KR20170057623A - An apparatus for the linguistically disabled to synthesize the pronunciation and the script of words of a plural of designated languages - Google Patents
An apparatus for the linguistically disabled to synthesize the pronunciation and the script of words of a plural of designated languages Download PDFInfo
- Publication number
- KR20170057623A KR20170057623A KR1020150160967A KR20150160967A KR20170057623A KR 20170057623 A KR20170057623 A KR 20170057623A KR 1020150160967 A KR1020150160967 A KR 1020150160967A KR 20150160967 A KR20150160967 A KR 20150160967A KR 20170057623 A KR20170057623 A KR 20170057623A
- Authority
- KR
- South Korea
- Prior art keywords
- vocabulary
- interface
- pronunciation
- syllable
- intonation
- Prior art date
Links
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 39
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 33
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 33
- 230000007935 neutral effect Effects 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims description 42
- 238000012512 characterization method Methods 0.000 claims description 21
- 239000004744 fabric Substances 0.000 claims description 11
- 206010044565 Tremor Diseases 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 210000000214 mouth Anatomy 0.000 description 4
- 238000003825 pressing Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000001771 impaired effect Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 229910001043 Chinese silver Inorganic materials 0.000 description 1
- 241000282412 Homo Species 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 206010025482 malaise Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 210000002105 tongue Anatomy 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
- G10L13/086—Detection of language
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
- G10L13/10—Prosody rules derived from text; Stress or intonation
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Document Processing Apparatus (AREA)
Abstract
A global syllable synthesizer for synthesizing syllable, neutral, longitudinal and intonation inputted from a user according to an embodiment to form a syllable and generating the syllable; A lexical information synthesis unit for acquiring the synthesized syllable to form a vocabulary and providing a pronunciation and a Hangul notation according to the vocabulary; A multilingual vocabulary DB for classifying vocabularies having the same meaning for a vocabulary according to a plurality of languages and storing the vocabulary in a spoken form of the vocabulary for the language, An output control unit for searching for a vocabulary of a vocabulary formed based on a syllable input from the user, a vocabulary corresponding to the vocabulary of the vocabulary stored in the multilingual vocabulary DB, and selecting an output language for the searched vocabulary; And an output unit outputting the searched vocabulary according to the selected output language and spelling.
Description
In the following description, vocabularies having the same meaning in a plurality of languages are grouped together, and a database is constructed by noting the spelling of these vocabulary as well as pronounciation pronunciation information and its pronunciation in Korean, and the information contained therein is used in a language It is about Korean-based multi-lingual vocabulary input / output technology that enables the vocabulary to be written in Korean and provide a method to search through the text information.
In order to communicate between a person and a person, a mutually familiar vocabulary must be used. These vocabularies are expressed in speech or letters. There are over 6,000 languages on earth, and most people can speak only one of them, so the communication situation of humans is very closed. Although the communication technology developed by the introduction of the letter and the development of the ICT technology, it is impossible to access it if the character is unknown, and there are only about 400 languages written in the language, and the characters are different between these languages, There are many people who are restricted from communication because they can not use letters due to physical disabilities.
On the other hand, the voices of all languages are human voices. Therefore, if there is a character that expresses a voice, all languages in the world can be represented by this character. Of course, this does not mean communication, but if we add ICT technology here, human communication problems can be solved at any rate.
Hangeul has a unique sound value for each letter, and it can express any pronunciation of any language with a reasonable accuracy through the combined syllable principle of Hunminjeongeum. As such, the Arabic numerals are numerically calculated to the same 'value' in any country, so that the Korean alphabet has the same phonetic value in any language, It is possible to satisfy the enemy demand.
A problem to be solved by the present invention is to synthesize the vocabulary of the visually impaired, the visually impaired, or the illiterate person by means of a mechanical manipulation, and propose a method of expressing the vocabulary in correspondence with sound with 1: 1. We have proposed a technique to manipulate a radio transmitter and manipulate a 'national language syllable synthesizer' to produce a desired speech and display its pronunciation in Korean.
A problem to be solved by the present invention is to provide a multi-language vocabulary DB in which vocabularies of selected plural languages are grouped together and words of spelling, The present invention provides a method of searching for a vocabulary corresponding to the synthesized pronunciation of a Korean word, and outputting and displaying a pronounciation pronunciation and a spelling method in a desired language. Through this, the language disabled person can express the pronunciation of the vocabulary with correct pronunciation without speaking with his own mouth, and the blind and illiterate person provides a technique to express the desired word without spelling it by correct spelling.
