KR102119743B1 - Electronic terminal device for performing a correction process for a homophonic vowel based on speech recognition and operating method thereof - Google Patents

Abstract

Disclosed is an electronic terminal device and a method of operating the same, which perform a correction process for a homophone collection based on speech recognition. The present invention provides an electronic terminal device capable of performing correction processing based on a user's voice recognition when a typo occurs in a homophone vowel included in a word input to an electronic terminal device through an input device and an operation method thereof By doing so, it is possible to assist the user in correcting a typo in the homophone collection.

Description

ELECTRONIC TERMINAL DEVICE FOR PERFORMING A CORRECTION PROCESS FOR A HOMOPHONIC VOWEL BASED ON SPEECH RECOGNITION AND OPERATING METHOD THEREOF}

The present invention relates to a technique for performing correction processing based on a user's voice recognition when a typo occurs in a homophone vowel included in a word input to an electronic terminal device through an input device.

When a user inputs a character into an electronic terminal device using an input device such as a keyboard, a typo often occurs.

Particularly, as electronic terminal devices equipped with a touch screen such as a smart phone or a tablet PC are widely used, virtual keyboards for enabling text input in such electronic terminal devices have been widely used, and these virtual keyboards are physical buttons. Unlike this provided keyboard, since a user receives an input command in the form of applying a touch input on a touch screen, a typo often occurs during a character input process.

Normally, when a typo occurs in a character entered through the keyboard, the user corrects the typo by deleting the mistyped character and re-entering the character correctly, but the correction of the typo causes a lot of inconvenience to the user Doing.

In the case of Hangeul, there are many vowels with the same note, ie, homophone vowels, such as'ㅔ' and'ㅐ', so users often enter the same vowel vowel incorrectly in the process of entering text. have. In particular, in Korean keyboards, since keyboards corresponding to homophone vowels such as'ㅐ' and'ㅔ' are located at adjacent points, the user frequently enters a homophone vowel in the process of inputting characters.

For example, when a user tries to input'personnel', a typo called'person' is often inputted to the electronic terminal device as'ㅔ' instead of'ㅐ' is inputted from'jae'.

Therefore, when a user inputs a predetermined word in the electronic terminal device, if there is a typo in the homophone vowel, there is a need for research on a technique to assist the user to easily correct the typo for the homophone vowel.

The present invention provides an electronic terminal device capable of performing correction processing based on a user's voice recognition when a typo occurs in a homophone vowel included in a word input to an electronic terminal device through an input device and an operation method thereof By doing so, it is intended to assist the user in correcting a typo in the homophone collection.

An electronic terminal device that performs a correction process for a homophone vowel based on speech recognition according to an embodiment of the present invention includes a plurality of vowels predefined as a homophone vowel and a predetermined pronunciation string corresponding to each of the vowels The first word including the first vowel among the plurality of vowels is input from the user through a vowel table holding unit that stores and maintains the vowel tables recorded in correspondence with each other and an input device that enables input of characters. When the first word is displayed on the screen, and after the first word is displayed on the screen, a voice corresponding to the pronunciation of the alternative vowel for correcting the typographical error of the first vowel is input from the user through the microphone. A pronunciation string generation unit that recognizes the user's voice and generates a first pronunciation string according to a result of recognizing the user's voice, and a first pronunciation string corresponding to the first pronunciation string among the plurality of vowels recorded in the vowel table. 1 A correction word generation unit that identifies a replacement vowel and changes the first vowel included in the first word to the first alternative vowel to generate a correction word for the first word and is displayed on the screen And a correction processing unit displaying the first word by replacing it with the correction word.

In addition, an operation method of an electronic terminal device that performs a correction process for a homophone vowel based on voice recognition according to an embodiment of the present invention corresponds to a plurality of vowels previously designated as a homophone vowel and each of the plurality of vowels Storing and maintaining a vowel table in which predetermined pronunciation strings are recorded in correspondence with each other, a first word including a first vowel among the plurality of vowels from a user through an input device enabling input of characters When is input, the first word is displayed on the screen, and after the first word is displayed on the screen, a voice corresponding to the pronunciation of the alternative vowel for correcting a typo in the first vowel is input from the user through a microphone. When the user's voice is recognized, generating a first pronunciation string according to a result of recognizing the user's voice, the first corresponding to the first pronunciation string among the plurality of vowels recorded in the vowel table Checking a replacement vowel, changing the first vowel included in the first word to the first alternative vowel to generate a correction word for the first word, and the first word displayed on the screen And replacing and displaying the corrected word.

