JPS6149716B2 - - Google Patents

Description

[Detailed description of the invention] The present invention relates to an electronic translation machine.

Note that in this specification, translation refers not only to converting the language of one country into the language of another country, but also to converting letters and symbols into sounds, or sounds into letters and symbols in the language of the same country. Therefore, converting a dialect into a standard language even if the language is from the same country, and vice versa, is called translation, and it also includes calculations.

The source language refers to the language before translation, and the translated language refers to the language after translation. For example, in a Japanese-English electronic translator, "Good morning" is in the original language,
"GOOD MORNING" is a translation language.

Conventional voice input/output type electronic translators have the disadvantage that accurate translation cannot be performed because the voice input microphone is always active.

The present invention eliminates such drawbacks and provides an electronic translator capable of highly accurate translation.

An embodiment of the present invention will be described below with reference to FIGS. 1 and 2.

FIG. 1 is a block diagram of an electronic translation machine which is an embodiment of the present invention, and FIG. 2 is a timing chart showing the operating state of an input permission indicator lamp of the same machine.

In the figure, reference numeral 1 denotes a microphone for voice input, which is connected to a voice analysis recognition circuit (hereinafter referred to as SA) 2 via a switch (hereinafter referred to as SW) S1. The SA 2 is connected to a speaker 5 via a Japanese-English electronic translation circuit (hereinafter referred to as TI) 3 and a speech synthesis circuit (hereinafter referred to as SM) 4.
TI3 is connected to an input permission indicator lamp (hereinafter referred to as LED) 7 via an input limiting circuit (hereinafter referred to as CT) 6 that switches SWS1 to contact S1b and SWS2 to contact S2b during the translation language output signal transmission time. There is.

SWS1 and SWS2 are interlocked, with constant contact S1a,
Each is connected to S2a.

Next, the operation of this device will be explained.

First, both SWS1 and SWS2 have contacts S1a and S
Consider the case where conduction occurs to 2a.

At this time, the LED 7 lights up to notify the operator (not shown) that translation is possible.

After confirming that LED 7 is lit, the operator says "I'm Tom" into microphone 1 as shown in Figure 2A, and this audio signal (original language) is
It is applied to SA2 via SWS1, and after being converted into a character signal (original language) "Watashiwatomudes", TI
3 is applied.

TI3 translates this into an English character signal (translation language) "I AM TOM", and converts it into an audio signal (translation language) "I AM TOM" in SM4 and applies it to speaker 5.

While the output signal of the translation language "I AM TOM" is being sent from TI3 (Figure 2B), CT6 is
Both SWS1 and SWS2 are switched to contacts S1b and S2b, and LED7 is turned off as shown in FIG. 2c. Therefore, the operator knows that the LED 7 is off, and knows that translation is in progress, and knows that the original language cannot be applied to the microphone 1.

Of course, at this time, since the SWS1 is electrically connected to the contact S1b, the translated language "I am Tom" from the speaker 5 will not be translated again.

The same operation is repeated below.

In this embodiment, the LED 7 is used as a warning means, but the warning means is not limited to this, and a buzzer or the like may be used. Also, in this example, an example was shown in which SM4 voice synthesis is instantaneous, but if it takes more than 0.5 seconds,
Install a delay circuit in CT6 or use SM4
Just connect CT6.

In addition, in this specification, a warning that input is not possible is as follows:
It also includes things like:

A. If the warning means is a visible display means; a. Turning off a lamp, etc., which lights up when input is possible and turns off when input is not possible.

b. Lighting of lamps, etc., which turn off when input is possible and turn on when input is not possible.

c. Turning on the red lamp or changing color to red when the blue lamp etc. lights up when input is possible and the red lamp etc. lights up when input is not possible.

d) Display of marks, symbols, characters, etc. when nothing is displayed when input is possible, and specific marks, symbols, characters, etc. are displayed when input is not possible.

e No display, where a specific mark, symbol, character, etc. is displayed when input is possible, and nothing is displayed when input is disabled.

B. If the warning means is an audible sounding means; a. It is emitted for a short period of time at least when switching from an input enabled state to an input disabled state, or when switching from an input disabled state to an input enabled state. Sounds (beep, pop, etc.).

b Silence when input is possible, and a sound (continuous or discontinuous) that is emitted when input is disabled.

In addition, warnings that can be entered include lamps turning off, turning on, discoloring, marks,
This includes the display, non-display, and pronunciation of symbols and characters.