According to one embodiment, a pronunciation synthesis and characterization apparatus of a multilingual vocabulary may include a user inputting a first, a second, a last, and an intonation of a syllable to be searched by a user, A global syllable synthesizer for synthesizing a pronunciation by selecting and operating a character button so as to generate a pronunciation; A lexical information synthesis unit for acquiring the synthesized syllable to form a vocabulary and providing a pronunciation and a Hangul notation according to the vocabulary; A multilingual vocabulary DB for classifying vocabularies having the same meaning for a vocabulary according to a plurality of languages and storing the vocabulary in a spoken form of the vocabulary for the language, An output control unit for searching for a vocabulary of a vocabulary formed based on a syllable input from the user, a vocabulary corresponding to the vocabulary of the vocabulary stored in the multilingual vocabulary DB, and selecting an output language for the searched vocabulary; And an output unit outputting the searched vocabulary according to the selected output language and spelling.
According to one aspect, the universal language syllable synthetizer provides a consonant interface, a vowel interface, and an intonation interface, and a pronunciation corresponding to the selected interface may be generated as the interface is selected.
According to another aspect of the present invention, the consonant interface includes a basic consonant including consonants a, b, c, d, k, g, (Loud sounds) and treble sounds (strong sounds), and the pronunciation of at least one of the loudspeak, the base sound, the hyphen and the shud can be uttered based on the position where the consonant interface is selected.
According to another aspect of the present invention, the vowel interface can be classified into a basic collection of Hangul, a vowel, a vowel, a vowel, a vowel, a vowel, a vowel, ㅕ, ㅖ, ㅠ, ㅒ, ㅖ, ㅞ, ㅘ, ㅝ, ㅞ, which are formed by the combination of ㅔ, ㅚ, ㅚ and the basic vowel of Hangul, Thereby outputting the pronunciation of the syllable.
According to another aspect of the present invention, the intonation interface may include a plurality of intonations included in each of the plurality of languages, the intonation interface being installed on the intonation interface, To provide an accent to the user.
According to another aspect of the present invention, the multilingual vocabulary DB classifies vocabularies containing the same meaning from a plurality of languages, and stores the vocabularies in the form of spelling, And can be stored so as to provide a spoken pronunciation of a vocabulary corresponding to another language including the same meaning as the vocabulary input from the user and a spelling method specific to the language.
According to an exemplary embodiment, a method for synthesizing and characterizing a multilingual vocabulary includes synthesizing a first sentence, a neutral sentence, a last sentence, and an intonation input from a user, and generating the synthesized syllable; Acquiring the synthesized syllable to form a vocabulary, and providing pronunciation and Hangul notation according to the vocabulary; Classifying vocabularies having the same meaning for a vocabulary according to a plurality of languages, storing the vocabulary in a spoken form of the vocabulary for the language, Searching for a vocabulary of a vocabulary formed based on a syllable input from the user, a vocabulary corresponding to the vocabulary of the vocabulary stored in the multilingual vocabulary DB, and selecting a language for the searched vocabulary; And outputting the searched vocabulary according to the selected language.
According to one aspect of the present invention, the step of synthesizing the synthesized syllable, neutrality, vertex and intonation inputted from the user and providing the synthesized syllable includes providing a consonant interface, a vowel interface and an intonation interface, And generating a pronunciation corresponding to the interface.
According to another aspect of the present invention, there is provided a method for generating synthesized syllable, synthesizing synthesized syllable, neutrality, utterance and intonation inputted from a user and generating synthesized syllable by synthesizing consonants a, c, And a basic consonant including the basic consonant and the basic consonant and a basic consonant including the basic consonant and the basic consonant and a basic consonant including the basic consonant and the basic consonant, And the pronunciation of at least one of the fundamental sound, the hyphenated sound, and the tremolous sound is uttered.
According to another aspect of the present invention, there is provided a method for synthesizing a sentence, a neutral sentence, a consonant, and an intonation input from the user, and generating the synthesized syllable, comprises the steps of: inputting a combination of cloth, , ㅕ, ㅛ, ㅠ, ㅒ, ㅖ, ㅘ, ㅘ, 형성된, 형성된, ㅚ, ㅚ, ㅚ, 형성된, 형성된, 복, 복, 복, 복, ㅖ, ㅖ, ㅖ, ㅖ, ㅖ, , ㅙ, ㅝ, ㅞ and providing the pronunciation of the syllable by outputting the syllable by forming a syllable in combination with the consonant as vowels are generated.
According to another aspect of the present invention, the step of synthesizing the synthesized syllable, neutrality, utterance, and intonation input from the user and synthesizing the synthesized syllable may include installing some of the intonations included in each of the plurality of languages on the intonation interface And providing the intonation to the syllable selected and formed through the consonant interface and the vowel interface as the intonation interface is selected.
