One-button intelligent voice interactive microphone system and usage method

Abstract

The present invention discloses a one-button intelligent voice interactive microphone system and a method for using the same, including a one-button intelligent voice interactive microphone system, including a search module, an access module, a voice acquisition module, a processing module, a recognition module, an evaluation module and an interaction module, and provides a method, including obtaining multiple voice signal beams with the largest analog signal waveform widths, establishing a voice quality evaluation test model for the analog signals corresponding to the selected voice signal beams, and training the voice samples of the selected voice signal beams to obtain uniform, stable and continuous voice samples, and performing voice quality evaluation based on uniformity, stability and continuity to obtain a voice quality evaluation score, and outputting the voice sample with the highest voice quality evaluation score to complete the interaction.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic equipment, and in particular to a microphone interaction technology, and specifically to a one-button intelligent voice interaction microphone system and a use method thereof. Background Art

[0002] With the rapid development of wireless microphone circuit technology, the performance of wireless microphone systems is getting better and better, the anti-interference ability is getting stronger and stronger, and the functions are becoming more and more. Change the RF frequency, spectrum analysis, infrared frequency matching, scan interference-free frequency, frequency allocation, sound pickup sensitivity adjustment, transmission power setting, each channel volume and total volume control, anti-howling frequency shifter setting, effect setting, equalizer adjustment, audio output squelch control, etc., each function is manually operated by pressing the buttons on the wireless microphone transmitter or wireless microphone receiver. With powerful performance and more functions, the operation is very complicated, cumbersome and difficult to operate.

[0003] Therefore, in the prior art, for example, the publication number "CN104936091A" discloses an intelligent interaction method and system based on a circular microphone array, which includes: receiving a user voice signal through a circular microphone array; denoising the voice signal to obtain a denoised voice signal; pre-identifying the denoised voice signals in different beam directions, and selecting the beam direction of the voice signal with the highest recognition score as the target speaker direction, and subsequently performing voice recognition on the denoised voice signal in the target speaker direction to obtain a voice recognition result; and performing operations according to the voice recognition result. The signal-to-noise ratio of the voice signal output by the microphone array beam can be effectively improved, thereby improving the voice recognition effect and making human-computer interaction more intelligent.

[0004] In the above, it is difficult to determine the input voice signal by using the signal-to-noise ratio of the voice signal. For example, in a noisy environment, the signal-to-noise ratio of the voice signal obtained by shouting loudly is the largest. The input signal cannot be obtained by the signal-to-noise ratio alone. The continuity, uniformity and stability of the voice signal must be judged. The voice signal obtained by shouting loudly is not continuous, uniform and stable, so these intrusion signals can be effectively excluded. Summary of the invention

[0005] In view of this, an object of the present invention is to provide a one-touch intelligent voice interaction microphone system and a method of use.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A one-button intelligent voice interactive microphone system, comprising

[0008] The search module is used to start the cellular network module or the Bluetooth module to search for request signals of smart devices around the microphone that can be used to connect to the microphone.

[0009] The access module matches and connects the smart device with the microphone according to the device request signal.

[0010] The voice acquisition module acquires the voice signal input by the user through the microphone array.

[0011] A processing module, which performs denoising, Fourier transform and analog conversion on the external input voice signal collected by the voice collection module to obtain a clear analog signal;

[0012] The recognition module is used to obtain at least two speech signal beams with the largest waveform width in the analog signal,

[0013] The evaluation module establishes a voice quality evaluation test model for the analog signal corresponding to the selected voice signal beam, trains the voice samples of the selected voice signal beam, performs voice quality evaluation and obtains the voice quality evaluation score, and outputs the voice sample with the highest voice quality evaluation score;

[0014] The interaction module completes the interaction with the connected smart device according to the voice sample.

[0015] Preferably, the cellular network module or the Bluetooth module is embedded in the microphone, and a key module is provided on the microphone, the key module is connected to the control module, and the control module is connected to the cellular network module and the Bluetooth module.

[0016] Preferably, the cellular network module includes multiple modules including WiFi module, Zigbee module, Wlan module and 4 / 5G module.

