JP4702081B2 - Character input device - Google Patents

Description

  The present invention relates to a character input device capable of displaying a plurality of characters and designating and inputting each of the displayed characters.

  In recent years, navigation systems that can input facility names and the like by voice using voice recognition technology are widely known. In addition to the navigation system, voice recognition technology is used in various systems.

  As a speech recognition device using speech recognition technology, for example, a speech recognition device is known that operates a speech input in a single syllable and a selection unit corresponding to the speech to accurately extract speech (for example, (See Patent Document 1).

  Also, when inputting syllables one by one, a voice input device is known that improves voice recognition accuracy by inputting syllables by voice after pressing a row button (see, for example, Patent Document 2).

Furthermore, by combining the result input from the input device with the result recognized by the speech recognition device, the input character is specified, and the button input / voice recognition combined input for quickly and accurately inputting the character. An apparatus is also known (for example, refer to Patent Document 3).
JP 2000-003748 A JP 2000-056796 A JP 09-288495 A

  However, the voice recognition technology may cause erroneous recognition when a device with low recognition accuracy is used, and even if a syllable is input by voice after pressing the row button as in the voice input device described in Patent Document 2 above. However, if the recognition accuracy is low, there is a problem that voice input must be repeated many times, which is troublesome.

  In addition, when inputting characters using an input device such as a touch panel or a keyboard, a user who is not accustomed to input using a touch panel or keyboard having a button for inputting 50 sound characters cannot input accurately and quickly with a single operation. difficult. The same applies even if a device that collates the result input from the input device and the result recognized by the voice recognition device, such as the device described in Patent Document 3, is used.

  The present invention has been made to solve the above-described problem, and an object of the present invention is to provide a character input device that can input characters accurately and efficiently using voice recognition and a 50-character input operation. And

In order to achieve the above object, a character input device according to the present invention includes a voice input means for inputting voice, a voice recognition means for recognizing a character or a character string from the voice input by the voice input means, A 50-sound input means for displaying and displaying each of the displayed 50-sound characters by a touch operation , and among the 50-sound characters displayed on the 50-sound input means, the speech recognition means Control means for controlling the 50 sound input means so that the characters corresponding to each of the recognized characters or characters constituting the character string are highlighted.

  That is, in this character input device, when a character input person inputs a voice or a character string desired to be input with the 50 sound input means by voice input with the voice input means, the input voice is recognized as a character or character string by the voice recognition means, Of the 50-sound characters displayed on the 50-sound input means, the characters corresponding to each of the characters constituting the speech-recognized character or character string are highlighted. Thereby, the character input person can easily find a character to be input from the displayed 50-sound characters, and can specify and input a character or a character string accurately and efficiently.

  The control means, when the plurality of different characters or character strings from the same voice are recognized as recognition candidates by the voice recognition means, out of the fifty-sound characters displayed on the fifty-sound input means. The fifty-sound input means can also be controlled so that all the characters corresponding to each of the characters constituting the plurality of recognition candidates or the character string are highlighted.

  Thus, by highlighting all of the characters corresponding to each of the characters constituting the plurality of recognition candidates or the character string, the characters can be compared with the case where only the first candidate is used as the speech recognition result. Since the 50 phonetic characters corresponding to the character that the input user wants to input can be highlighted with a high probability, it is easier to designate and input the 50 phonetic characters, and the total input efficiency is significantly improved.

  As described above, according to the present invention, 50-sound characters that can be designated and input are displayed, and among the displayed 50-sound characters, each of the characters constituting the speech-recognized character or the character string is displayed. Since the corresponding characters are highlighted, an excellent effect is achieved that the characters or character strings can be designated and input accurately and efficiently.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a block diagram showing a schematic configuration of a character input device 10 according to an embodiment of the present invention. This character input device 10 is connected to a car navigation system (car navigation system) 30 that is mounted on a vehicle or the like and detects the current position of the vehicle and guides the route to the destination, and inputs the target facility name and the like. Used to output to the car navigation system 30.