According to another aspect of the present invention, there is provided a method of classifying vocabularies having the same meaning for a vocabulary according to a plurality of languages, and spelling the vocabulary for the language, Wherein the vocabularies are classified into a plurality of vocabularies having the same meaning from the language, and a spelling corresponding to the vocabulary of the plurality of languages, a pronounciation pronunciation, and a Hangul notation for the upbringing pronunciation are assigned, And storing the pronunciation of the vocabulary corresponding to another language including the meaning and the spelling of the language together.
A multilingual vocabulary pronunciation synthesizing and characterizing apparatus according to an embodiment synthesizes pronunciation of a vocabulary to be operated by manipulating a vocabulary of a voice and displays it in Korean and finds a standard pronunciation and a standard spelling method of a desired language, Non-Speakers and Non-Speakers Even non-literate speakers can provide the words they want to express in standard spelling and standard spelling of the desired language, and provide them to overcome language difficulties.
The multilingual vocabulary pronunciation synthesizing and characterizing apparatus according to an exemplary embodiment allows a user who is accustomed to a sounding letter board or a normal person without a disorder to input a voice by pressing a desired letter button like a general dial without composing sound.
The multi-lingual phonetic pronunciation synthesis and characterization apparatus according to an embodiment executes translation into a desired language by selecting one or more languages. Through this, it is possible to solve the problem of language caused by differences of characters, differences of language, illiteracy and physical disability, as well as disruption of communication caused by the existence of characters. Also, although Hangul does not appear on the surface, it will operate on the basis of the system and will inform the world of the value of Hangul.
1 is a block diagram for explaining a configuration of a pronunciation synthesizing and characterizing apparatus of a multilingual vocabulary according to an embodiment.
FIG. 2 is a diagram showing the types of basic characters and intonation in the pronunciation synthesis and characterization apparatus of a multilingual vocabulary according to an embodiment.
FIG. 3 is a diagram for providing ten basic consonants of a multilingual vocabulary through phonetic consonant interfaces in a pronunciation synthesizing and characterizing apparatus, in which voices, fundamental sounds, audible sounds, and whistles are uttered.
FIG. 4 is a diagram illustrating a configuration of a Hangul vowel through a vowel interface in a pronunciation synthesizing and characterizing apparatus of a multilingual vocabulary according to an exemplary embodiment and providing pronunciation to be uttered.
5 is a diagram for explaining a multi-language vocabulary synthesis and characterization apparatus according to an embodiment of the present invention.
Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.
1 is a block diagram for explaining a configuration of a pronunciation synthesizing and characterizing apparatus of a multilingual vocabulary according to an embodiment.
A syllable can be a minimal unit of speech according to human vocabulary consisting of initial, neutral and intonation, initial, neutral, longitudinal and intonation. In the embodiments, the beginning is a combination of 10 basic consonants and a basic consonant in Hangul, 10 a basic vowel in Hangul is a combination of basic vowels, and a vowel is a combination of 10 basic consonants in Hangul and a basic consonant It can be expressed as consonant, and the syllable has its own intonation, so it can be expressed in speech and Hangul notation.
The multilingual vocabulary synthesizing and characterizing apparatus 100 is intended to provide a convenient vocabulary generator for a person who can not speak, a person who can not speak, and a person who can not read a character. For example, A
The multilingual vocabulary synthesizing and characterizing apparatus 100 provides a consonant interface, a vowel interface, and an intonation interface for each desired pronunciation of a desired speech synthesizer and a Korean word, And to reproduce the appropriate accent.
The universal
The common language
In other words, the multi-lingual phonetic synthesis and characterization apparatus transmits the synthesized phonetic syllables through the respective interfaces to the lexical
The multi-language
The lexical
The multilingual vocabulary DB 130 classifies vocabularies having the same meaning for vocabularies according to a plurality of languages, and can organize and store the vocabularies in the spelling of the selected language, the pronunciation of the selected language, and the Korean pronunciation of the pronunciations. The multi-language vocabulary DB 130 classifies vocabularies having the same meaning from a plurality of languages and stores the vocabularies, and the spelling corresponding to the vocabulary of the plurality of languages and the Korean pronunciation And may also store the pronunciation of the vocabulary corresponding to another language including the same meaning as the vocabulary input from the user and the spelling of the language.
At this time, the
The
The
FIG. 2 is a diagram showing the types of basic characters and intonation in the pronunciation synthesis and characterization apparatus of a multilingual vocabulary according to an embodiment.
