JP3074351U - Voice control identification device - Google Patents

Abstract

(57) [Summary] To enable a user to control computer peripheral equipment or home information means by voice. SOLUTION: A sound source, a voice control identification unit for expanding an input sound source, converting the obtained information into digital information, comparing the obtained information with pre-stored information, and transmitting an error signal or an enable signal; A command signal end connected to the input port of the voice control identification unit,
An enable signal terminal connected to an output port of the voice control identification unit, performing the following processing according to a signal of the voice control identification unit, transmitting information to a computer, or transmitting a command signal to the voice control identification unit. A single-chip microcomputer that receives the next voice command by transmitting, a recording function key connected to the single-chip microcomputer,
An identification indicator connected to an output port of the voice control identification unit and illuminated when a recording function key is pressed, so that a user can control a computer peripheral or a home information product by outputting a voice. .

Description

[Detailed description of the invention]

[0001]

[Technical field to which the invention belongs]

 The present invention relates to a voice control identification device, and more particularly, to a voice control identification device capable of controlling a computer peripheral device or a home information product by a user speaking.

[0002]

[Prior art]

 In recent years, computers and various household products have been continuously growing in terms of functions and performance, and sometimes the technology has been surpassed.However, in terms of operation, humanization is insufficient. Therefore, it is sometimes inconvenient in terms of use.

Performing control and input / output through voice identification is one important factor for humanization and simplification of operation, so many product manufacturers (computers and information field manufacturers) have We are conducting research and development on the hardware and software of voice recognition means at a considerable cost, and hope to achieve humanization of control using hardware or software voice recognition technology.

[0004] There are roughly two directions in the conventional voice recognition technology. One is to use software and compare the large amount of information by the processing functions of current high-speed computers, but in such a case, it is necessary to establish a huge database (sound source), Since the languages of each country are different, there is a problem in the efficiency of identification and it can be used only for high-speed computers.

[0005] The second type uses a sound compression technique. That is, voice is processed by hardware to convert information. However, such techniques can be used simply to memorize voices and to play them back.

[0006]

[Problems to be solved by the invention]

 The present invention re-arranges the tasks in view of the impediments in speech recognition at hand, and the tasks that can be organized include the following: (1) All characters can be identified and even different words What is identifiable is far beyond the level of the current technology, which cannot be completed in decades, and the cost of exhausted R & D and the price of products is This can be a heavy load on users and manufacturers. (2) The frequency of each person's voice is different, and applying one person to any person with a single voice recognition system, based on current technology, still needs to be surpassed. (3) For discriminating speech, discrimination efficiency is important, that is, an error may occur. If an error occurs, it must not cause any injury or loss to humans or things. Therefore, it is necessary to pay attention to voice recognition as applied to human nature.

[0007]

[Means for Solving the Problems]

 In view of the above problems, the inventor of the present invention has proceeded with research and development and has developed a humanized voice control identification device in accordance with academic applications. It can be used in various computer peripherals and household information products.

In the present invention, the basis of identification is set based on a voice waveform, regardless of character or language recognition, and the maximum determination of a voice waveform is limited to 30. That is, the number of voice samples is 30 or less. In this way, no database is required, and a speech recognition system can be created at extremely low hardware cost.

Further, the present invention provides a voice control identification device corresponding to humanization, which enables a user to input a voice sample by himself / herself when using the device of the present invention for the first time and to improve the efficiency of voice recognition. Its primary purpose.

Another object of the present invention is to provide a voice control identification device capable of inferring logic by a single-chip microcomputer in the design of an electric circuit, seeking rescue, and automatically removing errors. The purpose of.

In order to further clarify the features and technical contents of the present invention, preferred embodiments of the present invention will be described below in detail with reference to the accompanying drawings, but those configurations limit the present invention. is not.

[0012]

[Embodiment of the invention]

 As shown in FIG. 1, the present invention relates to a voice control identification device, which is built into various computer peripheral equipment and home information products. It mainly includes a voice control identification unit 1, a single chip microcomputer 2, an identification indicator light 3, and a recording function key 4.