  The character input device 10 includes a voice input device 20 such as a microphone for inputting a voice of a character input person, a voice recognition database (DB) 22 storing a voice recognition dictionary, a voice recognition device 24 for performing voice recognition, a character input A control device 26 that controls the entire device 10 and a touch panel display 28 as a user interface in which a touch panel is superimposed on a display panel made of a liquid crystal display panel are provided.

  The touch panel display 28 is connected to the control device 26. The control device 26 controls the touch panel display 28 to display an input screen as shown in FIG. As shown in FIG. 2, the input screen includes a character button 50 for designating a 50-sound character in which a 50-sound hiragana or the like is displayed in a frame, and a character input person's of the 50-sound character button 50. A function area 54 including a display area 52 for sequentially displaying characters represented by a character button touched and pressed by a fingertip or the like (hereinafter, touch operation), a confirmation button for confirming a character or a character string displayed in the display area as an input character, and the like. It is included. By operating each of the character button 50 and the function button 54 included in the input screen displayed on the touch panel display 28, a command for executing the function of the character or the operation button displayed on the touched portion is input. Is done.

  The speech recognition device 24 performs speech recognition processing on the speech input from the speech input device 20 using the speech recognition dictionary stored in the speech recognition database 22, and the character or character string obtained by the speech recognition processing. Is output to the control device 26 as a voice recognition result. When the voice recognition device 24 recognizes a plurality of different characters or character strings as recognition candidates from the same voice, the voice recognition device 24 outputs the plurality of recognition candidates to the control device 26 as a voice recognition result.

  When the voice recognition result is input from the voice recognition device 24, the control device 26, among the fifty-sound character buttons 50 included in the input screen displayed on the touch panel display 28, the characters constituting the recognition candidate indicated by the voice recognition result. The display on the touch panel display 28 is controlled so that the character button 50 on which is displayed is highlighted.

  Hereinafter, the flow of character input processing in the character input device 10 will be described with reference to FIG. FIG. 3 is a flowchart showing a character input processing routine executed by the control device 26.

  When the character input person wants to input the character “Satoi”, first, the user inputs “Satoi” to the voice input device 20. When voice is input to the voice input device 20, the voice recognition device 24 performs voice recognition processing using the voice recognition dictionary stored in the voice recognition DB 22. The voice recognition device 24 outputs the character or character string obtained by the voice recognition processing to the control device 26 as a voice recognition result.

  In step 100, the control device 26 determines whether or not a voice recognition result has been input from the voice recognition device 24. Note that the speech recognition apparatus 24 of the present embodiment can output a plurality of recognition candidates as described above. For example, as shown in FIG. 4A, the first candidate “Satoen”, the second candidate “Katouiin”, the third candidate “ When three different character strings “Satoin” are recognized as recognition candidates, all of the plurality of recognition candidates are output to the control device 26.

  If it is determined in step 100 that the voice recognition result has been input from the voice recognition device 24, the process proceeds to step 102, and the 50 sounds constituting each of the plurality of recognition candidates on the input screen displayed on the touch panel display 28. The character button 50 corresponding to the character is highlighted and displayed. In this example, as shown in FIG. 4B, the logic of characters constituting the three recognition candidates of the first candidate “Satoen”, the second candidate “Katouiin”, and the third candidate “Satouiin”. The character buttons 50 on which “sa”, “to”, “e”, “n”, “ka”, “u”, and “i” are displayed are highlighted in a thick frame.

  As described above, the character button 50 on which the character input by the character input person is displayed on the input screen is highlighted, so that the character input person can easily find the character button 50 (that is, the character to be input) that he / she wants to touch. Can input characters efficiently and accurately.

  In step 104, it is determined whether or not a touch operation is performed on the 50-sound character button 50 displayed on the touch panel display 28. If it is determined that a touch operation has been performed on the 50-sound character button 50, a character corresponding to the touched character button 50 is displayed in the display area 52 of the input screen in step 106, and The character information is held in an internal memory (not shown).

  Further, after the processing of step 106 or when it is determined that the touch operation has not been performed in step 104, the process proceeds to step 108, where the confirmation button of the function button 54 is touch-operated, and an instruction to confirm the input character is input. It is determined whether or not. If it is determined that the confirm button has not been touched, the process returns to step 104 to wait for input of a touch operation on the 50-sound character button 50.

