A pronunciation annotation method, system and program product for english natural phonics

Abstract

This application discloses a method, system, and computer program product for phonetic annotation of English phonics. The method includes: obtaining a target word and its corresponding syllable separator and International Phonetic Alphabet (IPA); determining whether the word is a polysyllabic word based on the syllable separator; rewriting the IPA for monosyllabic and polysyllabic words according to the correspondence between phonics phonetic annotation and IPA; rewriting monosyllabic words using the first font or first font size, and rewriting polysyllabic words by using the first font or first font size for syllables other than weak syllables, and rewriting weak syllables using the second font or second font size; adding spaces to the corresponding positions of the rewritten string according to the position of the syllable separator in the target word to generate English phonics phonetic annotation. This application uses IPA rewriting for English phonics phonetic annotation, applicable to 100% of words, with simple rules, simplified annotation, and easy to learn and master.

Description

Technical Field

[0001] This invention relates to the field of English pronunciation annotation technology, specifically to a pronunciation annotation method, system, and computer program product for English phonics. Background Technology

[0002] Phonetic transcription is an important method for pronouncing English words, and there are currently two main methods: the International Phonetic Alphabet (IPA) and phonics.

[0003] However, both of these phonetic notation methods have their own shortcomings. The problems with the International Phonetic Alphabet (IPA) are threefold: First, many of the 48 phonetic symbols are unfamiliar symbols outside the 26 letters of the English alphabet, making it impossible to directly correlate them with the alphabet and thus severing the relationship between pronunciation and spelling, preventing the ability to read words from sight and write words from sound. Second, many of its concepts are abstract and difficult to understand, such as front vowels, back vowels, open and closed diphthongs, central diphthongs, plosives, fricatives, lateral consonants, consonants, voiceless consonants, and voiced consonants. Third, many special symbols in the phonetic symbols are inconvenient to annotate and format.

[0004] Current phonics pronunciation annotation methods, while aiming to enable word reading and spelling without relying on any phonetic system, have several drawbacks: First, they are not suitable for 100% of words, especially multi-syllable words. Second, they require memorizing a large number of letter combination rules, resulting in high learning costs and poor effectiveness. Third, almost every letter combination rule has numerous exceptions. Summary of the Invention

[0005] To address the aforementioned shortcomings, the technical problem to be solved by this invention is to provide a method, system, and computer program product for phonetic annotation of English phonics, which visualizes the correspondence between word pronunciation and spelling, thereby solving the problems of narrow applicability and high learning difficulty of existing English phonics phonetic annotation techniques.

[0006] Therefore, the first aspect of this application provides a method for phonetic annotation in English phonics, comprising the following steps: Obtain the target word, its syllable separator, and its International Phonetic Alphabet (IPA) symbol; the target word is an English word. Based on the syllable separators of the target word, determine whether the target word is a polysyllabic word; if there is at least one syllable separator, the target word is a polysyllabic word; if there is no syllable separator, the target word is a monosyllabic word. Based on the correspondence between phonics pronunciation symbols and the International Phonetic Alphabet (IPA), the IPA symbols for monosyllabic and polysyllabic words are rewritten separately, including: For monosyllabic words, rewrite them using the first font or the first font size; For multi-syllable words, syllables other than weak syllables are rewritten using the first font or first font size, while weak syllables are rewritten using the second font or second font size. Based on the position of the syllable separator in the target word, spaces are added at the corresponding positions in the rewritten string to separate the syllables, generating pronunciation annotations for English phonics. The weight of the second font is less than that of the first font, and the height of the second font size is less than that of the first font size. The method for identifying weak syllables in a word based on its International Phonetic Alphabet (IPA) transcription is as follows: If a syllable in the International Phonetic Alphabet (IPA) of a target word meets both of the following conditions, then that syllable is a weak syllable: it has no accent mark, and the vowel in that syllable is […]. ] or [ɪ].

[0007] In the above technical solution, preferably, different acquisition modes are selected according to the specific application to acquire the target word. These acquisition modes include input mode, word selection mode, and photo capture mode. It is suitable for various application scenarios, such as: it can be designed as a PC application running in the background; it can be designed as a browser plugin; it can be designed as a mobile APP or mini-program; it can be designed as an AI intelligent agent, etc., making it convenient to use.

[0008] In the above technical solution, preferably, the International Phonetic Alphabet (IPA) symbol and syllable separators corresponding to the target word are obtained using an existing online English dictionary. Compared with building an IPA database, this method is faster to deploy, consumes fewer resources, and reduces the risk of copyright disputes.