Since the consonants and vowels of Hunminjeongum are made on the basis of the characteristic activities of the human oral cavity, they can express any syllable by choosing the representative basic characters shown in Hunminjeongeum and using them (in Hunminjeongeum, this is called collective sickness.
For example, the current Korean alphabet is composed of 14 consonants (a, b, c, d, k, f, g, o, ㅕ, ㅗ, ㅛ, ㅜ, ㅠ, ㅡ, ㅣ), the total number of 24 consonants can be obtained by sb, a, c, . Therefore, the basic consonants are compressed to 10 except for,,,, ㅌ, and ㅍ, and ㅑ, ㅕ, ㅛ, and 중 among 10 vowels omit them with phonetic pronunciation when a, ㅓ, ㅗ, Instead, they are compressed into 10 basic vowels, including short vowels ㅐ, ㅔ, ㅚ and Hunminjeongeum (ㆍ) which can not be synthesized.
ㅑ = ㅑ + a; ㅕ = ㅣ + ㅓ; ㅛ = ㅣ + ㅗ; ㅠ = ㅣ + ㅜ
Syllables can have unique accents depending on the language, so proper accent should be chosen to complete the syllable marking. Thus, the multilingual vocabulary synthesizing and characterizing device is accented by 4 accents of Chinese and accents of English, 3 vocabulary of Vietnamese
) And 4 ) Can be provided to choose from ten commonly used accents.FIG. 2 is a table showing 10 basic consonants, 10 basic vowels, and intonation.
It is a combination of the above, a, c, and b,
) Phenomenon. Theoretically, any consonant can have the same effect. Similarly, the consonant is converted to a ).
In addition, if consonants are combined with the same consonant,
)do.
Accordingly, the basic consonant may have the following four types.
Multilingual Vocabulary Pronunciation Synthesis and characterization devices can be set by judging that Chinese tongues sh and zh ch are made to meet with,,,, and 혓 respectively. In addition, the multilingual vocabulary pronunciation synthesis and characterization apparatus may be configured such that a combination of the words "f" and "f" together with "ㅇ" and "ㅂ" form a v-pronunciation.
In order to mechanically implement the above pronunciation changes, an interface for ten basic consonants can be provided. FIG. 3 is a diagram for providing ten basic consonants of a multilingual vocabulary through phonetic consonant interfaces in a pronunciation synthesizing and characterizing apparatus, in which voices, fundamental sounds, audible sounds, and whistles are uttered. FIG. 3 illustrates a configuration of a sounding consonant interface, for example, a consonant interface and a consonant interface.
As shown in FIG. 3, the consonant interface of each consonant interface for the consonant has a consonant with the consonants A, B, C, D, K, F, G, (Loud sounds), fundamental sounds, loud sounds (loud sounds), and tremble (strong sounds). At this time, depending on the position of the consonant interface, it may be provided to utter the lyme-base-tone-percussion-percussive sound. At least one of the following can be uttered based on the position at which the consonant interface is selected: yell, base, audible, and shaky. For example, a multilingual vocabulary pronunciation synthesizing and characterizing device can select a desired consonant from a user through a consonant interface, and the pronunciation corresponding to the selected consonant can be selected and spoken.
However, in the consonant interface, both the lunar and the hypnotism are both ㅇㅇ, and the ㅎ button has both loud and loud sounds, and one of them becomes meaningless. In addition, there may be some pronunciations of 10 basic consonants that are not actually used in any language, but it is necessary to secure the function of pronunciation which is not currently used for the expression of the national pronunciation. It is possible to synthesize phonemic pronunciation with the four-phonetic pronunciation of this basic consonant.
The pronunciation synthesizing and characterizing apparatus of the multilingual vocabulary can combine vowels in the same manner as in Fig. 4 as the desired consonants are selected from the user through the consonant interface and vocalized. FIG. 4 is a diagram illustrating a configuration of a Hangul vowel through a vowel interface in a pronunciation synthesizing and characterizing apparatus of a multilingual vocabulary according to an exemplary embodiment and providing pronunciation to be uttered.
The collection of Hunminjeongeum consists of a combination of cloth (), cloth () and cloth (). If you pronounce the cloth with the mouth shape as l (ㅣ) and you pronounce the cloth (ㆍ) with the mouth shape as) (.), It becomes.. In this way, there are 10 basic vowels, ㅣ, a, ㅓ, ㅡ, ㅗ, ㅜ, ㅐ, ㅔ, ㅚ,.. As in consonants, basic vowels can be merged to implement any vowel. For example, the wa in English is ㅗ + a,
Can be expressed as ㅜ + ㅣ.Multilingual Vocabulary Pronunciation Synthesis and Characterization System is composed of vocabulary composed of a point (cloth), a vertical line (in), and a horizontal line (ground) on the left and right sides of the cloth () -) can be arranged to form a vowel interface as shown in FIG.