  On the highlighted input screen, the character input person inputs a desired character (in this example, “Satoin”) by touching the touch panel display 28, and touches the confirmation button. Then, in step 108, it is determined that an instruction to confirm the input character has been input, and the process proceeds to step 110.

  In step 110, the character information held in the internal memory in step 106 is output to the car navigation system 30 as a character input result.

  In step 112, the highlighted display on the input screen is reset to return to the initial state.

  As described above, when the character input person inputs a voice, the character button 50 corresponding to each of the characters constituting the recognized character or the character string is highlighted and displayed. The touch operation becomes easy, and a character or a character string to be input can be input accurately and efficiently.

  In addition, since character input is finally performed by performing a touch operation on the input screen, it is possible to input characters accurately without any problem even if the voice recognition process is slightly misrecognized.

  In addition, when a plurality of recognition candidates are obtained as a recognition result in the speech recognition processing, only the characters constituting the first candidate may be highlighted, but as in the above embodiment, the plurality of recognition candidates may be highlighted. By highlighting the character buttons 50 corresponding to all of the characters constituting the recognition candidates, the character buttons corresponding to the characters that the character input user wants to input compared to the case where only the first candidate is used as the speech recognition result Since 50 can be highlighted with a very high probability, the touch operation becomes easier and the total input efficiency is remarkably improved. In this case, the number of recognition candidates or the number of characters to be highlighted can be appropriately limited.

  In the above embodiment, the example in which the character button 50 is highlighted with a thick frame is described. However, the present invention is not limited to this. For example, the character button 50 may blink or the color may be changed. The brightness may be increased.

  Furthermore, in the above embodiment, the example in which the character represented by the character button 50 touched by the character input person is displayed in the display area 52 has been described. However, the present invention is not limited to this. The first candidate may be displayed in the display area 52 with white characters as a state before confirmation, and if the displayed character or character string is OK, the character input person can confirm the input with the confirmation button. Furthermore, when the character button 50 is touched without confirming the first candidate character or character string displayed in the display area 54, the first candidate character or character displayed in the display area 52 is displayed. The column may be deleted, and the character represented by the touched character button 50 may be displayed as the input character. This further improves the overall usability.

  Moreover, in the said embodiment, although the case where the character input person uttered and input a character before touch-operating on the touch panel display 28 was mentioned as an example, this character input device 10 does not necessarily need to utter, When a character input person does not utter, it can also be set as the structure which inputs a character only by touch operation like the normal touch panel display 28. FIG.

It is a block diagram which shows the schematic structure of the character input device which concerns on embodiment of this invention. It is a figure which shows the example of a display of the input screen displayed on the touchscreen display. It is a flowchart which shows the character input processing routine performed with a control apparatus. (A) is a figure which shows an example of the speech recognition result with respect to the speech of "Satoiin" input by the character input person, (B) respond | corresponds to each character which comprises the character string by which speech recognition was carried out. It is a figure which shows the state which highlighted the character button.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Character input device 20 Voice input device 22 Voice recognition database 24 Voice recognition device 26 Control device 28 Touch panel display 50 Character button 52 Display area 54 Function button

Claims (2)

Voice input means for inputting voice;
Voice recognition means for recognizing characters or character strings from the voice input by the voice input means;
A 50-sound input means for displaying 50-sound characters and capable of designating and inputting each of the displayed 50-sound characters by a touch operation ;
Of the 50-sound characters displayed on the 50-sound input unit, the 50-sound input unit so that a character corresponding to each of the characters recognized by the speech recognition unit or the characters constituting the character string is highlighted. Control means for controlling
A character input device. The control means, when a plurality of different characters or character strings from the same voice are recognized as recognition candidates by the voice recognition means, out of the plurality of 50-sound characters displayed on the 50-sound input means. The character input device according to claim 1, wherein the sound input unit is controlled so that all of the characters corresponding to each of the characters constituting the recognition candidate or the character string are highlighted.

Images