[0009] In the above technical solution, preferably, the phonics pronunciation annotation uses the 26 English letters and their variants. These variants include adding underlines, changing to italics, altering font weight or size, and changing color grayscale, or combinations thereof. This implementation ensures that the phonics pronunciation annotation corresponds to the 26 letters, does not use special symbols, and does not require the installation of complex fonts. This makes it easier to understand and master, simplifies annotation, and is particularly suitable for mobile applications.

[0010] In the above technical solution, preferably, a database or table of corresponding rewriting relationships between English International Phonetic Alphabet and phonics pronunciation annotations is constructed. The database or table includes both British and American pronunciations of the same phoneme, and is rewritten in response to the user's selection of British or American pronunciation.

[0011] In the above technical solution, preferably, the silent letters in the target word are marked with a lighter format than the phonological letters for natural pronunciation. For both monosyllabic and polysyllabic words, the following methods are used to identify the silent letters in the target word: For monosyllabic words, the target word is compared with the letters in the phonics pronunciation annotation from front to back. The extra letters in the target word are the silent letters. The silent letters are inserted into the corresponding positions and annotated with a lighter format than the pronunciation letters. For multi-syllable words, the target word is divided into multiple parts according to syllable separators. Each part is identified and labeled using the method described above for identifying silent letters in monosyllable words, and then combined.

[0012] A second aspect of this application provides a annotation system for English phonics, comprising: The first acquisition unit is used to acquire a target word, wherein the target word is an English word; The second acquisition unit is used to acquire the syllable separator and international phonetic symbol corresponding to the target word; The determination unit is used to determine whether a target word is a polysyllabic word based on the syllable separators of the target word; if there is at least one syllable separator, the target word is a polysyllabic word; if there is no syllable separator, the target word is a monosyllabic word. The rewriting annotation unit is used to rewrite the International Phonetic Alphabet (IPA) symbols for monosyllabic and polysyllabic words based on the correspondence between phonics pronunciation annotations and IPA symbols. The rewriting annotation unit includes a monosyllabic word rewriting annotation unit, a polysyllabic word rewriting annotation unit, and a weak syllable recognition unit. The monosyllabic word rewriting annotation unit uses the first font or the first font size for rewriting; The multisyllable word rewriting and annotation unit rewrites syllables other than weak syllables using a first font or first font size, and rewrites weak syllables using a second font or second font size. Based on the position of the syllable separator in the target word, it adds spaces at the corresponding positions in the rewritten string to separate the syllables, generating pronunciation annotations for English phonics. The weight of the second font is less than that of the first font, and the height of the second font size is less than that of the first font size. The weak syllable recognition unit identifies a syllable as a weak syllable based on the following two conditions being met in the International Phonetic Alphabet of the target word: there is no stress mark, and the vowel in the syllable is […]. ] or [ɪ].

[0013] In the above system, preferably, it also includes a database or table of corresponding rewriting relationships between English International Phonetic Alphabet and phonics pronunciation annotations. The database or table of corresponding rewriting relationships includes both British and American pronunciations of the same phoneme. In response to the user's selection of British or American pronunciation, the annotation unit is rewritten accordingly. Phonics pronunciation annotations use the 26 English letters and their variations, including adding underlines, changing to italics, changing the weight or size of the letter, and changing the grayscale of the color or a combination thereof. Silent letters are annotated in a lighter format than the phonics letters.

[0014] Preferably, the system further includes: The silent letter annotation unit for monosyllabic words compares the target word with the letters in the phonics pronunciation annotation from front to back. The extra letters in the target word are the silent letters. The silent letters are inserted into the corresponding positions and annotated with a lighter format than the pronunciation letters. The silent letter annotation unit for monosyllabic words divides the target word into multiple parts based on syllable separators. Each part is identified and annotated using the method described above for identifying silent letters in monosyllabic words, and then the parts are combined.

[0015] A third aspect of this application provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the above-described method for phonetic transcription of English phonics.

[0016] As can be seen from the above technical solutions, the pronunciation annotation method, system, and computer program product for English phonics provided by this invention solve the problems of narrow applicability and inconvenience of existing phonics pronunciation annotation methods. Compared with the prior art, this invention has the following beneficial effects: This application utilizes the International Phonetic Alphabet (IPA) to annotate the pronunciation of English phonics, visualizing the correspondence between pronunciation and spelling. It is applicable to 100% of words (especially multi-syllable words), and the rules are simple and the annotation is convenient, making it easier to learn and master English pronunciation.