[0017] Preferably, the evaluation module establishes a voice quality evaluation test model method as follows:

[0018] According to the waveform width of the analog signal, the uniformity, stability and continuity of the analog signal waveform per second are obtained, and a voice quality evaluation model is established according to the uniformity, stability and continuity of the analog signal waveform.

[0019] Preferably, the specific formula of the voice quality assessment model is:

[0020] Y = (∑AA) + ￡ * ￠

[0021] in:

[0022] Y is the voice quality score;

[0023] A is the waveform of the analog signal;

[0024] ∑A is the mathematical expectation of the waveform average of the analog signal;

[0025] ￡ is a parameter to be determined;

[0026] ￠ is the continuity of the waveform of the analog signal per second.

[0027] Preferably, the interaction module receives the interaction instruction input by the input module, and completes the interaction with the connected smart device according to the interaction instruction.

[0028] Preferably, the input module receives a speech sample with the highest speech quality evaluation score, converts the speech sample into a corresponding analog signal, and obtains a speech signal based on the analog signal.

[0029] A method for using a one-button intelligent voice interaction microphone comprises the following steps:

[0030] Before establishing voice interaction, the search module is turned on by the button module, and the cellular network module or the Bluetooth module is turned on and started. The search module establishes a connection with the smart device based on the smart device signal searched by the cellular network module or the Bluetooth module and the provided microphone matching code;

[0031] After the connection is established, press the voice collection button, and the voice collection module obtains the voice signal input by the user through the microphone array;

[0032] The external input voice signal collected by the voice collection module is subjected to denoising, Fourier transform and analog conversion to obtain a clear analog signal;

[0033] At least two speech signal beams with the largest waveform width are obtained from the analog signal;

[0034] Establish a speech quality assessment test model for the analog signal corresponding to the selected speech signal beam, train the speech samples of the selected speech signal beam, perform speech quality assessment and obtain the speech quality assessment score, and output the speech sample with the highest speech quality assessment score;

[0035] The interaction is completed with the connected smart device according to the voice sample.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention converts the input voice signal to obtain an analog signal, obtains multiple voice signal beams with the largest analog signal waveform width, establishes a voice quality assessment test model for the analog signal corresponding to the selected voice signal beam, and trains the voice sample of the selected voice signal beam to obtain a uniform, stable and continuous voice sample, and performs voice quality assessment based on uniformity, stability and continuity and obtains a voice quality assessment score, outputs a voice sample with the highest voice quality assessment score to complete the interaction, and the present invention makes a judgment and assessment on the continuity, uniformity and stability of the voice signal. The voice signal obtained by shouting loudly is not continuous, uniform and stable, so these intrusion signals can be effectively excluded.

[0038] The invention is operated by buttons, which is simple and convenient to operate. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A connection diagram between a microphone and a smart device in the present invention;

[0040] Figure 2 Schematic diagram of the microphone system in the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] See also Figure 1-2 The present invention provides a one-touch intelligent voice interactive microphone system, comprising

[0043] The search module is used to start the cellular network module or the Bluetooth module to search for request signals of smart devices around the microphone that can be used to connect to the microphone.

[0044] The access module matches and connects the smart device with the microphone according to the device request signal.

[0045] The voice acquisition module acquires the voice signal input by the user through the microphone array.

[0046] A processing module, which performs denoising, Fourier transform and analog conversion on the external input voice signal collected by the voice collection module to obtain a clear analog signal;

[0047] The recognition module is used to obtain at least two speech signal beams with the largest waveform width in the analog signal,

[0048] The evaluation module establishes a voice quality evaluation test model for the analog signal corresponding to the selected voice signal beam, trains the voice samples of the selected voice signal beam, performs voice quality evaluation and obtains the voice quality evaluation score, and outputs the voice sample with the highest voice quality evaluation score;

[0049] The interaction module completes the interaction with the connected smart device according to the voice sample.