The present invention provides an electronic terminal device capable of performing correction processing based on a user's voice recognition when a typo occurs in a homophone vowel included in a word input to an electronic terminal device through an input device and an operation method thereof By doing so, it is possible to assist the user in correcting a typo in the homophone collection.

1 is a diagram showing the structure of an electronic terminal device that performs a correction process for a homophone collection based on voice recognition according to an embodiment of the present invention.
2 is a flowchart illustrating an operation method of an electronic terminal device that performs a correction process for a homophone collection based on voice recognition according to an embodiment of the present invention.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. It should be understood that these descriptions are not intended to limit the invention to specific embodiments, and include all modifications, equivalents, or substitutes included in the spirit and scope of the invention. In describing each drawing, similar reference numerals have been used for similar elements, and unless otherwise defined, all terms used in this specification, including technical or scientific terms, have common knowledge in the technical field to which the present invention pertains. It has the same meaning as commonly understood by people who have it.

1 is a diagram showing the structure of an electronic terminal device that performs a correction process for a homophone collection based on voice recognition according to an embodiment of the present invention.

Referring to FIG. 1, the electronic terminal device 110 that performs a correction process for a homophone vowel based on voice recognition according to the present invention includes: a vowel table holding unit 111, a pronunciation string generator 112, and a correction word generation It includes a section 113 and a correction processing section 114.

The vowel table holding unit 111 stores and maintains a vowel table in which a plurality of vowels previously designated as homophone vowels and a predetermined pronunciation string corresponding to each of the vowels are recorded in correspondence with each other.

Here, the homophone vowel means a vowel having the same notes, such as'ㅔ' and'ㅐ', and a plurality of vowels predetermined by the administrator such as'ㅔ' and'ㅐ' are recorded in the vowel table. . In addition, the pronunciation string corresponding to each of the plurality of vowels is a string used for pronunciation when expressing each vowel, and for the vowel'ㅔ' is a vowel created by continuously combining'ㅓ' and'ㅣ', ' A phonetic character string'Hey' may be recorded in correspondence.

Summarizing these points, information may be recorded in the collection table as shown in Table 1 below.

Multiple vowels Pronunciation string ㅐ Child ㅔ Hey ㅖ Hey ㅒ Hey ㅡ Uh ㅢ Uh ... ...

The pronunciation string generator 112 displays the first word on the screen when the first word including the first vowel among the plurality of vowels is input from the user through an input device that enables input of characters. Then, after the first word is displayed on the screen, when a voice corresponding to the pronunciation of the alternative vowel for correcting the first vowel is input from the user through a microphone, the user's speech is recognized and the user's speech is recognized. Creates a first pronunciation string according to the result of recognizing.

For example, when a user wants to input the word'Talent' using the keyboard, but when a typo called'Inje' is entered due to a wrong input, the user may use the ' It is possible to input a voice called'eye', which is a pronunciation corresponding to'ㅐ', which is an alternative vowel for correcting a typographical error of 라는. At this time, the pronunciation string generation unit 112 may recognize the user's voice and generate a first pronunciation string called'child'.

The correction word generation unit 113 identifies a first replacement vowel corresponding to the first pronunciation string among the plurality of vowels recorded in the vowel table, and checks the first vowel included in the first word. The correction word for the first word is generated by changing to the first replacement vowel.

Then, the correction processing unit 114 replaces and displays the first word displayed on the screen with the correction word.

In relation to this, as described above, when the user inputs the word'Inje' through the keyboard and then inputs the voice'I', the first pronunciation string called'I' is generated, and the correction word is generated. The unit 113 may identify'ㅐ' as a first alternative vowel corresponding to the first pronunciation string'eye' among the plurality of vowels recorded in the vowel table as shown in Table 1, and'Inje' By changing the word'ㅔ' to'ㅐ', a'person' can be generated as a correction word for the word'Inje'.

Thereafter, the correction processing unit 114 may replace the “person” displayed on the screen with the correction word “person” to display.

At this time, according to an embodiment of the present invention, the correction word generation unit 113 has a specific configuration for processing the generation of the correction word, a replacement vowel confirmation unit 115, a similar vowel confirmation unit 116, and a word confirmation unit 117 and a correction unit 118, and a predetermined similar vowel corresponding to each vowel for each of the plurality of vowels may be additionally recorded in the vowel table.

