgets to turn off the microphone while the power is on, the microphone can automatically enter standby or off mode in time to prevent the microphone from transmitting ambient noise during operation.

[0015] If the laser ranging IC detects that there is a person in front of the microphone, the central control system IC controls the human voice decoding IC to start analyzing the sound wavelength received by the microphone and converting the sound wavelength to the AI ​​processing IC;

[0016] During processing, the AI ​​processing IC first performs analog-to-digital conversion on the audio signal obtained by the voice decoding IC, identifies the voice signal after the conversion is completed, and eliminates the non-voice (noise) part to obtain the final voice signal;

[0017] Finally, the amplifier performs signal gain processing on the retained human voice signal and transmits the human voice signal to the central control system IC. The central control system IC converts the audio processing of its own chip into UHF wireless transmission, allowing the receiver to receive it and play it through the speakers, thereby intelligently preventing the spread of other sounds except human voices in meetings or other environments, ensuring that only human voices are transmitted, and effectively blocking the spread of resonance sounds generated between the microphone and the speakers by identifying the human voice. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the structure of the AI ​​smart microphone of this utility model.

[0019] Figure 2 This is a schematic diagram of the structure of the AI ​​processing IC of the AI ​​smart microphone of this utility model.

[0020] In the figure: 1-laser ranging IC, 2-central control system IC, 3-human voice decoding IC, 4-AI processing IC, 41-digital-to-analog converter, 42-human voice recognition module, 43-filter, 44-spectral subtractor, 45-amplifier, 5-wake-up switch, 6-power module, 7-display decoding IC, 8-display. DETAILED DESCRIPTION

[0021] Typical embodiments that embody the features and advantages of the present invention will be described in detail in the following description. It should be understood that the present invention can have various variations in different embodiments without departing from the scope of the present invention, and the descriptions and illustrations therein are essentially for illustrative purposes and are not intended to limit the present invention.

[0022] In the description of this application, the terms "upper" and "lower" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. These are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the structure referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they should not be understood as limitations on this application.

[0023] See also Figure 1 The utility model provides a technical solution: an AI smart microphone, including a laser ranging IC1, a central control system IC2, a human voice decoding IC3 and an AI processing IC4, and also including a wake-up switch 5 and a power module 6 connected to the wake-up switch 5. The wake-up switch 5 is a power switch provided by the microphone, and the power module 6 can be controlled to be turned on or off by the wake-up switch 5; the power module 6 is used to provide energy for the operation of the central control system IC2. The power module 6 can be powered by a network serial port or a lithium battery to power the microphone, so that the microphone is in standby mode.

[0024] See also Figure 1 The central control system IC2 is connected to the laser rangefinder IC1. The laser rangefinder IC1 can use the existing VL53L0X laser rangefinder chip. The laser rangefinder IC1 is used to detect whether someone is using the microphone. If the laser rangefinder IC1 detects that no one is using it, the microphone remains in standby mode and does not transmit sound. If the laser rangefinder IC1 detects that someone is using it, the microphone can transmit sound normally. In addition, the laser rangefinder IC1 can control the effective distance of laser detection through software or hardware to avoid the adverse experience caused by being too far or too close. For example, if the distance is too far, it is easy to detect the presence of multiple people, while if it is too close, it is impossible to ensure that the user is within the normal communication distance with the microphone. The specific operation method is based on existing technology and will not be elaborated on here.

[0025] See also Figure 1The human voice decoding IC3 is connected to the central control system IC2. The central control system IC2 adopts the U1R32D wireless chip in the prior art. The human voice decoding IC3 is used to analyze the sound wavelengths received by the microphone, and by splitting the received wavelengths one by one, distinguish and obtain the most needed human voice. The human voice decoding IC3 adopts the CX31993 human voice decoding chip in the prior art.

[0026] See also Figure 1 and Figure 2 , the AI ​​processing IC4 is respectively connected to the human voice decoding IC3 and the central control system IC2. The AI ​​processing IC4 is used to identify and obtain the human voice signal in the sound wavelength received by the human voice decoding IC3. The AI ​​processing IC4 adopts the voice chip model NRK3502 in the prior art. The AI ​​processing IC4 can distinguish the human voice through the sound learned by the system in the early stage and filter out the transmission of sounds other than the human voice (the AI ​​processing IC4 can expand and recognize other sounds through learning, such as bird sounds, music accompaniment sounds or other sounds. Except for the learned sounds, all other sounds cannot pass through the core operation of the AI ​​processing IC4, so that the noise is eliminated in the AI ​​processing IC4 and the obtained sound effect is amplified), thereby outputting a clean target sound and blocking the transmission of other sounds (noise) in an environment without human voice;

[0027] The AI ​​processing IC4 includes a digital-to-analog converter 41 connected to the voice decoding IC3, the digital-to-analog converter 41 is used to perform digital-to-analog conversion on the analog audio signal obtained by the voice decoding IC3, and a voice recognition module 42 connected to the digital-to-analog converter 41;

[0028] The AI ​​processing IC 4 further includes a filter 43, a spectrum subtractor 44 and an amplifier 45 respectively connected to the human voice recognition module 42, and the filter 43 and the spectrum subtractor 44 are used to eliminate non-human voices or noise;

[0029] The amplifier 45 is used to perform gain processing on the voice signal retained by the voice recognition module 42 and transmit the sound signal to the central control system IC2 for transmission.

