JPH08278972A - Speech input translation device - Google Patents

Abstract

PURPOSE: To display a translated language in the direction opposite to display of the original language. CONSTITUTION: This is a portable speech input translation device 1 which allows persons who talk face to face to easily read character strings in optional languages by displaying the speech-inputted character string in the original language and its translated character character string at display parts such as liquid crystal display panels 2 and 3 in mutually opposite directions. For example, speech input operation keys for the 1st and 2nd languages are provided in mutually opposite directions and paragraphs corresponding to the 1st and 2nd languages are displayed on the liquid crystal panels 2 and 3 in the mutually opposite directions to improve the operability of electronic conversation.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a portable voice input / translation device for converting a voice signal input in one language into another language and outputting the voice, and particularly to a certain original language character and its original character. The present invention relates to a portable voice input translation device which is convenient for conversation in an overseas travel destination or the like and has a function of displaying translated language characters obtained by translating a language on a display device in a direction in which interlocutors can easily see each other.

[0002]

2. Description of the Related Art In a conventional portable translation device, an operator selects from a plurality of keywords in an original language displayed on a display device an item having a content that matches a conversation desired by the operator. There has been a format in which a desired conversational phrase is extracted through several steps and the resulting conversational phrase is translated into another language. There is a portable translation device that displays the characters of the translated translation on a display panel device such as a liquid crystal display.

However, in the above translation apparatus, when people using different languages interact with each other using this common portable translation apparatus, the bunsetsu characters and translated bunsetsu characters of the original languages of these languages are translated. There was no function for the interlocutors to visually confirm on the display device at the same time in directions and states that were easy for the interlocutors to see each other, and the dialogue between the interlocutors did not go smoothly.

An example of a conventional portable speech translation apparatus will be described below with reference to FIGS. 6 and 7. Translation device body 1
00 includes a liquid crystal display unit (LCD panel) 101, cursor keys 102a to 102d, a speaker 103, and a power on / off switch 104. Also,
A key word 105 for determining and selecting a keyword and a plurality of other function keys 106 are provided.

Let us assume a case where a Japanese operator, for example, hears the opening time of a cafeteria in an American hotel using this apparatus. The operator operates the power switch 104
After the operation of, the "keyword" of the item keyword displayed on the liquid crystal display panel 101 is displayed as shown in FIG.
By selecting with a and operating the enter key 105, the content of the next screen of FIG. 7b is displayed. In this screen, when "English" is selected from the language keywords according to the above-mentioned operation, "hotel" is selected from the scene keywords in which the content of FIG. 7c is displayed. Next, FIGS. 7d to 7f.
Finally, select the keywords "Question text" → "Information" → "When does the cafeteria open?"
As shown in g, “What time does
he dining room open? Is displayed on the liquid crystal display panel 101, while the speaker 10
This phrase has been uttered since 3.

[0006]

However, in the above-mentioned translation device, when a person using different languages interacts with each other using this common portable speech translation device, the phrase characters of the original language of these languages or There is no function for visually confirming the translated phrase characters in a direction and a state where the interlocutors can easily see each other on the display device at the same time, which makes the interlocutor's conversation exchange complicated and takes a long time.

In view of the above, the present invention, for example, when a Japanese person and an American person face each other and have a conversation using Japanese and English, a Japanese conversational phrase character and this (translation)
It provides a convenient portable voice input translation device for conversations at overseas travel destinations, etc., which is equipped with a function to display the English sentence clause characters on the display device so that the interlocutors can easily see each other. is there.

A first object of the present invention is that even a person who is unfamiliar with the key operation of an electronic device can easily handle it, the desired conversational sentence can be quickly selected and displayed, and the display is easy to see and use. The purpose is to provide an input type automatic translator.

A more detailed object of the present invention is that, for example, when a Japanese and an American face each other and use the translation device of the present invention to have a conversation in Japanese and English, the Japanese conversational phrase characters and their translation ( The function of displaying the translated English sentence characters on the display device with the language characters required by each other in opposite directions so that the interlocutors can easily see each other is provided. The purpose of the present invention is to provide a portable voice input translation device which is convenient for use. Further, in the present invention, the translated phrase is displayed in parallel with the phrase in the original language so that it is easy to confirm whether or not the translated content is correct, and thus the user's convenience is improved.