[0017] In addition, the annotation uses 26 English letters and their variants, without using special symbols or installing complex fonts, which makes it easier to understand and master, and also simplifies the annotation process. Attached Figure Description

[0018] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the embodiments of the present invention or the prior art will be briefly introduced and explained below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart of the pronunciation annotation method for English phonics provided by the present invention; Figure 2This is a diagram showing the word structure and IPA representation of the word "fate" in the Longman online dictionary. Figure 3 This is a diagram showing the word structure and IPA symbol for the word "information" in the Longman online dictionary. Figure 4 Example diagrams of primary and secondary accent symbols in the International Phonetic Alphabet; Figure 5 This is a diagram showing the correspondence between the International Phonetic Alphabet and the phonetic transcription in this invention.

[0020] Figure 6 This is an example diagram illustrating the rewriting of short vowels in this invention; Figure 7 This is an example diagram illustrating the rewriting of long vowels in this invention; Figure 8 This is an example diagram illustrating the rewriting of diphthongs in this invention; Figure 9 This is an example diagram illustrating the rewriting of consonants in this invention; Figure 10 This is an example diagram illustrating the rewriting of monosyllabic words containing silent letters in this invention; Figure 11 This is an example diagram illustrating the rewriting of multisyllabic words containing silent letters and vowels in this invention. Figure 12 Example diagram of word rewriting containing two accent marks in this invention; Figure 13 This is an example diagram illustrating the application of this invention to the annotation of the entire sentence; Figure 14 This is an example diagram illustrating the application of this invention to annotation of an entire paragraph; Figure 15 This is a schematic diagram of the user interface for application example 2 of the present invention; Figure 16 This is a schematic diagram of the user interface for application example 2 of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] To provide a clearer explanation and description of the technical solution and implementation of the present invention, several preferred specific embodiments for implementing the technical solution of the present invention are described below.

[0023] It should be noted that the directional terms such as "inner" and "outer", "front" and "back" and "left" and "right" in this article are based on the product's usage status. Obviously, the use of these directional terms does not limit the scope of protection of this solution.

[0024] like Figure 1 As shown, this application provides a method for phonetic annotation in English phonics, comprising the following steps: Step 110: Obtain the target word, which is an English word.

[0025] In this step, different acquisition modes can be selected depending on the specific application. For example, input mode, word selection mode, or photo mode.

[0026] The input mode refers to manually or verbally inputting the target word in the input box of the application interface, or inputting it through copy and paste. Additionally, the input mode also includes importing text files, such as Word documents and TXT documents, which is suitable for publishers and other organizations to annotate entire books or long documents.

[0027] If the input is a sentence, it is split according to the spaces between words to obtain each target word.

[0028] In web browsing and article reading scenarios, a word-selection mode can be used to obtain target words. Specifically, the system monitors word-selection operations in real time and responds by obtaining the corresponding target words or sentences. Word selection is an existing, conventional technology, and its specific implementation will not be elaborated here.

[0029] In photo mode, after taking a picture to obtain an image, an OCR tool is used to recognize and extract English words, sentences, or paragraphs. Photo mode can be combined with word highlighting mode; for example, after taking a picture and using the OCR tool to recognize English words, sentences, or paragraphs, you can then highlight and select the words.

[0030] Step 120: Obtain the syllable separators and IPA symbols for the target word.

[0031] This step can be achieved using existing online English dictionaries or electronic English dictionaries, such as the Longman Online Dictionary (https: / / www.ldoceonline.com / ). Alternatively, an existing English dictionary can be used to extract a database of word-to-IPA symbols.

[0032] The syllable separator is the "·" in the International Phonetic Alphabet, such as... Figure 3 , Figure 4 As shown.

[0033] Step 130: Determine whether the target word is a polysyllabic word based on the syllable separators; if there is at least one syllable separator, the word is a polysyllabic word; if there is no syllable separator, the word is a monosyllabic word.

[0034] For example: the word "fate" can be obtained through the Longman online dictionary as follows: Figure 2 The word structure and IPA symbol shown are: fate, / feɪt / . Since there are no syllable separators in the word structure, the word fate is a monosyllabic word.

[0035] The word "information" can be obtained through the Longman online dictionary, such as... Figure 3 The word structure and IPA symbols shown are: in·for·ma·tion, / ɪnf meɪʃ n / . Because in·for·ma·tion contains three syllable separators "·", the word information is a polysyllabic word (four syllables).

[0036] At the same time, when obtaining the International Phonetic Alphabet of the target word, this application will also consider the main accent mark " 、 "and secondary accent mark" 、 "The primary stressed syllable and the secondary stressed syllable are obtained, while the remaining syllables are weakly stressed syllables, such as..." Figure 4 As shown. According to the International Phonetic Alphabet (IPA) rules, a syllable containing one vowel is considered a syllable.

[0037] Step 140: Based on the correspondence between phonics pronunciation symbols and International Phonetic Alphabet (IPA), rewrite the IPA symbols for monosyllabic and polysyllabic words respectively, where: For monosyllabic words, rewrite them using the first font or the first font size.