Relatedly, similar vowels corresponding to each vowel may be additionally recorded in the vowel table as shown in Table 2 below.

Multiple vowels Pronunciation string Similar vowels ㅐ Child ㅔ ㅔ Hey ㅐ ㅖ Hey ㅒ ㅒ Hey ㅖ ㅡ Uh ㅢ ㅢ Uh ㅡ ... ... ...

In this case, when the first pronunciation string is generated, the replacement vowel checking unit 115 checks the first replacement vowel corresponding to the first pronunciation string among the plurality of vowels recorded in the vowel table.

When the first alternative vowel is confirmed, the similar vowel checking unit 116 checks the first similar vowel recorded in the vowel table corresponding to the first alternative vowel.

The word checking unit 117 checks whether the first vowel includes the same vowel as the first similar vowel.

The correction unit 118 replaces the first vowel included in the first word with the first vowel when it is determined that the first vowel is included in the first vowel as the same vowel as the first similar vowel. By changing to a vowel, the generation of the correction word for replacing the first word is processed.

In relation to this, the alternative vowel checking unit 115, the similar vowel checking unit 116, the word checking unit 117, and the correcting unit 118 will be described as follows using the examples used above.

First, as the user applies the first word called'Inje' using the keyboard and then inputs a voice called'I', the pronunciation string generating unit 112 generates a first pronunciation string called'I'. In the case, the alternative vowel checking unit 115 confirms'ㅐ' as the first alternative vowel corresponding to the first pronunciation string called'child' among the plurality of vowels recorded in the vowel table as shown in Table 2 above. Can be.

Then, when the first replacement vowel called'ㅐ' is identified, the similar vowel checking unit 116 is the first similar vowel recorded in correspondence to the first alternative vowel called'ㅐ' in the vowel table. ㅔ'can be checked.

Then, the word confirming unit 117 may check whether the first vowel that is'Inje' contains the same vowel as the first similar vowel that is'ㅔ'.

At this time, according to an embodiment of the present invention, the word identification unit 117 divides the first word into units of words, and compares each of the plurality of elements constituting the first word with the first similar vowel. By checking whether the same vowel as the first similar vowel is included among the plurality of vocabularies, it is possible to check whether the first vowel is the same as the first similar vowel.

In relation to this, the word confirming unit 117 may divide the first word called'Inje' into units, and generate a plurality of elements called'ㅇㅣㄴㅈㅔ', a plurality of words called'ㅇㅣㄴㅈㅔ' By comparing each of the elements of the first and the first similar vowel'ㅔ' with each other and checking whether the same vowel as the first similar vowel'ㅔ' is included among the plurality of elements called'ㅇㅣㄴㅈㅔ', In the first word called'Inje', it is possible to check whether the same vowel as the first similar vowel called'ㅔ' is included.

In the present embodiment, since the plurality of elements called'ㅇㅣㄴㅈㅔ' includes'ㅔ', the word confirming unit 117 is the first similarity called'ㅔ' to the first word'Inje' It can be confirmed that the same vowel as the vowel is included.

In this way, when it is determined that the first word'Inje' includes the same vowel as the first similar vowel, the correction unit 118 is included in the first word'Inje'. By changing'ㅔ' to the first alternative vowel'ㅐ' identified by the alternative vowel checking unit 115,'person' can be generated as a correction word for replacing the first word'Inje'. .

At this time, according to an embodiment of the present invention, if it is determined that the correction unit 118 includes two or more of the first vowels in the same vowel as the first similar vowels in the first word, the first word It is possible to process the generation of the correction word for replacing the first word by changing the last input vowel through the input device among the two or more first vowels included in the first vowel.

For example, when the first word input through the keyboard is a'financial statement', and the voice input by the user to perform a typo correction on the vowel is'o', the alternative vowel confirmation unit 115 may display the table A first alternative vowel called'ㅔ' may be identified by referring to a vowel table such as 2, and the similar vowel checking unit 116 may include a first called '제'corresponding to the first alternative vowel called'ㅔ'. You can see similar vowels.

In this case, the word confirming unit 117 may check whether the first similar vowel, which is called'ㅐ', is included in the first word called'financial statement'. Since two'ㅐ' are included, the correction unit 118 is the last input vowel through the keyboard among the two'ㅐ' included in the first word'financial statement', that is, the'remark' A'financial statement' may be generated as a correction word for substituting the first word'financial statement' by changing the'ㅐ' located at to the first alternative vowel called'ㅔ'.