[0050] In the present invention, the mobile cellular network module or the Bluetooth module is embedded in the microphone, and a key module is arranged on the microphone, the key module is connected to the control module, and the control module is connected to the cellular network module and the Bluetooth module.

[0051] In the present invention, the cellular network module includes multiple types of WiFi module, zigbee module, Wlan module and 4 / 5G module.

[0052] In the present invention, the interaction module receives the interaction instruction input by the input module, and completes the interaction with the connected smart device according to the interaction instruction.

[0053] In the present invention, the input module receives a speech sample with the highest speech quality evaluation score, converts the speech sample into a corresponding analog signal, and obtains a speech signal based on the analog signal.

[0054] Implementation Method 1

[0055] A method for using a one-button intelligent voice interaction microphone comprises the following steps:

[0056] Before establishing voice interaction, the search module is turned on by the button module, and the Bluetooth module is turned on and started. The search module establishes a connection with the smart device through Bluetooth based on the smart device signal searched by the Bluetooth module and the provided microphone matching code;

[0057] After the connection is established, press the voice collection button, and the voice collection module obtains the voice signal input by the user through the microphone array;

[0058] The external input voice signal collected by the voice collection module is subjected to denoising, Fourier transform and analog conversion to obtain a clear analog signal;

[0059] At least two speech signal beams with the largest waveform width are obtained from the analog signal;

[0060] Establish a speech quality assessment test model for the analog signal corresponding to the selected speech signal beam, train the speech samples of the selected speech signal beam, perform speech quality assessment and obtain the speech quality assessment score, and output the speech sample with the highest speech quality assessment score;

[0061] The interaction is completed with the connected smart device according to the voice sample.

[0062] In the above, the method for the evaluation module to establish a voice quality evaluation test model is:

[0063] According to the waveform width of the analog signal, the uniformity, stability and continuity of the analog signal waveform per second are obtained, and a voice quality evaluation model is established according to the uniformity, stability and continuity of the analog signal waveform.

[0064] Preferably, the specific formula of the voice quality assessment model is:

[0065] Y = (∑AA) + ￡ * ￠

[0066] in:

[0067] Y is the voice quality score;

[0068] A is the waveform of the analog signal;

[0069] ∑A is the mathematical expectation of the waveform average of the analog signal;

[0070] ￡ is a parameter to be determined;

[0071] ￠ is the continuity of the waveform of the analog signal per second.

[0072] Implementation Method 2

[0073] A method for using a one-button intelligent voice interaction microphone comprises the following steps:

[0074] Before establishing voice interaction, the search module is turned on through the button module, and the cellular network module is turned on and started. The search module establishes a connection with the smart device through the cellular network module based on the smart device signal searched by the cellular network module and the provided microphone matching code;

[0075] After the connection is established, press the voice collection button, and the voice collection module obtains the voice signal input by the user through the microphone array;

[0076] The external input voice signal collected by the voice collection module is subjected to denoising, Fourier transform and analog conversion to obtain a clear analog signal;

[0077] At least two speech signal beams with the largest waveform width are obtained from the analog signal;

[0078] Establish a speech quality assessment test model for the analog signal corresponding to the selected speech signal beam, train the speech samples of the selected speech signal beam, perform speech quality assessment and obtain the speech quality assessment score, and output the speech sample with the highest speech quality assessment score;

[0079] The interaction is completed with the connected smart device according to the voice sample.

[0080] In the above, the method for the evaluation module to establish a voice quality evaluation test model is:

[0081] According to the waveform width of the analog signal, the uniformity, stability and continuity of the analog signal waveform per second are obtained, and a voice quality evaluation model is established according to the uniformity, stability and continuity of the analog signal waveform.

[0082] Preferably, the specific formula of the voice quality assessment model is:

[0083] Y = (∑AA) + ￡ * ￠

[0084] in:

[0085] Y is the voice quality score;

[0086] A is the waveform of the analog signal;

[0087] ∑A is the mathematical expectation of the waveform average of the analog signal;

[0088] ￡ is a parameter to be determined;

[0089] ￠ is the continuity of the waveform of the analog signal per second.