[0038] For multi-syllable words, syllables other than the weak syllables are marked with the first font or the first font size, and the weak syllables are rewritten with the second font or the second font size.

[0039] The second font size has a lighter weight than the first font size (the strokes of the second font size are thinner than those of the first font size), or the font height of the second font size is smaller than that of the first font size.

[0040] For example: the first font size should be set to Regular / Normal / Book weight, and the second font size should be set to Light weight. The height of the second font size should be smaller than that of the first font size, meaning the second font size is larger than the first font size. For example, the first font size should be size 4, and the second font size should be size 5.

[0041] In the above steps, the method for identifying weak syllables in a word based on the International Phonetic Alphabet (IPA) of the target word is that a syllable in the word simultaneously meets the following two conditions: 1. No accent marks.

[0042] 2. The vowel is [ ] or [ɪ].

[0043] If both of the above conditions are met, then that syllable in the word is a weak syllable. A word may have one weak syllable or multiple weak syllables.

[0044] Some disyllabic words do not have weak syllables (vowels are pronounced as [...]). Syllables with [ɪ] or [ɔ] only have primary and secondary stressed syllables. In this case, the secondary stressed syllable does not have a secondary stress mark and looks like a weak syllable, but it is not a weak syllable because its vowel is not [ɔ]. [ɪ] or [ɪ]. For example: also / ɔ ls ʊ$ lsoʊ / Step 150: Based on the position of the syllable separator in the target word, add spaces at the corresponding positions in the rewritten string to separate the syllables and generate pronunciation annotations for English phonics.

[0045] Step 140 rewrites the International Phonetic Alphabet (IPA) of the target word to form a letter string, which corresponds one-to-one with each letter in the target word. Step 150 adds spaces to the corresponding positions in the letter string according to the positions of the syllable separators in the word structure of the target word, thereby generating the pronunciation annotations for English phonics. Monosyllabic words do not have syllable separators and do not require adding spaces.

[0046] For example, the word "panda" has the word structure "pan·da" and its International Phonetic Alphabet (IPA) symbol is / pænd / , in step 140, the International Phonetic Alphabet is rewritten as panda or panda, and then in step 150, a space is inserted according to the position of the syllable separator (the fourth position) to form the phonics pronunciation mark pan da or pan da.

[0047] Specifically, this can be achieved using two arrays. The first array stores the word structure of the target word, storing one letter or syllable separator for each character in sequence from front to back. The second array stores the letter string formed after rewriting the International Phonetic Alphabet, storing one letter for each character. Then, the position of the syllable separator in the first array is determined, and a blank space is added to the corresponding position in the second array. Finally, the pronunciation annotation of English phonics is generated based on the second array.

[0048] The method described above, which rewrites the target word's IPA symbol into a string, can be done in the same way and will not be repeated here. Standard English IPA symbols can be pre-stored for easy IPA recognition.

[0049] Standard English International Phonetic Alphabet (IPA) includes 20 vowels and 28 consonants. To this end, a database or table of correspondences between English IPA and phonics pronunciation symbols is constructed. The database or table includes both British and American pronunciations of the same phoneme, and the corresponding pronunciation is modified in response to the user's choice of British or American pronunciation.

[0050] like Figure 5 , Figure 6 , Figure 7 , Figure 8 , Figure 9 As shown, a corresponding rewrite example is as follows: Examples of rewriting 7 short vowels: [æ] rewritten as a For example, bat, / bæt / , can be rewritten as / b a t / .

[0051] [ Rewritten as u , such as but, / b t / , rewritten as / b u t / .

[0052] [ʊ] rewritten as u For example, put, / pʊt / , can be rewritten as / p u t / .

[0053] [ $ɑ Rewritten as o , such as hot, / h t$hɑ t / , rewritten as / h o t $ h o The t / (the part before the $ indicates British English pronunciation, and the part after the $ indicates American English pronunciation) will be rewritten accordingly based on the user's choice of British or American pronunciation.

[0054] [e] rewritten ase For example, red, / red / , can be rewritten as / r e d / .

[0055] [ɪ] is rewritten as i, such as p i g, / pɪɡ / , rewritten as / p i g / .

[0056] [ Rewrite the words using the corresponding English letters, and use the second font size, such as: panda / pænd / , rewritten as / p a n da / or / p a n da / ; even / i v n / , rewrite as / e ven / or / e ven / ; civil / sɪv l / , rewritten as / s i v il / or / s i v il / ; bottom / b t m$ bɑ t m / , rewritten as / b o t tom / or / b o t tom / ; humus / hju m s / , rewritten as / hu mus / or / hu mus / .