According to an embodiment of the present invention, the electronic terminal device 110 that performs a correction process for a homophone collection based on speech recognition may further include a font information table holding unit 119 and a volume value checking unit 120. Can be.

The font information table holding unit 119 is a font in which information on predetermined unique fonts for each of the plurality of different volume value ranges and the plurality of different volume value ranges are recorded in correspondence with each other. Store and maintain information tables.

For example, information may be recorded in the font information table as shown in Table 3 below.

Multiple different volume ranges Information about native fonts 0~30dB Myeongjo 30~70dB Gothic 70~100dB Archery ... ...

When a voice is input from the user through the microphone, the volume value checking unit 120 checks a first volume value according to the user's voice input.

At this time, when the correction word is generated, the correction processing unit 114 checks the information on the first unique font recorded corresponding to the volume value range to which the first volume value belongs, from the font information table, and the correction After applying the font format according to the first unique font to the word, the first word displayed on the screen may be replaced with the correction word to be displayed.

For example, if the first volume value according to the voice applied by the user is '40dB', and the first word is'Inje' and the correction word is'Talent', the correction processing unit 114 may display the table. Referring to the font information table as 3, check the'Gothic' which is the information on the first unique font recorded in correspondence to the volume value range to which the first volume value '40dB' belongs, and check the correction word'Talent' After applying the font format according to'Gothic' for', the first word,'Inje' displayed on the screen may be replaced with'Talent'.

2 is a flowchart illustrating an operation method of an electronic terminal device that performs a correction process for a homophone collection based on voice recognition according to an embodiment of the present invention.

In step S210, a vowel table in which a plurality of vowels pre-designated as homophones and a predetermined pronunciation string corresponding to each of the plurality of vowels is recorded in correspondence with each other is stored and maintained.

In step S220, when a first word including a first vowel among the plurality of vowels is input from a user through an input device that enables input of characters, the first word is displayed on the screen, and the After the first word is displayed on the screen, if a voice corresponding to the pronunciation of the alternative vowel for correcting the first vowel is input from the user through the microphone, the user's speech is recognized to recognize the user's speech. The first pronunciation string is generated according to the result.

In step S230, a first replacement vowel corresponding to the first pronunciation string is identified among the plurality of vowels recorded in the vowel table, and the first vowel included in the first word is the first vowel. A correction word for the first word is generated by changing to an alternative vowel.

In step S240, the first word displayed on the screen is replaced with the correction word to be displayed.

At this time, according to an embodiment of the present invention, a predetermined similar vowel corresponding to each vowel may be additionally recorded in each vowel table in the vowel table.

At this time, in step S230, when the first pronunciation string is generated, checking the first replacement vowel corresponding to the first pronunciation string among the plurality of vowels recorded in the vowel table, the first When a replacement vowel is confirmed, checking a first similar vowel recorded in correspondence with the first alternative vowel in the vowel table, and checking whether the first vowel includes the same vowel as the first similar vowel. And if it is determined that the first vowel is included in the first vowel as the same vowel as the first similar vowel, the first vowel included in the first word is changed to the first alternative vowel. By doing so, it may include the step of processing the generation of the correction word to replace the first word.

At this time, according to an embodiment of the present invention, the step of determining whether the same vowels as the first similar vowels are included is divided into the first words in units of letters, and a plurality of letters forming the first words Each of the first similar vowels is compared with each other to determine whether the same vowels as the first similar vowels are included among the plurality of elements, and the same vowels as the first similar vowels are included in the first word. You can check whether it is.

In addition, according to an embodiment of the present invention, when processing the generation of the corrected word, when it is determined that the first word includes two or more of the first vowels in the same vowel as the first similar vowels, Processing the generation of the corrected word to replace the first word by changing the last input vowel through the input device among the two or more first vowels included in the first word to the first alternative vowel. can do.

According to an embodiment of the present invention, an operation method of an electronic terminal device that performs a correction process for a vowel collection based on the speech recognition includes a plurality of predetermined volume ranges and a plurality of different volume ranges Storing and maintaining a font information table in which information about a predetermined unique font for each of them is recorded in correspondence with each other, and when a voice is input from the user through the microphone, a first volume according to the user's voice input The method may further include checking a value.

