JPS60215287A - Character recognizing system - Google Patents

Abstract

PURPOSE:To use both visual and manual capacities of an operator exclusively to input of characters and to increase the input speed of character information, by entrusting the aural system of the operator with confirmation for input of characters of an information processor. CONSTITUTION:When an operator supplies characters through a character input board 1, the pattern of input characters is recognized by a character recognition device 3. The signals corresponding to the recognized characters are produced, and the voice signals corresponding to said produced signals are produced by a voice response device 4 with voice. Then the pronunciation corresponding to the input characters are transmitted to the operator via an electroacoustic transducer 5. The operator supplies an affirmative word such as ''yes'' to a speech recognition device 7 via an acoustic-electric transducer 6 in case the heard voice is coincident with the pronunciations of input characters. The recognition device 7 applies signals to the recognizer 3 based on the input of said affirmative word. Then the characters recognized by the recognition device 3 are fixed. Thus it is possible to deliver signals corresponding to input character signals to an external device from the recognition device 3.

Description

DETAILED DESCRIPTION OF THE INVENTION [Technical field to which the invention pertains] The present invention relates to an improvement in a method for recognizing character input to an information processing device.

[Description of prior art]

FIG. 1 is a block configuration diagram showing the configuration of a conventional system. In this conventional method, character information input on the character input board 1 is recognized by the character recognition device 3, and the result is displayed on a character pattern display device (hereinafter referred to as a display device). The character input operator (hereinafter referred to as the operator) visually compares this display with the input character information source (hereinafter referred to as the information source), and also selects keys on the auxiliary keyboard 2 depending on the quality of the result. Requires operation.

Therefore, there is a drawback in that there is a limit to the improvement in character input speed due to operations that depend on the operator's visual observation and key operations that depend on the quality of the result in addition to character input. Also,
This has the disadvantage that the operator's eyes become tired and cannot be used for a long period of time.

[Purpose of the invention]

SUMMARY OF THE INVENTION The present invention aims to eliminate the above-mentioned drawbacks, and provides a character recognition system in which the auditory senses are substituted for manual and visual character input results comparison and confirmation operations.

[Features of the invention]

The present invention includes a character input board for inputting characters as shapes, a means for inputting an operator's intention, and a dictionary in which a large number of characters are stored. The characters in the box are selected and displayed in order from the most likely to the most likely, and when there is a negative input in the means for inputting the intention indication, the next most likely character is displayed, and when there is an affirmative input in that means, the next most likely character is displayed. In a character recognition system comprising a character recognition device that performs character recognition by confirming the selected and displayed character, the character recognition device is equipped with means for audibly displaying the character with a high probability, and the character recognition device The means for inputting a display is characterized in that it includes means for identifying at least two types of the operator's voice: affirmative or negative.

[Explanation based on examples]

Hereinafter, an embodiment of the present invention will be explained based on the drawings.

FIG. 2 is a block configuration diagram showing the configuration of this embodiment system. First, the configuration of this embodiment system will be explained based on FIG. 2. This embodiment system includes a character input board 1, a character recognition device 3, a voice response device 4, an electroacoustic transducer 5,
Consisting of an acousto-electrical transducer 6 and a voice recognition device 7, the output of the character recognition device 1 is connected to the first input of the character recognition device 3, and the output of the character recognition device 3 is connected to the input of the voice response device 4. The output of the voice response device 4 is connected to the input of the electroacoustic transducer 5, and the input of the acoustoelectric transducer 6 is connected to the input of the voice recognition device 7, and the output of the voice recognition device 7 is connected to the input of the electroacoustic transducer 5. Connected to the second input of device 3. This character recognition device 3 is equipped with a dictionary in which a large number of characters are stored in advance, and the characters in the dictionary are displayed to the operator one by one, and the character that the operator confirms is confirmed as the recognized character. It is configured.

Next, the operation of this embodiment device will be explained based on FIG. 2. When the operator inputs a character on the character input panel 1, the character recognition device 3 executes input character Φ pattern recognition, generates a signal corresponding to the recognized character, and generates an audio signal corresponding to this signal. The voice response device 4 generates the pronunciation that corresponds to the input character, and transmits the pronunciation corresponding to the input character to the operator via the electroacoustic transducer 5. If the voice heard matches the pronunciation of the characters input, the operator selects the affirmative word (
For example, "Yes") is input to the voice recognition device 7 via the acoustoelectric transducer 6, the voice recognition device W7 gives a signal to the character recognition device 3 based on this input, and the character recognized by this device is Once determined, a signal corresponding to the input character signal can be output from the character recognition bag W3 to an external device.

On the other hand, if the heard voice does not match the pronunciation of the input character, the operator can use a negative word (for example, "
”) through an acoustoelectric transducer 6 and a speech recognition device 7
, the pronunciation corresponding to the next pronunciation information stored in the voice response device 4 is transmitted to the operator via the acousto-electric transducer 6. This process is repeated.

〔Effect of the invention〕

As explained above, by entrusting the confirmation process of character input to the information processing device to the operator's auditory system, the operator's visual and manual operation abilities can be dedicated to character input, so This has the effect of improving the input speed of information to the information processing device. Furthermore, since the operator does not need to keep looking at the screen, there is an advantage that the operator can operate for a long time without tiring his eyes. This effect is particularly noticeable when the input characters are handwritten characters. Furthermore, this method works effectively when inputting characters that are homophones.

[Brief explanation of the drawing]

FIG. 1 is a block configuration diagram showing the configuration of a conventional system. FIG. 2 is a block configuration diagram showing the configuration of the system according to the embodiment of the present invention. ■...Character input board, 2...Auxiliary keyboard, 3...Character recognition device, 4...Voice response device, 5...Electroacoustic transducer, 6...Acoustic electric transducer, 7 ...Voice recognition device 8...Display device. Patent Applicant NEC Corporation Representative Patent Attorney Nao Takashi Ide M Figure 2

Claims (1)

[Scope of Claims] tit A character input board for inputting characters as shapes, a means for inputting an operator's intention, and a dictionary storing a large number of characters, with respect to the characters input to the character input board. The characters in the dictionary are selected and displayed in order from the most likely to the most likely, and when there is a negative input in the means for inputting the above intention indication, the next most likely character is displayed, and when an affirmative input is input in that means. In a character recognition method comprising a character recognition device that performs character recognition by confirming the selected and displayed character in some cases, the character recognition device is equipped with means for audibly displaying the character with a high probability, A character recognition system characterized in that the means for inputting the operator's intention expression includes means for identifying at least two types of the operator's voice, affirmative or negative.