[0057] When a particular weak pronunciation is [ɪ], the 'i' is represented by the second font size and rewritten in bold using the second font size. For example, positive, / p z tɪv$ pɑ - / can be rewritten as / poz itive / or / pozitive / .

[0058] Examples of rewriting 6 long vowels: [i Rewrite ] with e, such as treat, / tri t / is rewritten as / treat / , and the silent a is rewritten as gray.

[0059] [ɔ $ Rewritten as o $ o , such as law, / lɔ $l / , rewritten as / l o w$ l o w / 。 (Phonics short o) o The pronunciation differs between British and American phonics, naturally distinguishing between British and American English. o This is the underlined italic format for the letter 'o'. That is, 'o' and... o These are the regular and underlined italic formats for the same letter, respectively.

[0060] [u Rewritten as u , such as blue, / blu / , rewritten as / bl u The silent e at the end is rewritten in gray.

[0061] [ju Rewrite ] with u, such as mute, / mju t / is rewritten as / mute / . The silent 'e' at the end is rewritten in gray.

[0062] [ɑ ]rewrite a It is only applicable to British English. For example, glass, / ɡlɑ s$ɡlæs / , rewritten as / gl a ss $gl a ss / .

[0063] [ $ The letter r is rewritten as a doubled form of the corresponding vowel, indicated by the second font size or font number. In American English, the vowel is not doubled; instead, "r" is added directly after the corresponding letter. Examples include / ee-er / or / ee-er / , / ii-ir / or / ii-ir / , / oo-or / or / oo-or / , / uu-ur / or / uu-ur / , etc. nerd / n d$n Rewrite rd / as / need $nerd / or / need $nerd / ; bird / b d$b rd / , rewrite as / biid $bird / or / biid $bird / ; work, / w k$w rk / , rewrite as / wook $work / or / wook $work / ); burp / b p$b (Rewrite rp / as / buup $burp / or / buup $burp / ).

[0064] 8 examples of diphthong rewriting: [aɪ] is rewritten as i, such as lie / laɪ / , which is rewritten as / lie / . The silent e at the end is rewritten as gray.

[0065] [eɪ] is rewritten as a, such as date / deɪt / , which is rewritten as / date / . The silent 'e' at the end is rewritten as gray.

[0066] [ɔɪ] rewritten as o i , such as join / d ɔɪn / , rewritten as / j o i n / , here o The underlined italic format is for the letter 'o'.

[0067] [ ʊ] Rewritten as o, such as road / r ʊd$roʊd / , rewritten as / road / . The silent 'a' is rewritten as gray.

[0068] [aʊ] rewritten as a u $ o u For example, mouth / haʊθ / , rewritten as / m a u th $ m o u th / .

[0069] [e Rewritten as e e$ e r ore e$ e r, such as hair / he $her / , rewrite as / h e e$ h e r / or / h e e$h e r / .

[0070] [ɪ Rewritten as i i$ i r or i i$ i r, such as here / hɪ $hɪr / , rewritten as / h i i$ h i r / or / h i i$h i r / .

[0071] [ʊ Rewritten as u u$ u r or u u$ u r, such as tour / tʊ $tʊr / , rewritten as / to u u$ to u r / or / to u u$ to u r / .

[0072] When 'y' is at the end of a word or syllable, it is treated as a vowel and pronounced according to the same rules as the letter 'i', such as 'fly / flaɪ / ' which is rewritten as 'fli'. When 'y' is at the beginning of a word or syllable, it is treated as a consonant, such as 'yes / j'. e s / changed to / y e s / .

[0073] Examples of rewriting 12 voiceless consonants: [p] is rewritten as / p / ; [t] is rewritten as / t / ; [k] is rewritten as / k / ; [f] is rewritten as / f / ; [θ] is rewritten as / th / , such as thin, / θɪn / is changed to / th. i n / ; [s] is rewritten as / s / ; [ʃ] is rewritten as / sh / , such as ship, / ʃɪp / is changed to / sh / . i p / ; [tʃ] is rewritten as / ch / , such as in chip, / tʃɪp / is changed to / ch / . ip / ; [h] is rewritten as / h / ; [ts] is rewritten as / ts / ; [tr] is rewritten as / tr / ; [kw] is rewritten as / q / , such as quake, / kweɪk / is changed to / quake / . Silent u and e are changed to gray.

