JP2002006881A - Controller based on voice recognition - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent a serious malfunction from being caused by erroneous voice recognition. SOLUTION: A controller is provided with a switching means which switches vocabulary as the voice recognition object to general vocabulary 5b and vocabulary 5c for confirmation and a discrimination means which discriminates whether a control command obtained by performing voice recognition with general vocabulary 5b as the object may cause a serious malfunction or not. When a control command which may cause a serious malfunction is obtained, a message prompting a speech for confirmation is outputted, and vocabulary as the voice recognition object is switched to vocabulary 5c for confirmation, and the confirmed control command is executed only when a voice prompting execution is confirmed.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a control device using voice recognition, and more particularly to a control device for preventing a serious malfunction from occurring due to a voice recognition error.

[0002]

2. Description of the Related Art FIG. 3 shows an example of a conventional voice recognition apparatus for recognizing a command by voice and controlling the apparatus.
Audio input to the microphone 1 shown in the figure is converted into an electric signal, amplified by the amplifier 2, and converted into a digital signal by the A / D converter 3.

[0003] The digital signal is input to a microcomputer 4 and compared with a voice pattern stored in a memory 5 to recognize the input voice. A device (not shown) is controlled by the voice command thus recognized.

The operation of the above speech recognition apparatus will be described with reference to FIG. When the voice recognition software is started, first, in step S20, it is determined whether or not a voice is input, and when the voice is input, the process proceeds to step S21. In step S21, a voice recognition process is performed by comparing the voice pattern stored in the memory 5 with the input voice pattern, and then another device is controlled by the command obtained in step S22. The voice recognition operation ends.

[0005]

In speech recognition, erroneous recognition occurs in any system due to the wide range of input speech. Controlling the device with erroneously recognized speech can have serious adverse effects on the device.

SUMMARY OF THE INVENTION The present invention has been made in view of the above points, and an object of the present invention is to reduce the probability of erroneous speech recognition when a serious malfunction may occur due to an error in speech recognition. It is an object of the present invention to provide a control device by voice recognition which can confirm whether or not the control operation can be performed correctly.

[0007]

According to the present invention, there is provided a control apparatus for speech recognition, comprising: switching means for switching a vocabulary targeted for speech recognition between a general vocabulary and a confirmed vocabulary; and performing speech recognition targeting a general vocabulary. Determining means for determining whether or not the obtained control command is a control command that may cause a serious malfunction, and confirming when a control command that may cause a serious malfunction is obtained. The system is configured to output a message prompting pronunciation for use, switch a vocabulary targeted for voice recognition to a confirmation vocabulary, and execute the confirmed control command only when a voice prompting execution is confirmed.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A speech recognition apparatus according to an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a speech recognition apparatus according to an embodiment of the present invention. Audio input to the microphone 1 shown in the figure is converted into an electric signal, amplified by the amplifier 2, and converted into a digital signal by the A / D converter 3.

The digital signal is input to the microcomputer 4 and is compared with a voice pattern stored in the dictionary memory 5a to recognize the input voice.
A device (not shown) is controlled by the voice-recognized command. The dictionary memory 5a includes a general vocabulary memory 5
The vocabulary pattern stored in either the “b” or the operation confirmation vocabulary memory 5c is loaded.

The operation of the speech recognition apparatus will be described with reference to FIG. First, when the apparatus is started, in step S1, the contents of the general vocabulary memory 5b are stored in the dictionary memory 5b.
a and the process proceeds to step S2.

In step S2, step S2 is repeated until a voice is input.
Move to 3. In step S3, the input voice pattern is compared with the general vocabulary pattern, and a voice recognition process is performed.

In step S4, it is determined whether or not the recognized voice command is intended for malfunction prevention, and if not, the process proceeds to step S10.
If there is a malfunction prevention target, the process proceeds to step S5.

In step S5, the operation confirmation vocabulary memory 5
The content of c is loaded into the dictionary memory 5a, and step S6
Move to In step S6, a message asking the speaker whether to execute the recognized command is transmitted, and the process proceeds to step S7 (not shown, but the apparatus is provided with a speech synthesizer and a speaker).

In step S7, step S7 is repeated until a voice is input.
Move to 8. In step S8, the input voice pattern is compared with the operation confirmation vocabulary pattern, and a voice recognition process is executed, and the process proceeds to step S9.

In step S9, it is determined whether or not the recognized voice is one that affirms execution. If it is affirmative, the process proceeds to step S10, and if it is denied, the process proceeds to step S1.

In step S10, the apparatus is controlled by the recognized voice command, and this routine ends.

When there is a possibility that the command obtained by the voice recognition may cause a serious malfunction, check with the speaker and compare the voice generated by the speaker with a limited number of vocabulary words. Since recognition is performed, the possibility of erroneous recognition is extremely small, and occurrence of serious malfunction is prevented.

[0018]

According to the control apparatus using voice recognition of the present invention, a serious malfunction due to erroneous voice recognition is prevented.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a speech recognition apparatus according to an embodiment of the present invention.

FIG. 2 is a flowchart showing an operation of the voice recognition device.

FIG. 3 is a block diagram illustrating an example of a conventional voice recognition device.

FIG. 4 is a flowchart showing an operation of the voice recognition device.

[Explanation of symbols]

Reference Signs List 1 microphone 2 amplifier 3 A / D converter 4 microcomputer 5 memory, 5a dictionary memory, 5b general vocabulary memory 5c operation confirmation vocabulary memory

Claims (1)

[Claims] 1. A switching means for switching a vocabulary for speech recognition between a general vocabulary and a confirmation vocabulary, and a control command obtained by performing speech recognition on a general vocabulary may cause a serious malfunction. Judgment means for judging whether the command is a certain control command, and when a control command that may cause a serious malfunction is obtained, outputs a message prompting a sound for confirmation and performs speech recognition. A speech recognition control device configured to switch a vocabulary to be confirmed to a confirmation vocabulary and execute the confirmed control command only when a voice prompting execution is confirmed.