JPH04308923A - Voice inputting device - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice input device.

0002

2. Description of the Related Art Voice input devices are considered to be very efficient means of inputting information. However, voice input devices have not yet become a common means of inputting information. The reason for this is that conventional methods have very important problems.

That is, in the conventional technology, when using a voice input device, it was necessary to prepare in advance hardware including the voice input device and application software that can handle voice input. However, it is clear that this is a very large limitation. In other words, there is a shortage of hardware that can handle voice input, and acquiring new hardware requires a very large investment in hardware. If that happens, I won't use it because I don't have the hardware. A cycle often forms where people don't buy hardware because they don't use it.

[0004] An even more problematic problem is that there is a critical shortage of application software that can handle speech recognition. In conventional technology, when attempting to handle voice recognition, it was necessary to handle it on the application software side. Unfortunately, creating software requires significantly more human investment than creating hardware. Therefore, it is practically impossible to create software compatible with hardware that has a low penetration rate.

[0005] Furthermore, even if conventional software were to be rewritten to support voice recognition input, if the method of using the software changed as a result, this would be a major factor in the user's rejection of the software.

[0006] In addition to the above-mentioned problems, a problem with the speech recognition technology itself is that it is difficult to extract speech sections even in the noise of a normal office environment. Furthermore, since speech recognition processing requires a considerable amount of computer resources, keeping it running all the time may have an adverse effect on other processing.

[0007] In other words, in the conventional technology, as mentioned above, there are many problems in terms of hardware and software, and even if all of these problems were solved, it would still be difficult to use It has been extremely difficult in the prior art to create an environment where it is easy to do so.

[0008]

[Problem to be Solved by the Invention] The problem to be solved by the present invention is as described above. In other words, when attempting to use a speech recognition device in the conventional technology, a dedicated computer is required to use it. A system and application software compatible with speech recognition are required, and furthermore, even if these are used, it is difficult to extract speech sections. An object of the present invention is to solve the above problems by simply adding a minimum amount of audio input hardware to existing hardware, and which can be used without changing existing application software.
Another object of the present invention is to realize a voice input device that allows a user to easily select voice input and key input.

[0009]

Means for Solving the Problems FIG. 1 is a schematic diagram of the concept of the present invention. To explain the present invention using FIG. 1, the present invention comprises: 1. a keyboard 1; 2. a key code input means 2 for inputting a key code generated by the keyboard 1; and 3. a key input by the keyboard 2. voice input selection code detection means 3 and 4 for detecting the voice input selection code from the code;
, voice input means 4; voice recognition means 5 which receives the output of the voice input means 5, 4; key code generation means 6 which receives the results of the voice recognition means 6, 5; and 7, 2. Audio input consisting of a key code input means, an input/output selection means 7 for selecting one of the key code generation means 6, and a key code output means 8 for outputting the key code selected by 8 and 7. It is a device.

0010

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a schematic illustration of the concept of the present invention. Moreover, FIG. 2 is an outline of the processing in the present invention. The present invention will be explained in detail below using these two figures.

[0011] Many computers currently in use have a keyboard independent of the main body. Furthermore, the keyboard has a CPU independent from the main body, scans the keyboard, performs processing according to the pressed keys according to a program, and communicates the results with the computer main body.

The present invention realizes a speech recognition device using hardware and software connected to the keyboard and the communication line of the main body. Of course, the connection to this communication line does not have to be a physical connection, and may be a software connection via a keyboard device driver of the computer itself.

The operation of the present invention will be explained using FIGS. 1 and 2. First, register the voice input selection character code in advance. This character code may be a non-printing character, such as a control character. Thereafter, the character code input from the keyboard 1 is sent to the voice input selection code detection means 3 via the key code input means 2. If the input code is not a voice input selection code, the character code is sent to the key code output means 8 via the input/output selection means 7, and thereby to the computer main body 9. This process is exactly the same as when the keyboard is directly connected to the computer.

If the character code sent to the voice input selection means 3 is a voice input selection character code, that character code itself is discarded, and as a side effect, the voice input means 4 and the voice recognition means 5 The key code generation means 6 is activated.

In this state, voice is input from the voice input means 4, and the input voice is recognized by the voice recognition means 5. Then, a key code corresponding to the recognition result is generated by the key code generating means 6.
For example, suppose your computer is running word processing software and you need to enter your address into it. At this time, if you press the key corresponding to the voice input selection code character on the keyboard and input ``address'' into the voice input means, the corresponding character code string, for example ``3-3-5 Yamato, Suwa City, Nagano Prefecture,'' will be displayed. ”
A key code corresponding to a character string such as ``etc'' is generated. Thereafter, the key code is sent via the input/output selection means 7 to the key code output means 8, and thereby to the computer main body 9. In the word processing software running on the computer at this time, there is no means to distinguish whether the input key code string is input from the keyboard or the result of voice input. On the contrary, this means that there is no need to modify the software running on the computer itself.

[0016] To give another example of operation, many of the recent software are operated by menu selection. However, as software becomes more sophisticated, it is often necessary to make preliminary selections from several menus before reaching the desired menu. but,
For people who are accustomed to keyboard operations, using a mouse or the like and the large movement of the line of sight will increase fatigue. To avoid this, a control string corresponding to the operation is often defined. However, when the number of functions increases, or when multiple pieces of software are used, operations often become inconsistent and confusion occurs.

This problem can be solved using the present invention. For example, assume that the control character string "ABC" corresponds to the operation of opening a new window. Then, when the voice says "window", the character string "A"
It is assumed that the generation of "BC" is made compatible. In that setting, hold down the voice input selection code character on the keyboard and press "
If you say ``Window'', a control string ``ABC'' will be generated, which is the same as inputting it from the keyboard. Alternatively, it is the same as selecting "A", "B", and "C" sequentially using the mouse.

[0018]

As described above, according to the present invention, audio input can be made possible by simply adding the minimum amount of audio input/output hardware to existing hardware.
Furthermore, there is no need to modify existing application software.

[0019] Furthermore, the user can easily switch between voice input and keyboard input, no errors in segmentation of speech sections occur, and the load on computer resources is extremely small.

In the present invention, the additional hardware and software parts of the present invention do not need to be independent from the computer main body. This can also be implemented as a software keyboard device driver program using hardware included in the computer itself.

[Brief explanation of drawings]

FIG. 1 is a schematic diagram of the concept of the configuration of the present invention.

FIG. 2 is a flowchart showing a schematic algorithm of processing of the present invention.

[Explanation of symbols]

1: Keyboard 2: Key code input means 3: Audio input selection means 4: Voice input means 5: Voice recognition means 6: Key code generation means 7: Input/output selection means 8: Key code output means 9: Computer

Claims (1)

[Claims] Claims 1: 1. A keyboard; 2. Key code input means for inputting a key code generated by the keyboard in 1; and 3. Voice input for detecting a voice input selection code from the key code input in 2. selection code detection means; 4;
voice input means; voice recognition means which inputs the output of the voice input means 5 and 4; key code generation means which inputs the results of the voice recognition means 6 and 5; and key code input means 7 and 2. , an input/output selection means for selecting one of the key code generation means of 6, and a key code output means for outputting the key code selected by 8 and 7. .