[0074] Examples of rewriting 17 voiced consonants: [b] is rewritten as / b / ; [d] is rewritten as / d / ; [ɡ] is rewritten as / g / ; [v] is rewritten as / v / ; [ð] is rewritten as / th / For example, this / ðɪs / should be changed to / th is / ; [z] is rewritten as / z / ; [ Rewrite as / sh / , such as beige / beɪ / changed to / ba sh / ;[d Rewrite as / j / , such as job / d b$d a b / changed to / j o b / ; [m] is rewritten as / m / ; [n] is rewritten as / n / ; [ŋ] is rewritten as / ng / , such as singing / stiŋ / being changed to / s i ng / ; [l] is rewritten as / l / ; [r] is rewritten as / r / ; [dz] is rewritten as / dz / ; [w] is rewritten as / w / ; [dr] is rewritten as / dr / ; [j] is rewritten as / y / , such as yes / j e s / changed to / y e s / ; [ks] should be rewritten as / x / , such as text / tekst / should be changed to / t e xt / .

[0075] By using the above methods to mark the pronunciation of phonics, English can be made into a phonetic language.

[0076] The above-mentioned correspondence between the English International Phonetic Alphabet and the phonics pronunciation symbols is only an example. The phonics pronunciation symbols are represented by the 26 English letters and other variants, all of which are included within the scope of protection of this application. That is, the variants of the 26 English letters are not limited to adding underlines, changing to italics, changing the weight or size of the characters, or changing the grayscale of the colors or combinations thereof.

[0077] In order to achieve "being able to read words upon seeing them and write words upon hearing them", this application's solution uses a lighter format (lower gray level than normal pronunciation letters) to mark the silent letters in the target words when performing phonics pronunciation.

[0078] For monosyllabic and polysyllabic words, the following methods are used to identify silent letters in the target words: For monosyllabic words, the target word is compared with the letters in the phonics pronunciation annotation in order from front to back. The extra letters in the target word are the silent letters. The silent letters are inserted into the corresponding positions in the phonics pronunciation annotation and annotated in a lighter format than the pronounced letters.

[0079] This can also be achieved using two arrays.

[0080] like Figure 10 As shown, the target word is "nice," and its IPA symbol is / naɪs / .

[0081] The first step is to rewrite the International Phonetic Alphabet (IPA) into phonics pronunciation symbols, for example, / naɪs / is rewritten as nis.

[0082] The second step is to compare the target word with the letters in the phonics pronunciation chart, one by one, from front to back. To facilitate comparison, you can first separate the letters with hyphens (-).

[0083] The third step is to identify the extra letters in the target word through comparison; these extra letters are the silent letters. For example, the 'e' at the end of the target word 'nice' is a silent letter.

[0084] The fourth step is to insert the silent letter 'e' into the corresponding position in the phonics pronunciation annotation, using a lighter format than the spoken letter. For example, inserting the 'e' at the end of the target word 'nice' into the end of the phonics pronunciation annotation 'nis', and using a lighter format than the spoken letter, results in 'nise'.

[0085] For multi-syllable words, the target word is first divided into multiple parts according to the syllable separator. The syllable positions of silent letters and different vowels in each part are identified, marked, and then combined. After combination, spaces are used to replace the syllable separator to separate the syllables, thus achieving "adding spaces to the corresponding positions in the rewritten string according to the position of the syllable separator in the target word to separate the syllables".

[0086] like Figure 11 As shown, the target word is "beautiful," with the word structure "beau·ti·ful," and its IPA symbol is / bju: t f l / .

[0087] The first step is to obtain the position information of each vowel phoneme from the International Phonetic Alphabet and the position information of each syllable from words with syllable separators.

[0088] The second step is to rewrite each syllable individually according to the correspondence between the International Phonetic Alphabet and the phonics pronunciation symbols.

[0089] The third step is to compare the rewritten result with the word with syllable separators one syllable at a time to see if there are any silent letters. If so, add light-colored silent letters.

[0090] The fourth step is to replace the syllable separators with spaces, thus achieving the goal of "adding spaces at the corresponding positions in the rewritten string to separate syllables based on the position of the syllable separators in the target word".

[0091] In the above method, when the target word is a multi-syllable word with both primary and secondary stressed syllables, the first character of the primary stressed syllable is in bold (Bold / Black) format, and the first character of the secondary stressed syllable is in regular format, such as... Figure 12 As shown, examples are as follows: The polysyllabic word *abracadabra* has the word structure *ab·ra·ca·dab·ra*. International Phonetic Alphabet / æbr k dæbr / , Phonics pronunciation markings a b ra kad a bra.

[0092] The polysyllabic word tyrannosaurus has the word structure ty·ran·no·sau·rus. International Phonetic Alphabet / t ræn sɔ:r s / , phonics pronunciation marked ty r a n nos o urus.

[0093] Based on the above method, this application also provides a annotation system for English phonics, including: The first acquisition unit is used to acquire the target word, which is an English word; The second acquisition unit is used to acquire the syllable separator and IPA symbol corresponding to the target word.