[0010]

Therefore, according to the present invention, the first language based on the input means (microphone, keyboard) for inputting the first language (Japanese) and the voice information of the first language. First character synthesizing means for creating (Japanese) characters, translating means for converting the first voice information into voice information in a second language (English code), and voice information in the second language Second character synthesizing means for creating a character in a second language (English) based on the above, and liquid crystal display means (L) for displaying the character in the language created by the first and second character synthesizing means.
CD) and the characters of the first and second languages are displayed in mutually opposite directions on the liquid crystal display means by a voice input translation device. It solves the drawbacks of the device.

Further, by providing a switching means for switching and displaying the characters of the first and second languages on the liquid crystal display means, a more convenient voice input translation device can be provided, and further, The liquid crystal display means is composed of two display parts, and the characters of the first and second languages are divided into these two display parts so that they are displayed in mutually opposite first and second directions. This makes it possible to display characters that are easy to see over a wide area and solve the drawbacks of conventional translators.

[0012]

1 is a perspective view showing the appearance of an example of a voice input translation apparatus according to the present invention. The voice input translation device main body 1 of the present invention comprises a base body portion 1a and a lid portion 1b, and liquid crystal display panels 2 and 3 are provided on the base body portion 1a and the lid portion 1b. The lid portion 1b is mechanically and electrically coupled by the coupling member 4. A microphone 10, cursor keys 6a to 6c, a group of various function keys 7 described later, a power switch 8, an intention match confirmation key 9, and an optional IC card 11 described later are inserted into the base body 1a. Etc. are provided. In the lid portion 1b, in addition to the liquid crystal display panel 3,
Speaker 12, translation start key 13, translation end key 14
And an intention matching confirmation key 14 is provided.

FIG. 2 is a plan view showing FIG. 1 in more detail. Although details of the parts common to those in FIG. 6 are omitted, they will be further described with reference to the drawings. The display of each language displayed on the liquid crystal display panels 2 and 3 is opposite to each other, and is in the normal direction when viewed from the opponent facing the operator. In the embodiment, the original language Japanese and the translated English phrase are displayed in opposite directions.

The function key group 7 of the base body 1a is, for example, a conversation key 16 for the purpose of translation,
A learning key 17 for learning conversation, a voice input key 18 for selecting a voice input according to the present invention, and a keyword input key 1 for inputting a keyword as in a conventional translator.
9. Language keys 20 and 21 for selecting a target language for conversation, dictionary function key 22, calculation function key 23, game selection key 2
4, a memo key 25, a clock display key 26, an address book selection key 27 and the like. Furthermore, function key group 7
Is provided with a start key 28 and an end key 29 for instructing the start and end of capturing the phrase to be translated. or,
With the display switching key 30, the display contents of the liquid crystal display panels 2 and 3 can be switched. For example, the display phrases in Japanese and English can be exchanged. Further, in the base body portion 1a, it is confirmed on the liquid crystal display panel 2 whether or not the phrase spoken by the operator is correctly recognized by voice, and the intention agreement for confirming at the correct time and executing the translation is input. An intention match confirmation key 9 is provided.

For example, when a Japanese operator speaks into the microphone, "Where is the emergency exit?", A voice recognition circuit, which will be described later, recognizes the phrase and the liquid crystal display panel 2 asks, "Where is the emergency exit?" Is displayed. At this time, the operator presses the intention match confirmation key 9 if the content of the phrase spoken by the operator and the displayed content match, and if the match cannot be obtained, the operator repeats the voice input again and again.
The lid 1b is provided with a translation start key 13, a translation end key 14, and an intention matching confirmation key 15 which should be operated by a person who interacts with a Japanese operator. Only the minimum necessary keys are provided to prevent the other person from getting lost.