[0030] See also Figure 1 The present invention also includes a display screen decoding IC7 and a display screen 8 connected to the display screen decoding IC7. The display screen decoding IC7 is used to decode the radio frequency, power and signal of the audio emitted by the central control system IC2 and display them on the display screen 8. The display screen decoding IC7 adopts the display screen decoding chip model ES7243L in the existing technology.

[0031] When the AI ​​smart microphone of the present invention is in use, the wake-up switch 5 can be used to turn on the power module 6 to provide energy for the operation of the entire microphone system. At this time, the central control system IC2 first controls the laser ranging IC1 to turn on to detect whether there is anyone in front of the microphone. If there is no one, the entire microphone is in standby mode. If someone leaves and forgets to turn off the microphone while the power is on, the microphone can automatically enter the standby or off mode in time to prevent the microphone from transmitting ambient noise during operation.

[0032] If the laser ranging IC1 detects that there is a person in front of the microphone, the central control system IC2 controls the human voice decoding IC3 to start analyzing the sound wavelength received by the microphone and converts the sound wavelength to the AI ​​processing IC4;

[0033] During processing, the AI ​​processing IC4 first performs analog-to-digital conversion on the audio signal obtained by the human voice decoding IC3. After the conversion is completed, the digital audio data stream is transmitted to the human voice recognition module 42. The human voice recognition module 42 pre-imports a trained voice algorithm model. The voice algorithm uses artificial intelligence technology and models to analyze and model the input original human voice signal and noise signal to analyze the spectrum, time domain and spatial domain characteristics of the sound signal, understand the type, distribution and intensity parameters of the sound, and improve the reliability of the voice algorithm through large-scale training and comparison of sound feature parameters;

[0034] The voice recognition module 42 uses a speech algorithm to analyze and count the digital audio data stream to identify the human voice signal, and eliminates the non-human voice (noise) portion through the filter 43 and the spectrum subtractor 44 to obtain the final human voice signal. The specific process of obtaining the human voice signal is conventional and will not be described in detail here.

[0035] Finally, the amplifier 45 performs signal gain processing on the human voice signal that is finally retained, and transmits the human voice signal to the central control system IC2. The central control system IC2 converts the audio processing of its own chip into UHF wireless transmission, allowing the receiver to receive and play through the speakers, thereby intelligently eliminating the propagation of other sounds except human voices in meetings or other environments, ensuring that only human voices are propagated, and effectively blocking the propagation of resonance sounds generated between the microphone and the speakers by identifying the human voice; the display screen decoding IC7 can decode the radio frequency, power and signal of the audio emitted by the central control system IC2 and display it on the display screen 8. The display screen 8 can also be used to display the volume or battery level of the microphone.

[0036] The microphone of the present invention uses the laser ranging IC1 to determine whether the product is in use and automatically turns it off or on. The microphone of the present invention uses the AI ​​processing IC4, which has fast AI calculation time and low latency. The AI ​​processing IC4 recognizes human voices and can be used in classrooms, conference rooms, performances, etc. to ensure the restoration of human voices. Secondly, the microphone of the present invention will not resonate even if the microphone is in zero-distance contact with the audio speaker in an environment without human voices, thereby ensuring the quality of human voice transmission and the use effect of the product.

[0037] The present invention can realize wired microphones and wireless microphones. The above process is the use process of wireless microphones. The difference is that wired microphones do not have UHF radio frequency transmission, and can directly convert the sound recognized by AI into an analog signal and play it through amplification devices such as power amplifiers or mixing consoles.

[0038] Finally, it should be noted that the above-mentioned embodiments are only preferred embodiments of the present invention and cannot be used to limit the scope of protection of the present invention. Any non-substantial changes and replacements made by technicians in this field on the basis of the present invention fall within the scope of protection required by the present invention.

Claims

1. An AI smart microphone, characterized by: The invention comprises a laser ranging IC (1), a central control system IC (2), a human voice decoding IC (3) and an AI processing IC (4), wherein the central control system IC (2) is connected to the laser ranging IC (1), the human voice decoding IC (3) is connected to the central control system IC (2), and the AI ​​processing IC (4) is connected to the human voice decoding IC (3) and the central control system IC (2) respectively; It also includes a wake-up switch (5) and a power supply module (6) connected to the wake-up switch (5), and the power supply module (6) is used to provide energy for the operation of the central control system IC (2).

2. The AI ​​smart microphone according to claim 1, characterized in that: The AI ​​processing IC (4) includes a digital-to-analog converter (41) connected to the human voice decoding IC (3) and a human voice recognition module (42) connected to the digital-to-analog converter (41).

3. The AI ​​smart microphone according to claim 2, characterized in that: The AI ​​processing IC (4) further includes a filter (43) and a spectrum subtractor (44) respectively connected to the human voice recognition module (42) for eliminating non-human voices or noise.

4. The AI ​​smart microphone according to claim 2 or 3, characterized in that: The AI ​​processing IC (4) further includes an amplifier (45), which is used to perform gain processing on the human voice signal retained by the human voice recognition module (42) and transmit the sound signal to the central control system IC (2) for transmission.

5. The AI ​​smart microphone according to claim 1, characterized in that: The invention also includes a display screen decoding IC (7) and a display screen (8) connected to the display screen decoding IC (7). The display screen decoding IC (7) is used to decode the radio frequency, power and signal of the audio emitted by the central control system IC (2) and display them on the display screen (8).

Images