[0090] Cellular network modules include WiFi modules, zigbee modules, Wlan modules and various 4 / 5G modules.

[0091] The present invention converts the input voice signal to obtain an analog signal, obtains multiple voice signal beams with the largest analog signal waveform width, establishes a voice quality assessment test model for the analog signal corresponding to the selected voice signal beam, and trains the voice sample of the selected voice signal beam to obtain a uniform, stable and continuous voice sample, and performs voice quality assessment based on uniformity, stability and continuity and obtains a voice quality assessment score, outputs a voice sample with the highest voice quality assessment score to complete the interaction, and the present invention makes a judgment and assessment on the continuity, uniformity and stability of the voice signal. The voice signal obtained by shouting loudly is not continuous, uniform and stable, so these intrusion signals can be effectively excluded.

[0092] The parts not involved in the present invention are the same as the prior art or can be implemented by the prior art. Although the embodiments of the present invention have been shown and described, it is understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the attached claims and their equivalents.

Claims

1. A one-button intelligent voice interactive microphone system, comprising The search module is used to start the cellular network module or the Bluetooth module to search for request signals of smart devices around the microphone that can be used to connect to the microphone. The access module matches and connects the smart device with the microphone according to the device request signal. The voice acquisition module acquires the voice signal input by the user through the microphone array. A processing module, which performs denoising, Fourier transform and analog conversion on the external input voice signal collected by the voice collection module to obtain a clear analog signal; The recognition module is used to obtain at least two speech signal beams with the largest waveform width in the analog signal, The evaluation module establishes a voice quality evaluation test model for the analog signal corresponding to the selected voice signal beam, trains the voice samples of the selected voice signal beam, performs voice quality evaluation and obtains the voice quality evaluation score, and outputs the voice sample with the highest voice quality evaluation score; The interaction module completes the interaction with the connected smart device according to the voice sample.

2. The one-touch intelligent voice interactive microphone system according to claim 1, characterized in that: The mobile cellular network module or the Bluetooth module is embedded in the microphone, and a key module is arranged on the microphone, the key module is connected to the control module, and the control module is connected to the cellular network module and the Bluetooth module.

3. The one-touch intelligent voice interactive microphone system according to claim 1, characterized in that: The cellular network module includes multiple types of WiFi module, zigbee module, Wlan module and 4 / 5G module.

4. The one-touch intelligent voice interaction microphone system according to claim 1, characterized in that: The method for establishing the voice quality evaluation test model by the evaluation module is as follows: According to the waveform width of the analog signal, the uniformity, stability and continuity of the analog signal waveform per second are obtained, and a voice quality evaluation model is established according to the uniformity, stability and continuity of the analog signal waveform.

5. The one-touch intelligent voice interactive microphone system according to claim 1, characterized in that: The interaction module receives the interaction instruction input by the input module, and completes the interaction with the connected smart device according to the interaction instruction.

6. The one-touch intelligent voice interactive microphone system according to claim 5, characterized in that: The input module receives a speech sample with the highest speech quality evaluation score, converts the speech sample into a corresponding analog signal, and obtains a speech signal according to the analog signal.

7. A method for using a one-button intelligent voice interactive microphone, characterized in that: The steps include: Before establishing voice interaction, the search module is turned on by the button module, and the cellular network module or the Bluetooth module is turned on and started. The search module establishes a connection with the smart device based on the smart device signal searched by the cellular network module or the Bluetooth module and the provided microphone matching code; After the connection is established, press the voice collection button, and the voice collection module obtains the voice signal input by the user through the microphone array; The external input voice signal collected by the voice collection module is subjected to denoising, Fourier transform and analog conversion to obtain a clear analog signal; At least two speech signal beams with the largest waveform width are obtained from the analog signal; Establish a speech quality assessment test model for the analog signal corresponding to the selected speech signal beam, train the speech samples of the selected speech signal beam, perform speech quality assessment and obtain the speech quality assessment score, and output the speech sample with the highest speech quality assessment score; The interaction is completed with the connected smart device according to the voice sample.

Images