The multilingual vocabulary pronunciation synthesis and characterization device can implement a vowel shape input from a user by providing a vowel interface. For example, a vowel and a vowel are on the right side of a lie, so the left lie should be used, and ㅓ and ㅕ should be on the right. Similarly, ㅗ and ㅛ should write the lower part (ㅡ), ㅜ and ㅠ (upper part). To enter ㅘ, you have to press the bottom (ㅡ), left (ㅣ), and cloth (ㆍ). The multilingual vocabulary pronunciation synthesizing and characterizing apparatus can combine pronunciation of consonants and vowels in the same manner as in FIGS. 3 and 4, so that pronunciation combined with initial and neutral can be uttered.
The following is an example of how to implement a vowel.
The pronunciation synthesis and characterization device of the multilingual vocabulary can be selected as a consonant after selecting the consonant after inputting the initial, neutral, and intonation, and the syllable pronunciation can be completed and vocalized. If the syllable has no continuity, Can proceed. At this time, a desired syllable is input and implemented by the user, so that when a vocabulary input is finished, a vocabulary input can be terminated by selecting a vocabulary completion interface.
5 is a diagram for explaining a multi-language vocabulary synthesis and characterization apparatus according to an embodiment of the present invention.
FIG. 5 shows the shape of a syllable synthesizer for a national language completed by arranging ten intonation interfaces together with a consonant interface and a vowel interface as described above. However, FIG. 5 exemplifies the universal language pitch synthesizer, and is not limited thereto. Similarly, the shapes and arrangement of the consonant interface, the vowel interface, and the intonation interface may be different.
The multi-lingual phonetic synthesis and characterization apparatus can provide a phonetic synthesizer for pronunciation and output through a terminal. For example, the terminal may be a fixed terminal implemented as a computer device or a mobile terminal. Examples of the terminal include a smart phone, a mobile phone, a navigation system, a computer, a notebook, a terminal for digital broadcasting, a PDA (Personal Digital Assistants), a PMP (Portable Multimedia Player), a tablet PC and the like.
Through this, the user can generate a vocabulary based on the desired consonant interface, vowel interface, and intonation interface through the terminal. Multilingual Vocabulary Pronunciation The synthesizing and characterizing apparatus can output spelling and pronunciation pronunciations according to a language according to a vocabulary input from a user.
Language speech can be expressed in syllables, and syllables usually consist of [prepositional + neutral + prosperous], but often they are omitted. The sounds of these syllables can be made by manipulating the voiced consonant interface and vowel interface described above from the user. For example, to manipulate the pronunciation of the word 'father', first select 'o' in the consonant interface and 'a' in the vowel interface, and 'a' in the consonant interface and ''ㅓ' and 'Ji' are clicked on the interface corresponding to 'ゃ' and 'ㅣ'. Three syllables such as 'ah', 'bur', and 'ji' all have no continuity, so that three syllables can be formed naturally. When the vocabulary is completed, the vocabulary completion interface can be selected to terminate the vocabulary input. Also, 'father'
And the second syllable of < RTI ID = 0.0 > First, the consonant interface is created by pressing the consonant interface and the consonant interface, and the long vowel is generated by pressing 'a' twice on the vowel interface. And to express the accent, The accent may be uttered.Even if you do not select the accent, you can search vocabulary by establishing pronunciation of Korean vocabulary and Hangul notation.
In the case of., Press the consonant interface and the consonant interface, enter 'ㅓ' and press'''. here And It is necessary to press both interfaces simultaneously to indicate that it is a consonant.As shown in FIG. 2, basic consonants and basic vowels, and intonation types can be assigned a numerical value from 0 to 9. Using these numerical symbols, the pronunciation can be expressed numerically, so even if the pronunciation is not used, the numerical value can be displayed. For example, a = 100, a = 100, a = 111, a = 1, a = 11, a = a, . In addition, ㅌ and 는 are similar in pronunciations, and it is difficult to distinguish them from each other. It is not known that these two pronunciations are similar pronunciation. However, since they are marked 39 and 69 respectively and share the
For example, 'father' is syllable and 'a / ver / zi' is used, and the above numerical symbol can be expressed as [0.2.] [6.3.] [8.1.]. Here, the vowels are distinguished by points before and after. In addition, the English 'father'
Can be separated into two syllables of [69.22 (5).] [03.2.4]. 22 (5) represents the neutral "a" of the word "a", which is regarded as a continuation of the word "a" twice. Chinese silver Two syllables of The four- 'Can be displayed as [96.6 (4).] [89.1 (1) .2] because it is one-sided.Such a speech can be obtained by selecting the corresponding consonant for each syllable in the case of the initial, neutral, intonation, and utterance in the above-mentioned syllable synthesizer. If you list the consonants and vowels selected in this process, it becomes the Hangul notation of this vocabulary.