At this time, in step S240, when the correction word is generated, the information on the first unique font recorded corresponding to the volume value range to which the first volume value belongs is checked from the font information table, and the correction word After applying the font format according to the first unique font to the first word displayed on the screen can be displayed by replacing the correction word.

The operation method of the electronic terminal device that performs correction processing for the homophone vowel based on speech recognition according to an embodiment of the present invention has been described above with reference to FIG. 2. Here, according to an embodiment of the present invention, an operation method of an electronic terminal device that performs a correction process for a phonetic vowel based on speech recognition performs a correction process for a phonetic vowel based on the speech recognition described with reference to FIG. 1. Since it may correspond to the configuration of the operation of the electronic terminal device 110, a detailed description thereof will be omitted.

An operation method of an electronic terminal device that performs a correction process for a vowel collection based on speech recognition according to an embodiment of the present invention may be implemented as a computer program stored in a storage medium for execution through combination with a computer.

In addition, an operation method of an electronic terminal device that performs a correction process for a phonetic vowel based on voice recognition according to an embodiment of the present invention is implemented in a form of program instructions that can be performed through various computer means, and thus is computer readable media. Can be written on. The computer-readable medium may include program instructions, data files, data structures, or the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the present invention, or may be known and available to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs, DVDs, and magnetic media such as floptical disks. -Hardware devices specifically configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language code that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler.

As described above, in the present invention, specific matters such as specific components and the like have been described by limited embodiments and drawings, but these are provided only to help the overall understanding of the present invention, and the present invention is not limited to the above embodiments , Anyone having ordinary knowledge in the field to which the present invention pertains can make various modifications and variations from these descriptions.

Accordingly, the spirit of the present invention should not be limited to the described embodiments, and should not be determined, and all claims that are equivalent or equivalent to the scope of the claims as well as the claims to be described later belong to the scope of the spirit of the invention. .

110: an electronic terminal device that performs a correction process for a homophone collection based on speech recognition
111: vowel table holding unit 112: pronunciation string generating unit
113: correction word generation unit 114: correction processing unit
115: Alternative vowel confirmation unit 116: Similar vowel confirmation unit
117: word confirmation unit 118: correction unit
119: Font information table maintenance unit 120: Volume value confirmation unit

Claims (12)