[0094] The determination unit is used to determine whether a target word is a polysyllabic word based on the syllable separators of the target word; if there is at least one syllable separator, the target word is a polysyllabic word; if there is no syllable separator, the target word is a monosyllabic word.

[0095] The annotation unit is used to rewrite the IPA symbols of monosyllabic words and polysyllabic words into phonics pronunciation symbols according to the correspondence between phonics pronunciation symbols and IPA symbols; the annotation unit includes a monosyllabic word unit, a polysyllabic word annotation unit, and a weak syllable recognition unit; The monosyllabic word units are marked using the first font or the first font size; The multi-syllable word annotation unit uses the first font or first font size to annotate syllables other than weak syllables, and uses the second font or second font size to annotate weak syllables. The second font weight is less than the first font, and the second font size is less than the first font size. Spaces are added to the pronunciation annotations of phonics according to the syllable separator to separate each syllable. The weak syllable recognition unit identifies a syllable as a weak syllable based on the following two conditions: it has no stress mark, and the vowel in the syllable is […]. ] or [ɪ].

[0096] The aforementioned method for phonetic annotation in English phonics can be implemented by a computer program. Based on this, this application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the aforementioned method for phonetic annotation in English phonics.

[0097] The following are several application examples of the proposed solution, with reference to the accompanying drawings.

[0098] Application Example 1: Creating electronic or print publications.

[0099] Specifically, electronic or print publications using the above method include phonetic annotations of English phonics below the English text, including word lists, example sentences, and articles, such as... Figure 13 , Figure 14 As shown.

[0100] Application Example 2: Applying to word annotation in mobile input.

[0101] like Figure 15As shown, the solution in this application is used as a mobile app (a phonics pronunciation annotation app). After launching the app, an English word is entered into the input box, and then the phonics pronunciation annotation is obtained using the method in this application. The English word and its phonics pronunciation annotation are displayed on the output interface. Thus, the English word can be pronounced accurately.

[0102] Application example 3, applied to word highlighting and annotation on PC or mobile devices.

[0103] like Figure 16 As shown, the PC client runs an app (Phonics Pronunciation Annotation App) in the background. When reading English web pages or English articles, users can highlight words they don't know how to pronounce. After the Phonics Pronunciation Annotation App detects the highlighting operation, it obtains the highlighted words, uses the method described in this application to obtain phonics pronunciation annotations, and displays the highlighted words and their phonics pronunciation annotations through a pop-up window.

[0104] For example: banana, ban a na $ ba n a na or ba n a na $ ba n a na.

[0105] The above examples are only used to illustrate some applications of the solution in this application and are not intended to limit the application to these examples. It should be understood that the solution in this application can be applied to any application scenario for phonics pronunciation annotation.

[0106] Application Example 4: Applied to AI multimodal products (such as "Doubao") for on-site teaching, providing real-time guidance to users on word pronunciation and spelling.

[0107] like Figure 16 As shown, the AI ​​product "Doubao" uses a camera to identify when a learner has problems with the pronunciation or spelling of a word (learners can let "Doubao" know their difficulties by pointing to the target word, etc.). "Doubao" can then generate a natural phonics pronunciation annotation for the target word and explain and demonstrate the pronunciation and spelling steps of the word syllable by syllable.

[0108] Based on the above description of specific embodiments, the pronunciation annotation method, system, and computer program product for English phonics provided by the present invention have the following advantages compared with the prior art: First, it has all the functions of the International Phonetic Alphabet, applicable to 100% of words, including 100% of multi-syllable words.

[0109] Second, there is only one strong and weak rule, which makes it easy to learn and master.

[0110] Third, the absence of unfamiliar letters and special symbols in the phonetic symbols makes English a truly phonetic language. This not only facilitates learning and mastery but also simplifies the publication of phonetic notations.

[0111] Finally, it should be noted that the terms "comprising," "including," or any other variations thereof as used herein are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a…" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0112] This invention is not limited to the above-described preferred embodiments. Anyone should know that any structural changes made under the guidance of this invention, and any technical solutions that are the same as or similar to this invention, fall within the protection scope of this invention.

Claims

1. A method for phonetic annotation in English phonics, characterized in that, Includes the following steps: Obtain the target word, its syllable separator, and its International Phonetic Alphabet (IPA) symbol; the target word is an English word. Determine whether the target word is a multi-syllable word based on the syllable separators in the target word; If there is at least one syllable separator, then the target word is a multisyllabic word; If there are no syllable separators, then the target word is a monosyllabic word; Based on the correspondence between phonics pronunciation symbols and the International Phonetic Alphabet (IPA), the IPA symbols for monosyllabic and polysyllabic words are rewritten separately, including: For monosyllabic words, rewrite them using the first font or the first font size; For multi-syllable words, syllables other than weak syllables are rewritten using the first font or first font size, while weak syllables are rewritten using the second font or second font size. Based on the position of the syllable separator in the target word, spaces are added at the corresponding positions in the rewritten string to separate the syllables, generating pronunciation annotations for English phonics. The weight of the second font is less than that of the first font, and the height of the second font size is less than that of the first font size. The method for identifying weak syllables in a word based on its International Phonetic Alphabet (IPA) transcription is as follows: If a syllable in the International Phonetic Alphabet (IPA) of a target word meets both of the following conditions, then that syllable is a weak syllable: it has no accent mark, and the vowel in that syllable is […]. ] or [ɪ].