Since the pronunciation synthesized above is a mechanical sound, it may be different from the pronunciation of the actual native speaker. Accordingly, it is possible to inform the correct pronunciation by listening to the pronunciations corresponding to the mechanical sounds, and at the same time, to confirm that the desired pronunciation is synthesized properly. To do this, you need to include all the recorded vocabulary information in all the vocabularies stored in the 'Multilingual Vocabulary DB'. At this time, the training record information should be recorded together with the pronunciation in Hangul, and the synthesized machine sounds are also automatically displayed in Korean, so that the two will be compared to find a matching vocabulary. If a matching vocabulary can not be found, several similar words may be presented in order to allow the user to select.
Multilingual vocabulary DB collects vocabularies of all target languages that have the same meaning for a specific vocabulary, and expresses the spoken information recorded by the spelling of the language and native speakers recorded for each, Information '. The vocabularies of the target language included in the multilingual vocabulary DB can be searched with the pronunciation information in Korean because the pronunciation of the vocabulary is written in Korean.
In the above description, the word " vocabulary " is used, but it is not necessarily targeted to only one vocabulary. For example, frequently used short texts such as Thank you and Thank you very much can be treated as a single vocabulary, and can be broadly used by being stored in a multilingual vocabulary DB.
A multilingual vocabulary pronunciation synthesizing and characterizing apparatus according to an embodiment synthesizes pronunciation of a vocabulary to be operated by manipulating a vocabulary of a voice and displays it in Korean and finds a standard pronunciation and a standard spelling method of a desired language, Non-Speakers and Non-Speakers Even non-literate speakers can provide the words they want to express in standard spelling and standard spelling of the desired language, and provide them to overcome language difficulties.
The multi-lingual phonetic pronunciation synthesis and characterization apparatus according to an embodiment executes translation into a desired language by selecting one or more languages. Through this, it is possible to solve the problem of language caused by differences of characters, differences of language, illiteracy and physical disability, as well as disruption of communication caused by presence or absence of characters. Also, although Hangul does not appear on the surface, it will operate on the basis of the system and will inform the world of the value of Hangul.
The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the apparatus and components described in the embodiments may be implemented as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit, a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For ease of understanding, the processing apparatus may be described as being used singly, but those skilled in the art will recognize that the processing apparatus may have a plurality of processing elements and / As shown in FIG. For example, the processing unit may comprise a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as a parallel processor.
The software may include a computer program, code, instructions, or a combination of one or more of the foregoing, and may be configured to configure the processing device to operate as desired or to process it collectively or collectively Device can be commanded. The software and / or data may be in the form of any type of machine, component, physical device, virtual equipment, computer storage media, or device , Or may be permanently or temporarily embodied in a transmitted signal wave. The software may be distributed over a networked computer system and stored or executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.
The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.
While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced.
Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.
Claims (12)
A lexical information synthesis unit for acquiring the synthesized syllable to form a vocabulary and providing a pronunciation and a Hangul notation according to the vocabulary;
A multilingual vocabulary DB for classifying vocabularies having the same meaning for a vocabulary according to a plurality of languages and storing the vocabulary in a spoken form of the vocabulary for the language,
An output control unit for searching for a vocabulary of a vocabulary formed based on a syllable input from the user, a vocabulary corresponding to the vocabulary of the vocabulary stored in the multilingual vocabulary DB, and selecting an output language for the searched vocabulary; And
And outputting the searched vocabulary to a spelling method and a pronouncing pronunciation in accordance with the selected output language
And a speech synthesizing and characterizing device for a multilingual vocabulary.