[0016] For example, the person who is an American who interacts with the person who speaks "Where is the emerg" after the translation function is executed.
energy exit? With the same content displayed on the liquid crystal display panel 3, the content spoken by the Japanese in Japanese can be known in English. On the contrary, the contents spoken by the Americans in English can also be viewed and listened to by the Japanese in Japanese by the reverse operation procedure. It should be noted that the translated English sentences and the untranslated Japanese sentences are displayed in parallel on each of the liquid crystal display panels 2 and 3, respectively, for the convenience of easily confirming whether or not the translation is correct. The parallel state in this case refers to the same direction, and its display position is arbitrarily selected.

Next, an example of a concrete circuit configuration of the present invention will be described with reference to FIG. The voice from the microphone 5 is sent to the voice recognition circuit 52 after being converted into a digital signal by the A / D converter 51. In the voice recognition circuit 52, the RAM
The pitch (frequency), strength (amplitude), speed, etc. of the input voice signal temporarily stored therein are discriminated, and the contents of the input voice signal are recognized by comparison with the existing voice data stored in the ROM 53. The recognized contents are coded and sent to the central processing unit CPU 55 of the computer and the translation circuit 70. The translation circuit 70 converts the coded voice data and the voice data in Japanese, which has been patterned in advance and stored in the ROM 71, into an English code. Therefore, the ROM 71 stores data such as a Japanese / English word dictionary, standard grammar, standard sentence pattern, and situation determination function.
Further, the RAM 72 is used for a temporary storage function of translation data, a learning function for situation determination, and the like.

The central processing unit CPU 55 has a voice recognition circuit 52, a translation circuit 70, a voice synthesis circuit 58, which will be described later, and a character display circuit 73 according to a program stored in the ROM 56.
To operate. The RAM 57 is the central processing unit CPU5.
5 is a buffer memory for the operation process of 5. CPU55
The translated English code is converted by the translation circuit 70 into an English voice signal by the voice synthesis circuit 58. The voice synthesizing circuit 5 creates an English voice signal by comparing the input English code with the English voice data which has been pattern-coded and stored in the ROM 59 in advance. RAM5
Reference numeral 7 serves to temporarily store data necessary for speech synthesis. This speech-synthesized digitized English sound phrase is converted to analog voice by the D / A conversion circuit 61, and then emitted from the speaker 12.

On the other hand, by the CPU 55 and the translation circuit 70,
The translated English code is supplied to the character display circuit 73 and converted into an English sentence. In the character information generation circuit 76, an English character signal is created by comparing the input English code with the English data which is pattern-coded and stored in the ROM 78 in advance, and the character information is sent to the character display circuit 73. The RAM 77 serves to temporarily store the data required for character creation. The digitized English phrase created by this character display circuit is converted into an analog character by the D / A conversion circuit 74, and then the liquid crystal display panel 3 is displayed.
Is displayed in English.

At this time, the Japanese phrase input from the microphone is the voice recognition circuit 52, the CPU 55, and the character display circuit 7.
3. It is also supplied to the liquid crystal display panel 2 via the D / A conversion circuit 74, and the phrase in Japanese is displayed. As shown in FIG. 2, the Japanese phrase on the liquid crystal display panel 2 and the English phrase on the liquid crystal display panel 3 have opposite display directions, and each of the conversation interlocutors faces each other and faces itself. You can easily check the related clauses. By this confirmation, it is possible to know in the native language and in the translated text whether or not the sentence spoken by oneself has been correctly translated. The display of each language on the liquid crystal display panel 2 and the liquid crystal display panel 3 can be switched by the switch 75 associated with the reverse display key 30 as necessary as described above. That is, it is possible to replace the Japanese characters with the translated English characters, and further display only the Japanese characters or only the translated English characters so as to face each other.

Input from the CPU 55 is also performed through the key input interface circuit 62 from each key. For example, it is possible to input a necessary conversational phrase by using a conventional keyword input expression. At this time, the keyword input key 19, the cursor key 6, the intention matching confirmation key 9, etc. in the function key group 7 are input. It is executed by an operation. When the capacity of the ROMs 54, 59, 71, 78 in this circuit is insufficient, various data can be obtained from the optional IC card 11. For example, it is possible to easily add vocabulary, grammar, sentence pattern, etc. of Japanese and English, and further add languages of each country.

