JPS60191329A - Voice input device - Google Patents

Abstract

PURPOSE:To recognize quickly the voice and to improve the working efficiency for input of voice by using a means for input of information on the paragraphs, the sentence ends, etc. in terms of voice. CONSTITUTION:A ROM2 and a RAM3 are connected to a central processor CPU1 which controls totally a voice input device. While a mike 7 is connected to the CPU1. The mike 7 includes a sentence head switch 4, a sentence end switch 5 and a paragraph switch 6. The CPU1 discriminates the ON or OFF operations of switches 4-6. Then the voice can be quickly recognized. In this way, the working efficiency for input of voice is improved.

Description

DETAILED DESCRIPTION OF THE INVENTION (Technical Field) The present invention relates to a voice input device, and particularly to a voice input device that can input information related to voice, such as phrases and endings of sentences.

(Prior Art) In general, speech input devices usually recognize information related to speech, such as clauses and end of sentences, based on the time interval of pronunciation by the person inputting the speech. However, since the voice inputter inputs voice while keeping in mind the time interval between pronunciations, it becomes inconvenient to handle if there is a large amount of information to be input. Therefore, the conventional method has had the disadvantage of requiring a skilled and dedicated voice input person.

(Purpose) The present invention has been made in view of the above points, and is to input speech-related information such as clauses and end of sentences more quickly and reliably than recognition based on the time interval of pronunciation by a speech inputter. It is an object of the present invention to provide a voice input device that can improve the recognition rate.

(Example) Hereinafter, one embodiment of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram showing the configuration of the voice input device of the present invention, where l is a central processing unit (hereinafter referred to as CPU) that controls the entire device, and 2 is an RO that stores a control program.
M, 3 is a RAM as a storage device such as registers for flags and calculations; 4 is a sentence beginning switch operated by the voice input person when the input voice information is at the beginning of a sentence; 5 is a switch at the end of a sentence regarding the input voice information. Reference numeral 6 denotes a sentence-end switch that is operated by the voice inputter when the inputted voice information is a phrase, and 7 is a microphone for inputting the voice information. This microphone 7 is equipped with the above-mentioned sentence beginning switch 4, sentence end switch 5, and phrase switch 6, as shown in FIG.

Next, the operation of the voice input device configured as described above will be explained with reference to the flow shown in FIG.

In FIG. 3, first, from "Start", the process moves to step Sl to determine whether or not the sentence beginning switch 4 has been operated. Step Sl is repeated until the sentence beginning switch 4 is turned on. When the sentence beginning switch 4 is turned on, the process proceeds to step S2 to determine whether the sentence end switch 5 has been operated. When the end-of-sentence switch 51 and clause switch 6 are both off, the audio input from the microphone 7 is taken as an "input signal" in step S4. Sentence end switch 5 is off, clause switch 6
When it is on, the process goes to step S5, and the "phrase signal" indicating the phrase is set as the "input signal." Step S4 or Step S5 described above until the sentence end switch 5 is turned on.
repeat. When the sentence end switch 5 is turned on, step S
The process moves to step 6, where it is determined as a "sentence end signal" or an "input signal", and the process returns to step Sl.

The "input signals" are set in the RAM 3, and the CPU performs voice recognition processing based on these input signals.

In addition, in the embodiment mentioned above, the switches for inputting information related to speech include a sentence beginning switch, a sentence end switch,
Although the phrase switch has been described, the microphone 7 may be further provided with a sentence cancel switch for canceling an input sentence, a phrase cancel switch for canceling an input phrase, etc. in addition to these switches.

Furthermore, in the second embodiment, a case has been described in which the switch for inputting audio-related information is attached to the microphone 7, but another type of switch, for example a dedicated keyboard, may be provided separately.

(Effects) As described above, according to the present invention, information related to speech, such as phrases and end of sentences, is input in addition to speech input, so speech can be recognized quickly and reliably. , voice input work can be done efficiently.

[Brief explanation of drawings]

Fig. 1 is a block diagram showing the configuration of an audio input device that is an embodiment of the present invention, Fig. 2 is a detailed diagram of the microphone shown in Fig. 1, and Fig. 3 explains the operation of the embodiment of Fig. 1. This is a flowchart for ■---Central processing unit, 2---ROM, 3---RA
M, 4-m-sentence beginning switch, 5-m-sentence end switch, 6
--- Clause Switch, 7 --- Mike. Applicant Canon Co., Ltd.

Claims (1)

[Scope of Claims] A voice input device for recognizing information inputted by voice, characterized in that the voice input device is provided with means for inputting information such as a phrase, the end of a sentence, etc. related to the voice.