The syllable synthesizer according to claim 1,
A consonant interface, a vowel interface and an intonation interface are provided, and as the interface is selected, a pronunciation corresponding to the selected interface is generated
Wherein the speech synthesis and characterization apparatus of the multi-lingual vocabulary is characterized in that the speech synthesis /
Wherein the consonant interface comprises:
The basic consonants including the consonants a, b, c, d, k, f, g, h, and o and the phonetic sounds of the basic consonants, the fundamental sounds, the lull sounds, Wherein at least one of the tongue, the base tongue, the tongue and the tremble is uttered based on a position at which the consonant interface is selected
Wherein the speech synthesis and characterization apparatus of the multi-lingual vocabulary is characterized in that the speech synthesis /
The collection interface comprises:
Based on the combination of cloth, ㅡ, and ㅣ, the basic vocabulary of Hangul ㅣ ㅓ ㅓ ㅗ ㅗ ㅐ ㅐ ㅔ ㅔ ㅚ ㅚ and the basic vowel of Hangul ㅑ ㅕ ㅛ ㅛ And generating a syllable by combining the consonants as the vowels are generated, thereby generating a pronunciation of the syllable
Wherein the speech synthesis and characterization apparatus of the multi-lingual vocabulary is characterized in that the speech synthesis /
Said intonation interface comprising:
The method comprising the steps of: mounting a part of the intonation included in each of the plurality of languages on the intonation interface, and providing the intonation to the syllable selected and formed through the consonant interface and the vowel interface as the intonation interface is selected
Wherein the speech synthesis and characterization apparatus of the multi-lingual vocabulary is characterized in that the speech synthesis /
The multilingual vocabulary DB includes:
A plurality of vocabularies having the same meaning from a plurality of languages are categorized and stored, and a spelling corresponding to the vocabulary of the plurality of languages, a pronouncing pronunciation, and a Hangul notation for the upbringing pronunciation are given, And the spelling of the vocabulary corresponding to another language including the same meaning and the spelling of the language are also provided together
Wherein the speech synthesis and characterization apparatus of the multi-lingual vocabulary is characterized in that the speech synthesis /
Acquiring the synthesized syllable to form a vocabulary, and providing pronunciation and Hangul notation according to the vocabulary;
Classifying vocabularies having the same meaning for a vocabulary according to a plurality of languages, storing the vocabulary in a spoken form of the vocabulary for the language,
Searching a vocabulary of a vocabulary formed based on a syllable input from the user and a vocabulary corresponding to the vocabulary of the vocabulary stored in the multilingual vocabulary DB and selecting an output language for the searched vocabulary; And
Outputting the searched vocabulary to a spelling method and a pronounciation according to the selected output language
A method for synthesizing and characterizing pronunciation of a multilingual vocabulary, comprising:
Synthesizing the sentence, the neutral, the utterance, and the intonation input from the user, and voicing the synthesized syllable,
Providing a consonant interface, a vowel interface and an intonation interface, and generating a pronunciation corresponding to the selected interface as the interface is selected
A method for synthesizing and characterizing pronunciation of a multilingual vocabulary, comprising:
Synthesizing the sentence, the neutral, the utterance, and the intonation input from the user, and voicing the synthesized syllable,
The basic consonants including the consonants a, b, c, d, k, f, g, h, and o and the phonetic sounds of the basic consonants, the fundamental sounds, the lull sounds, Wherein at least one of the tongue, the base tongue, the tongue and the tremble is uttered based on a position at which the consonant interface is selected
A method for synthesizing and characterizing pronunciation of a multilingual vocabulary, comprising:
Synthesizing the sentence, the neutral, the utterance, and the intonation input from the user, and voicing the synthesized syllable,
Based on the combination of cloth, ㅡ, and ㅣ, the basic vocabulary of Hangul ㅣ ㅓ ㅓ ㅗ ㅗ ㅐ ㅐ ㅔ ㅔ ㅚ ㅚ and the basic vowel of Hangul ㅑ ㅕ ㅛ ㅛ And generating a syllable by combining the consonants as the vowels are generated, thereby producing a pronunciation of the syllable
A method for synthesizing and characterizing pronunciation of a multilingual vocabulary, comprising:
Synthesizing the sentence, the neutral, the utterance, and the intonation input from the user, and voicing the synthesized syllable,
The method comprising the steps of: mounting a part of the intonation included in each of the plurality of languages on the intonation interface, and providing the intonation to the syllable selected and formed through the consonant interface and the vowel interface as the intonation interface is selected
A method for synthesizing and characterizing pronunciation of a multilingual vocabulary, comprising:
A method of classifying vocabularies having the same meaning with respect to vocabulary according to a plurality of languages and organizing the vocabulary in spoken words of the vocabulary,