Next, the basic translation processing flow of the speech input translation device 1 of the present invention will be described with reference to FIG. After the ON state of the power switch 8 is confirmed in step 200, and after the conversation key selection step 201 and the conversation language selection step 202,
The operator operates the phrase import start key 28 (step 20
3) Then, the speech recognition circuit 52 starts to take in Japanese phrases from the microphone 5. Input phrases from the microphone 5 are sent to the voice recognition circuit 52 until the phrase import end key 29 is operated, and the recognized words and phrases are displayed in Japanese on the liquid crystal display panel 2. The operator operates the phrase capturing end key 29 at the boundary of his / her own conversational phrase (step 206), and if the text on the liquid crystal display panel matches the text desired by the operator, the intention matching means meaning the intention matching. The confirmation key 9 is operated. This step 20
By the operation of 7, translation in the translation circuit 70 is started.
When the translation is completed (step 208), the Japanese phrase and the translated English phrase are displayed on the liquid crystal display panels 2 and 3, respectively, and sound is output in English (step 209).

The above operation flow is the same when displaying and uttering a Japanese voice input in English, and vice versa, when displaying and uttering an English voice input in Japanese. However, only the phrase acquisition start step 203 and end step 205
Is input by the start key 28 and the end key 29 or by the translation start key 13 and the translation end key 14 to distinguish between Japanese input and English input.

The translation of the translation circuit 70 may be performed by the following translation algorithm. A word keyword recognized by the voice recognition circuit 52, for example,
The Japanese words "I made a reservation in Tokyo" are generated from the phonetic words "I", "Reservation", "In Tokyo", and "Done", and "I made a reser".
It is possible to generate an English phrase “Vation in Tokyo”, cause the speaker 12 to emit sound, and display the English sentence on the liquid crystal display panel 3.

In the first embodiment of the present invention, the liquid crystal display panels 2 and 3 are provided at two places. However, the present invention is not limited to this, and one liquid crystal display panel may have the above-mentioned function. Although FIG. 5 is described by omitting the portions common to FIG. 2, one liquid crystal display panel 300 is divided into upper and lower parts to display each display, and each operation key is provided only on the base body part. In this example as well, Japanese characters and translated English characters are displayed opposite to each other. Also, a translation start key 13, a translation end key 14, and an intention match confirmation key 15
The display of is also in the same direction as the display direction of the corresponding language.

Further, it is the same as the first embodiment to arrange the interactive display in each of the languages in parallel and display the original language and the translated language in lowercase in the same direction for the convenience of the interlocutor. Is the same. Further, in the present invention, the selection keys 20 and 21 are used to select the input of English or Japanese. However, the selection may be made by the translator itself automatically instead of manually. In this case, the ROM 71
It is sufficient to provide a dictionary for language pattern discrimination in.

[0027]

As described above, according to the portable voice input translation apparatus of the present invention, when people who use different languages interact with each other using this common portable voice input translation apparatus, The ability to visually check the bunsetsu characters and translated bunsetsu characters of these languages in the directions in which the interlocutors can easily see each other on the display device at the same time makes it difficult for the interlocutors to exchange conversations and It no longer takes time. For example, when a Japanese person and an American person face each other and use Japanese and English for conversation, it is easy and efficient for the interlocutors to see the Japanese conversational phrase characters and their translated English translations. The layout of the display unit and the function of displaying on the display device of the size are added, so that it becomes possible to deal with instant conversations at overseas travel destinations. In addition, since the phrases in the translated language are displayed in the same direction in lowercase letters in the original language phrase display, it is possible to easily confirm whether or not the dialogue content is translated correctly.

[Brief description of drawings]

FIG. 1 is an external perspective view of a speech input translation device of the present invention.

FIG. 2 is a plan view of the speech input translation device of the present invention.

FIG. 3 is a specific circuit block diagram of the speech input translation device of the present invention.

FIG. 4 is a flowchart diagram for operating the circuit block of FIG.