While a plurality of vowels pre-designated as homophone vowels and a predetermined pronunciation string corresponding to each of the plurality of vowels are recorded in correspondence with each other, a predetermined similar vowel corresponding to each vowel for each of the plurality of vowels A collection table holding unit for storing and maintaining additionally recorded collection tables;
When the first word including the first vowel among the plurality of vowels is input from the user through an input device that enables input of characters, the first word is displayed on the screen, and the first word is displayed. After being displayed on the screen, if a voice corresponding to the pronunciation of the alternative vowel for correcting the first vowel is input from the user through the microphone, the first voice according to the result of recognizing the user's voice by recognizing the user's voice A pronunciation string generator for generating a pronunciation string;
A first replacement vowel corresponding to the first pronunciation string is identified among the plurality of vowels recorded in the vowel table, and the first vowel included in the first word is changed to the first alternative vowel. A correction word generation unit generating a correction word for the first word; And
A correction processing unit that replaces and displays the first word displayed on the screen with the correction word
Including,
The correction word generation unit
When the first pronunciation string is generated, a replacement vowel checking unit that checks the first replacement vowel corresponding to the first pronunciation string among the plurality of vowels recorded in the vowel table;
When the first replacement vowel is confirmed, a similar vowel checking unit that checks the first similar vowel recorded in the vowel table corresponding to the first alternative vowel;
A word checking unit checking whether the first vowel includes the same vowel as the first similar vowel; And
When it is determined that the first vowel includes the same vowel as the first similar vowel in the first word, by changing the first vowel included in the first word to the first alternative vowel, the Correction unit for processing the generation of the correction word for replacing the first word
An electronic terminal device that performs correction processing for a homophone collection based on speech recognition including a. delete According to claim 1,
The word confirmation unit
The first word is divided into units, and each of the plurality of elements constituting the first word is compared with the first similar vowel to each other to include the same vowel as the first similar vowel among the plurality of vocabularies. An electronic terminal device that performs a correction process for a homophone vowel based on a voice recognition that checks whether the first vowel includes the same vowel as the first pseudo vowel by checking whether or not it exists. According to claim 1,
The correction unit
When it is determined that the first vowel includes the first vowel in the same vowel as the first similar vowel in the first word, the first vowel among the two or more first vowels included in the first word is impersonated through the input device. An electronic terminal device that performs correction processing for a homophone vowel based on speech recognition processing the generation of the correction word for replacing the first word by changing the lately input vowel to the first replacement vowel. According to claim 1,
Font information that stores and maintains a font information table in which information on a predetermined plurality of different volume value ranges and predetermined unique fonts for each of the plurality of different volume value ranges are recorded in correspondence with each other Table holding unit; And
When a voice is input from the user through the microphone, a volume value confirmation unit to check a first volume value according to the user's voice input
Further comprising,
The correction processing unit
When the corrected word is generated, information about a first unique font recorded corresponding to a volume value range to which the first volume value belongs is checked from the font information table, and the corrected word is assigned to the first unique font. An electronic terminal device that performs correction processing for a homophonic vowel based on speech recognition that replaces and displays the first word displayed on the screen with the correction word after applying the font format. While a plurality of vowels pre-designated as homophone vowels and a predetermined pronunciation string corresponding to each of the plurality of vowels are recorded in correspondence with each other, a predetermined similar vowel corresponding to each vowel for each of the plurality of vowels Storing and maintaining additionally recorded collection tables;
When the first word including the first vowel among the plurality of vowels is input from the user through an input device that enables input of characters, the first word is displayed on the screen, and the first word is displayed on the screen. When the voice corresponding to the pronunciation of the alternative vowel for correcting the first vowel is input from the user through the microphone after being displayed on the screen, the first voice according to the result of recognizing the user's voice by recognizing the user's voice Generating a pronunciation string;
A first replacement vowel corresponding to the first pronunciation string among the plurality of vowels recorded in the vowel table is identified, and the first vowel included in the first word is changed to the first alternative vowel. Generating a correction word for the first word; And
Displaying the first word displayed on the screen with the correction word
Including,
The step of generating the correction word
When the first pronunciation string is generated, identifying the first replacement vowel corresponding to the first pronunciation string among the plurality of vowels recorded in the vowel table;
When the first replacement vowel is confirmed, checking a first similar vowel recorded in the vowel table corresponding to the first alternative vowel;
Checking whether the first vowel includes the same vowel as the first similar vowel; And
When it is determined that the first vowel is included in the first vowel as the same vowel as the first similar vowel, by changing the first vowel included in the first word to the first alternative vowel, the Processing the generation of the corrected word to replace the first word
Method of operating an electronic terminal device for performing a correction process for a homophone collection based on speech recognition including a. delete The method of claim 6,
The step of determining whether the same vowel as the first similar vowel is included is
The first word is divided into units, and each of the plurality of elements constituting the first word is compared with the first similar vowel to each other to include the same vowel as the first similar vowel among the plurality of vocabularies. A method of operation of an electronic terminal device that performs correction processing for a homophone vowel based on speech recognition to determine whether the first vowel includes the same vowel as the first pseudo vowel by checking whether the first vowel is present. The method of claim 6,
The step of processing the generation of the correction word is
When it is determined that the first vowel includes the first vowel in the same vowel as the first similar vowel in the first word, the first vowel among the two or more first vowels included in the first word is impersonated through the input device. An operation method of an electronic terminal device that performs a correction process for a homophone vowel based on speech recognition that processes the generation of the correction word to replace the first word by changing the lately input vowel to the first replacement vowel . The method of claim 6,
Storing and maintaining a font information table in which information on a predetermined plurality of different volume value ranges and predetermined unique fonts for each of the plurality of different volume value ranges are recorded in correspondence with each other; And
When a voice is input from the user through the microphone, checking a first volume value according to the user's voice input
Further comprising,
The step of replacing and displaying the correction word is
When the corrected word is generated, information about a first unique font recorded corresponding to a volume value range to which the first volume value belongs is checked from the font information table, and the corrected word is assigned to the first unique font. After applying the font format according to the method of operation of the electronic terminal device for performing a correction process for the homophone collection based on the speech recognition to replace the first word displayed on the screen with the correction word. A computer-readable recording medium recording a program for performing the method of any one of claims 6, 8, 9 or 10. A computer program stored in a storage medium for executing the method of any one of claims 6, 8, 9 or 10 through a combination with a computer.

Images