2. The method according to claim 1, characterized in that, Different acquisition modes are selected to acquire target words according to specific applications. The acquisition modes include input mode, word selection mode, and photo mode.

3. The method according to claim 1, characterized in that, Use existing online English dictionaries to obtain the International Phonetic Alphabet (IPA) symbols and syllable separators for the target words.

4. The method according to claim 1, characterized in that, Phonics pronunciation annotations use the 26 English letters and their variants, including adding underlines, changing to italics, changing font weight or size, and changing color grayscale or combinations thereof; a database or table of corresponding rewriting relationships between English International Phonetic Alphabet and phonics pronunciation annotations is constructed, which includes both British and American pronunciations of the same phoneme, and is rewritten in response to the user's selection of British or American pronunciation.

5. The method according to claim 4, characterized in that, The silent letters in the target word are marked with a lighter format than the spoken letters for phonics pronunciation. The following methods are used to identify silent letters in both monosyllabic and polysyllabic words: For monosyllabic words, the target word is compared with the letters in the phonics pronunciation annotation from front to back. The extra letters in the target word are the silent letters. The silent letters are inserted into the corresponding positions and annotated with a lighter format than the pronunciation letters. For multi-syllable words, the target word is divided into multiple parts according to syllable separators. Each part is identified and labeled using the method described above for identifying silent letters in monosyllable words, and then combined.

6. A annotation system for English phonics, characterized in that, include: The first acquisition unit is used to acquire a target word, wherein the target word is an English word; The second acquisition unit is used to acquire the syllable separator and international phonetic symbol corresponding to the target word; The determination unit is used to determine whether a word is a multisyllabic word based on the syllable separator of the target word; If there is at least one syllable separator, the target word is a polysyllabic word; if there is no syllable separator, the target word is a monosyllabic word. The rewriting annotation unit is used to rewrite the International Phonetic Alphabet (IPA) symbols for monosyllabic and polysyllabic words based on the correspondence between phonics pronunciation annotations and IPA symbols. The rewriting annotation unit includes a monosyllabic word rewriting annotation unit, a polysyllabic word rewriting annotation unit, and a weak syllable recognition unit. The monosyllabic word rewriting annotation unit uses the first font or the first font size for rewriting; The multisyllable word rewriting and annotation unit rewrites syllables other than weak syllables using a first font or first font size, and rewrites weak syllables using a second font or second font size. Based on the position of the syllable separator in the target word, it adds spaces at the corresponding positions in the rewritten string to separate the syllables, generating pronunciation annotations for English phonics. The weight of the second font is less than that of the first font, and the height of the second font size is less than that of the first font size. The weak syllable recognition unit identifies a syllable as a weak syllable based on the following two conditions being met in the International Phonetic Alphabet of the target word: there is no stress mark, and the vowel in the syllable is […]. ] or [ɪ].

7. The system according to claim 6, characterized in that, It also includes a database or table of corresponding rewriting relationships between English International Phonetic Alphabet and phonics pronunciation annotations. The database or table of corresponding rewriting relationships includes both British and American pronunciations of the same phoneme. In response to the user's selection of British or American pronunciation, the annotation unit is rewritten accordingly. Phonics pronunciation annotations use the 26 English letters and their variations, including adding underlines, changing to italics, changing the weight or size of the letter, and changing the grayscale of the color or a combination thereof. Silent letters are annotated in a lighter format than the phonics letters.

8. The system according to claim 6, characterized in that, Also includes: The silent letter annotation unit for monosyllabic words compares the target word with the letters in the phonics pronunciation annotation from front to back. The extra letters in the target word are the silent letters. The silent letters are inserted into the corresponding positions and annotated with a lighter format than the pronunciation letters. The silent letter annotation unit for monosyllabic words divides the target word into multiple parts based on syllable separators. Each part is identified and annotated using the method described above for identifying silent letters in monosyllabic words, and then the parts are combined.

9. A computer program product comprising a computer program / instructions, characterized in that, When executed by a processor, the computer program / instruction implements the phonetic annotation method for English phonics as described in any one of claims 1 to 6.

Images