As described above, according to the present embodiment, in an electronic translation machine in which a microphone and a speaker are arranged at a distance such that synthesized speech outputted from a speaker is recognized through the microphone, speech information inputted by the microphone is used. an input blocking means for preventing input of voice input into the electronic translation means; a warning means for warning whether voice input is possible or not in synchronization with the input blocking means; Detects the period corresponding to the period when the input voice information is output, and automatically activates the input blocking means during that period to prevent the input voice information from being translated, and synchronously warns that voice input is not possible. By providing an input control means for activating a warning means so as to emit a warning means, the problem that the voice information in the translated language outputted from the speaker is inputted again through the microphone and retranslated is completely eliminated. At the same time, the speaker does not have to operate any keys, foot switches, etc. by simply saying the source language to be translated into the microphone in accordance with the warning from the warning means that operates in synchronization with the input blocking means. Accurate translations can be easily obtained without the need for

As described above, according to the present invention, there is provided an input blocking means for preventing the speech information inputted to the speech information inputting means from being translated by the electronic translation means, and an input blocking means for preventing the speech information inputted to the speech information inputting means from being translated by the electronic translation means; A warning means for giving a warning, and an input control means for automatically activating the input blocking means while the electronic translation means is executing a translation operation and synchronizing the warning means with the input blocking means to give a warning. Therefore, unnecessary voices are input to the electronic translation means through the voice recognition means during translation, and mixed with the necessary information to be translated, resulting in mistranslation, can be avoided without operating the key switch, foot switch, etc. It can be prevented automatically and reliably, and anyone can do it without any effort, force, or attentiveness by simply seeing and talking about the warning that is issued in synchronization with the warning (for example, the lighting of a lamp). You can obtain efficient and accurate translations.

In addition, in devices where the speaker manually blocks input after seeing a warning display, there is a delay in the timing of the speaker's input blocking operation (because the speaker manually operates the switch after seeing the warning display, it is inevitable that translation will start). The speaker/operator must always pay close attention to the warning display, which causes a burden on the speaker. This would greatly reduce the value of the voice input method, which was originally supposed to reduce the burden on the speaker (operator) and improve input efficiency.

In contrast, in the present invention, input is blocked accurately and automatically during the period from the start to the end of translation, and a warning display is displayed synchronously during the input block period, so the speaker does not need to perform any manual operations. First, voice input can be performed easily according to the warning display, and anyone can efficiently perform accurate translations, thereby fully utilizing the merits of the voice input method.

Note that synchronization in this specification includes not only synchronization in the strict sense but also nearly synchronization and following with a slight delay.

[Brief explanation of the drawing]

FIG. 1 is a block diagram of an electronic translation machine which is an embodiment of the present invention, and FIG. 2 is a timing chart showing the operating state of an input permission indicator lamp of the same machine. 1...Microphone, 2...Speech analysis recognition circuit (SA), 3...Japanese-English electronic translation circuit (TI), 4...
...Speech synthesis circuit (SM), 5...Speaker, 6...
Input restriction circuit (CT), 7... Input permission indicator lamp (LED), S1, S2... Switch (SW), 13
...Character display circuit (LCD).

Claims (1)

[Scope of Claims] 1. Speech information input means for inputting speech information related to the source language to be translated; speech recognition means for recognizing the speech information related to the source language to be translated inputted to the speech information input means; electronic translation means for translating into information on the corresponding translation language based on information on the source language recognized by the voice recognition means; information output means for outputting information on the translation language translated by the electronic translation means; input blocking means for preventing the voice information input to the voice information input means from being input to the electronic translation means via the voice recognition means; input of voice information to the voice information input means;
or a warning means for warning that the electronic translation means is not acceptable; and while the electronic translation means is performing a translation operation, the input blocking means is automatically operated to block the input, and the warning means is synchronized with the input blocking means. An electronic translation device comprising an input control means for automatically issuing a warning. 2. The electronic translation means includes an electronic translation unit that translates information regarding the source language recognized by the voice recognition means into information regarding the corresponding translation language;
speech synthesis means for synthesizing speech information about the translation language corresponding thereto based on information about the translation language translated by the electronic translation section; and the information output means synthesizes speech information about the translation language synthesized by the speech synthesis means. is an audio information output means for outputting audio information related to Detecting a period during which audio information is being output to the warning means, automatically operating an input blocking means during both of the periods, and enabling or disabling the input of audio information to the warning means in synchronization with the input blocking means. The electronic translation machine according to claim 1, wherein the electronic translation machine issues a warning. 3. The electronic translator according to claim 1 or 2, wherein the warning means is a visible display means or an audible sounding means. 4. The voice information output means is a speaker, and the voice information input means is a microphone, and the microphone is placed at a distance such that the synthesized voice output from the speaker is input to the voice recognition means via the microphone. 3. The electronic translator according to claim 2, wherein said speaker is provided, and said warning means is a visible display means or an audible sounding means.