A plurality of vocabularies having the same meaning from a plurality of languages are categorized and stored, and a spelling corresponding to the vocabulary of the plurality of languages, a pronouncing pronunciation, and a Hangul notation for the upbringing pronunciation are given, And a spelling method of a vocabulary corresponding to another language including the same meaning
A method for synthesizing and characterizing pronunciation of a multilingual vocabulary, comprising:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150160967A KR20170057623A (en) | 2015-11-17 | 2015-11-17 | An apparatus for the linguistically disabled to synthesize the pronunciation and the script of words of a plural of designated languages |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150160967A KR20170057623A (en) | 2015-11-17 | 2015-11-17 | An apparatus for the linguistically disabled to synthesize the pronunciation and the script of words of a plural of designated languages |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20170057623A true KR20170057623A (en) | 2017-05-25 |
Family
ID=59051095
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020150160967A KR20170057623A (en) | 2015-11-17 | 2015-11-17 | An apparatus for the linguistically disabled to synthesize the pronunciation and the script of words of a plural of designated languages |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR20170057623A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110264994A (en) * | 2019-07-02 | 2019-09-20 | 珠海格力电器股份有限公司 | A kind of phoneme synthesizing method, electronic equipment and smart home system |
KR20220167362A (en) * | 2020-09-03 | 2022-12-20 | 정진우 | Speech output device and method for language with rhythm and prosody |
KR20220167361A (en) * | 2020-09-03 | 2022-12-20 | 정진우 | Rhythm display device and method for language with rhythm and prosody |
KR20220167359A (en) * | 2020-09-03 | 2022-12-20 | 정진우 | Hangul input device and method for language with rhythm and prosody |
KR102564985B1 (en) * | 2022-12-07 | 2023-08-10 | 목승환 | Apparatus for converting key input into voice signal and method thereof |
-
2015
- 2015-11-17 KR KR1020150160967A patent/KR20170057623A/en not_active Application Discontinuation
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110264994A (en) * | 2019-07-02 | 2019-09-20 | 珠海格力电器股份有限公司 | A kind of phoneme synthesizing method, electronic equipment and smart home system |
KR20220167362A (en) * | 2020-09-03 | 2022-12-20 | 정진우 | Speech output device and method for language with rhythm and prosody |
KR20220167361A (en) * | 2020-09-03 | 2022-12-20 | 정진우 | Rhythm display device and method for language with rhythm and prosody |
KR20220167359A (en) * | 2020-09-03 | 2022-12-20 | 정진우 | Hangul input device and method for language with rhythm and prosody |
KR102564985B1 (en) * | 2022-12-07 | 2023-08-10 | 목승환 | Apparatus for converting key input into voice signal and method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7142333B2 (en) | Multilingual Text-to-Speech Synthesis Method | |
US8447610B2 (en) | Method and apparatus for generating synthetic speech with contrastive stress | |
US20070203704A1 (en) | Voice recording tool for creating database used in text to speech synthesis system | |
CN101156196A (en) | Hybrid speech synthesizer, method and use | |
KR20170057623A (en) | An apparatus for the linguistically disabled to synthesize the pronunciation and the script of words of a plural of designated languages | |
US8155963B2 (en) | Autonomous system and method for creating readable scripts for concatenative text-to-speech synthesis (TTS) corpora | |
KR20140071070A (en) | Method and apparatus for learning pronunciation of foreign language using phonetic symbol | |
CN107041159B (en) | Pronunciation assistant | |
Thu et al. | HMM based myanmar text to speech system. | |
JP4964695B2 (en) | Speech synthesis apparatus, speech synthesis method, and program | |
US20070203706A1 (en) | Voice analysis tool for creating database used in text to speech synthesis system | |
JP2005031150A (en) | Apparatus and method for speech processing | |
Mittal et al. | Speaker-independent automatic speech recognition system for mobile phone applications in Punjabi | |
KR101553469B1 (en) | Apparatus and method for voice recognition of multilingual vocabulary | |
Archibald | Segmental and Prosodic Evidence for Property-by-Property Transfer in L3 English in Northern Africa. Languages 7: 28 | |
Kaveri et al. | A novel approach for hindi text description to speech and expressive speech synthesis | |
KR102112059B1 (en) | Method for making hangul mark for chinese pronunciation on the basis of listening, and method for displaying the same, learning foreign language using the same | |
Khamdamov et al. | Syllable-Based Reading Model for Uzbek Language Speech Synthesizers | |
JP6340839B2 (en) | Speech synthesizer, synthesized speech editing method, and synthesized speech editing computer program | |
JP2006302149A (en) | Japanese input device | |
JP5125404B2 (en) | Abbreviation determination device, computer program, text analysis device, and speech synthesis device | |
KR20140059910A (en) | An universal text to speech system based on the phonetic description of languages | |
Kaur et al. | BUILDING AText-TO-SPEECH SYSTEM FOR PUNJABI LANGUAGE | |
JP4208819B2 (en) | Speech synthesis dictionary registration method and apparatus | |
IMRAN | ADMAS UNIVERSITY SCHOOL OF POST GRADUATE STUDIES DEPARTMENT OF COMPUTER SCIENCE |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E601 | Decision to refuse application |