FIG. 5 is a plan view of a speech input translation device according to another embodiment.

FIG. 6 illustrates a conventional example of the present invention.

FIG. 7 shows an operation description of the conventional example shown in FIG.

[Explanation of symbols]

 1 Voice input translation device 2, 3, 102, 300 Liquid crystal display panel 5 Microphone 6 Cursor keys 7 Various function keys 8 Power switch 9 and 15 Intention match confirmation key 11 IC card 12 Speaker 13 and 28 Translation start key 14 and 29 Translation end key 52 Voice recognition circuit 55 Central processing unit (CPU) 58 Voice synthesis circuit 62 Key interface 70 Translation circuit 73 Character display circuit 75 Inversion switch circuit 76 Character generation circuit

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Shigeyuki Yoneyama 6-735 Kitashinagawa, Shinagawa-ku, Tokyo Sony Corporation

Claims (9)

[Claims] 1. A voice input means for inputting a voice in a first language; a voice recognition means for determining a pitch, a strength, a speed, etc. of a voice from the voice input means to obtain first voice information; A first character synthesizing unit that creates a character in a first language based on first voice information; a translation unit that converts the first voice information into voice information in a second language; A second character synthesizing means for creating a character of the second language based on the voice information of the language; and a display means for displaying the character of the language created by the first and second character synthesizing means. A voice input translation device, characterized in that the characters of the first and second languages are displayed on the display means in mutually opposite directions. 2. The voice input translation device according to claim 1, further comprising switching means for switching and displaying the characters of the first and second languages on the display means. 3. The display means comprises two display parts,
2. The voice input translation device according to claim 1, wherein the characters of the first and second languages are divided into these two display units and displayed in mutually opposite directions. 4. The two display portions of the display means are respectively provided on a base body portion and a lid portion of a voice input translation device, and the characters of the first and second languages are provided on the base body portion and the base body portion, respectively. 4. The voice input translation device according to claim 3, wherein the display unit is divided into two display units of the lid unit and displayed in opposite directions. 5. The display means comprises one display section,
2. The voice input translation device according to claim 1, wherein the characters of the first and second languages are divided into respective areas of the display unit and displayed in mutually opposite directions. 6. A voice input means including a microphone for inputting a first language, and a voice recognition means for determining a pitch, strength, speed, etc. of a voice from the voice input means to obtain first voice information. A first character synthesizing means for creating a character in a first language based on the first voice information; a translating means for converting the first voice information into voice information in a second language; A voice synthesizing unit that creates a voice in a second language based on voice information in the second language, a speaker that outputs the voice in the second language by voice, and a second voice based on the voice information in the second language. A second character synthesizing means for creating characters of a language, and a liquid crystal display means for displaying the first and second language characters, the first and second language characters, the liquid crystal Display on the display means in mutually opposite first and second directions To together, voice input translation apparatus, wherein a display of the control keys for controlling the audio input means corresponding to the second language for the said second direction. 7. The liquid crystal display means is composed of two display parts, and the characters of the first and second languages are divided into these two display parts and displayed in mutually opposite directions. The voice input translation device according to claim 6, characterized in that 8. A voice input unit for inputting a first language, a voice recognition unit for determining pitch, strength, speed, etc. of a voice from the voice input unit to obtain first voice information, A first character synthesizing means for creating a character in a first language based on the voice information, a translating means for converting the first voice information into voice information in a second language, A voice synthesizing unit that creates a voice in a second language based on voice information; a second character synthesizing unit that creates a character in a second language based on voice information in the second language; A liquid crystal display means for displaying characters in a second language, wherein the first language and a character in a second language translated by the translation means from the first language are displayed on the display means. A voice input translation device characterized by being arranged side by side and displaying in the same direction. 9. The liquid crystal display means is composed of two display sections, and the characters of the first and second languages are arranged in a pair in the same direction, and the parallel characters of these pairs are displayed on the two liquid crystal display sections. The voice input translation apparatus according to claim 8, wherein the voice input translation apparatus is configured to be divided and displayed in mutually opposite directions.