The voice control identification unit 1 is provided with a microphone expanding means 11, an input end of the microphone expanding means 11 is connected to the microphone 6, and an output end of the microphone expanding means 11 is connected to the signal conversion means 12. Connected, the output end of the signal conversion means 12 is connected to the signal storage means 13, and is connected to the sound processing means 14, and the output ports of the sound processing means 14 are the identification signal 3 and the enable signal of the single-chip microcomputer 2, respectively. The command signal end of the single-chip microcomputer 2 is connected to the input port of the voice processing means 14, and the input / output port 21 of the single-chip microcomputer 2 is connected to the computer (PC) 20. The input terminal of the single-chip microcomputer 2 is connected to the recording function key 4.

In the embodiment of the present invention, the microphone expansion means 11, the signal conversion means 12, the signal storage means 13, and the audio processing means 14 are matched to a single chip (see FIG. 1).

The operation method of the voice control identification device is as described below. That is, the user presses the recording function key 4 when first using. At this time, the identification indicator light 3 is turned on, and when the user records at most 30 different voice commands (e.g., a mailbox, online, a computer, etc.) one after another, and records the command each time, the identification indicator light 3 is used. Recording can be performed only when is lit, and after recording one command, the identification indicator light 3 is automatically turned off, and the sound is expanded to the microphone expanding means 11 via the microphone 6, and then the sound is expanded. The result is transmitted to the signal conversion means 12, the sound is converted to digital information, and the signal is stored in the signal storage means 13. At this time, the identification indicator lamp 3 is turned on again, and waits for the user to record a voice command. In this way, all the commands are input by repeating the procedure, and all the personalized voice command samples are stored in the signal storage means 13.

After the user completes the recording of the command sample, the single-chip microcomputer 2 sends a command signal to the audio processing means 14 at regular intervals, requests the lighting of the identification indicator lamp 3, and switches the function to the identification mode. At this time, the user waits for the identification indicator lamp 3 to be lit, and when lit, issues a command, the voice is expanded by the microphone expansion means 11, and is converted to digital information by the signal conversion means 12, and Then, the voice processing means 14 compares the information with the information in the existing signal storage means 13, and if applicable, the voice processing means 14 sends a comparison enable signal, and if not, sends an error signal. At this time, the identification indicator light 3 is turned off, so that no sound is received, the single-chip microcomputer 2 immediately executes required processing, and transmits necessary information to the computer 20 from the input / output port 21. You.

After the single-chip microcomputer 2 completes the processing of one command cycle, a command is transmitted at a regular time, the identification indicator 3 is turned on, and the next voice command is received.

When the user uses it for the first time, in addition to the voice recognition mode, a “key replacement mode” can be selected, the purpose of which is that some products may have more than one button, The key (button) function can be replaced by the command. That is, after all the settings are completed, the function of pressing the button with the finger by the user making a sound can be replaced. The operation method of the key replacement mode is as described below. That is, when the user uses the product for the first time, the user presses the recording function key 4 and other buttons that need to be replaced, and the single-chip microcomputer 2 automatically identifies the function of the button. The voice command is replaced by voice, a command signal is transmitted, and the voice command input by the user is stored in the signal storage means 13 of the corresponding address. In such a case, when the identification indicator lamp 3 is turned on, the user can sequentially input voice commands one after another, and the subsequent operation is the same as the operation method in the voice identification mode.

FIG. 2 shows a case where the voice control identification device is built in a keyboard.

The large manufacturers at hand all add a large number of special function keys to the standard keyboard, and also benefit from the use of the functions of the user's computer according to certain drivers. For example, pressing a key immediately goes online and opens the mailbox. When the voice control identification device is built in the keyboard, the purpose of humanization operation can be achieved.

When the user uses the keyboard 7 for the first time, a voice sample can be recorded by simultaneously pressing the recording function key 4 and any of the function keys (F1 to F12) 5. The user can perform the recording at will. After recording the voice sample, the keyboard 7 automatically enters the voice recognition mode. At this time, if the user utters the same voice as the voice sample, the keyboard 7 automatically operates and the hot key ( It is the same as pressing the function key). In such a case, the voice input replaces all the functions of the function keys, and can be used for humanization.

Further, the user can change the corresponding function of the function key by changing the driver function attached to the keyboard 7 by himself, the user can record a voice sample at any time again, and can change all the function keys. Capable of function.

In the case of FIG. 3, a recording function key 4 and an identification indicator 3 are added to a keyboard 7 having function keys, and when the user uses the keyboard 7 for the first time, the recording function key 4 is depressed in order. The required voice samples can be recorded and if the keyboard 7 is restored to the identification mode, the keyboard 7 can be commanded by voice to operate.

As shown in FIGS. 4 to 6, the present invention can introduce a recording function key 4 and an identification indicator 3 into products such as a remote controller 8, a mouse 9, and a display device 10, so that a user can use it first. If the recording function key 4 is pressed, the required audio samples can be recorded in sequence, and when the product is restored to the identification mode, the product can be commanded by voice to operate. On the other hand, the single-chip microcomputer 2 can transmit different corresponding information to the computer 20 according to the product difference.

[0025]

[Effect of the invention]

 As described above, the design of the present invention can provide a humanized processing interface, is low in cost, and can add new vitality to other products. Is not found in products.

[Brief description of the drawings]

FIG. 1 is a block diagram showing an electric circuit in a voice recognition mode of the present invention.

FIG. 2 is an external view showing a case where the present invention is applied to a keyboard.

FIG. 3 is another external view showing a case where the present invention is applied to a keyboard.

FIG. 4 is an external view showing a case where the present invention is applied to a remote controller.

FIG. 5 is an external view showing a case where the present invention is applied to a mouse.

FIG. 6 is an external view showing a case where the present invention is applied to a display device.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Voice identification unit 11 Microphone enlargement means 12 Signal conversion means 13 Signal storage means 14 Voice processing means 2 Single chip microcomputer 21 I / O port 20 Computer 3 Identification indicator 4 Recording function key 5 Function key 6 Microphone 7 Keyboard 8 Remote control 9 Mouse 10 Display device

Claims (3)

[Utility model registration claims] 1. A voice control identification device used for various computer peripheral equipment or information processing products, wherein a sound source and an input sound source are enlarged and converted into digital information, and the obtained information is stored in advance. A voice control identification unit for comparing with information and transmitting an error signal or an enable signal; a command signal end connected to an input port of the voice control identification unit; and an enable connected to an output port of the voice control identification unit. A signal terminal for performing the next processing according to the signal of the voice control identification unit, transmitting information to the computer, or receiving a next voice command by transmitting a command signal to the voice control identification unit 1. Connected to the chip microcomputer and the single chip microcomputer A sound function key, and an identification indicator light connected to the output port of the voice control identification unit and illuminated when the recording function key is pressed, so that the user can make a sound by using the computer peripheral equipment or home use. An audio control identification device characterized by forming a configuration for controlling an information product. 2. A microphone expansion means for expanding an input sound source signal; a signal conversion means connected to an output terminal of the microphone expansion means for converting a signal output from the microphone expansion means into a digital signal; A signal storage means connected to the output end of the single-chip microcomputer, the signal storage means being configured to store the digital signal output by the signal conversion means, being connected to the output end of the signal conversion means, being connected to the signal storage means, It is connected to the command signal terminal, and the output terminal is connected to the identification signal light and the enable signal terminal of the single-chip microcomputer, respectively, compares the digital information with the preset information, and outputs the error signal or enable signal to the single-chip microcomputer. Audio processing that performs the following processing by transmitting a signal 2. The voice control identification device according to claim 1, further comprising a control unit. 3. The voice control identification device according to claim 1, wherein the recording function key and the identification indicator are provided at the same time or respectively on computer peripheral equipment.