TW200421126A - System and method for searching a single word in accordance with speech - Google Patents

Abstract

A system and method searching a single word in accordance with speech firstly stores audio data. The audio acquisition module acquires the single word to be searched in audio data. The comparison module searches the pronunciation of the single word in word information database to locate matching word. Further forward the corresponding annotation information of single word to output display module for display so as to implement search of annotation for single word through single word pronunciation.

Description

200421126 V. Description of the invention (1) [Technical field to which the invention belongs] The present invention is a kind of word that uses the pronunciation of a word to inquire about the prior art] When learning foreign languages and using the meaning and usage of a word to be queried, I encounter an Words can be easily solved with a dictionary. More electronic dictionaries and computer software words can be easily searched. I heard that π is a very important skill in foreign language learning. When you listen to a sentence, you can immediately respond to the word composition. If you don't know its entire sentence. Disturbances in the use of the language of the words you hear on the go. When we encounter some people who use the dictionary to query the sounds without knowing the spelling of the word, the user must know that the user of the word can only pronounce it according to the word. After they come, substitute it into the sentence. Many words come only by virtue of The pronunciation is because there are many words that are pronunciation query systems and methods, especially systems and methods for interpreting words. Information in foreign languages is very common and convenient. When you get to the word and practice a certain language in this sentence to communicate thinking, do not understand the meaning, check the dictionary spelling party to guess it to verify that it is very irregular. 0 For example, it is the case that when the related words of the heading dictionary are used, the words containing words can also be used in the same way, but this requires spelling. This kind of guessing is difficult to correct because of the process before reading these or computer information. For communication, it requires meaning, sentence meaning, so it needs to be true, usually only know the input single query. Finding whether the phase is positive This often, foreign language words are often checked by entering a variety of types on the entry process. A non-learner who hears all the subordinates will affect the solution to the need to communicate in a timely manner. The spelling of the word's wording is sometimes changed with the corresponding word, but if it is spelled, it will waste a lot

200421126 Fifth, the invention explained the situation of guessing the time. The invention has a phonetic book for searching for words in the invention. It is used to receive a single pair of results in the received stored data. The corresponding word is first to receive the sound segment. Select the corresponding method according to the selected word, and break the query to the word (2) Test and test is still tolerant] Here, perform a word query and neck. Explicitly revealing the audio evidence of words above the audio may be a breakthrough in the query of the present invention. One is based on the material, but the corresponding word is still unavailable. The information-containing broadcast word, sound, sound, word information, and word information are displayed. The annotation information reveals an audio, and as a matching word annotation, the present invention creates the traditional bottleneck, query, data, and selected word information. The disclosed words are particularly effective. In order to solve the above problems, a system and method are proposed. Using speech recognition technology, the dictionary can only search for words by voice by inputting the spelling of the word. The system includes a receiving module. Module, which is used to release, a word information database for information, an audio capture module for capturing segments, as a selected word, a comparison module, and comparison of sound information in the module Right, and get the comparison module, according to the comparison result, display and output a method of word query according to the voice, play the audio data, retrieve a word at the same time, and then search the word information database for sound information, and then According to the comparison results, the system for outputting word queries based on speech and square queries can only be performed by listening to the spelling of the words. In the listening practice process, the pronunciation of new words that appear in listening is directly solved.

200421126 V. Description of the invention (3) Short learning time in exchange for greater learning results. The detailed content and technology of the present invention are described below with reference to the drawings. [Embodiment] The present invention will be described in detail below with reference to the drawings. According to the disclosed system and method for querying words in accordance with speech, the present invention will be described in detail by taking listening exercises as an example. Please refer to "Figure 1". "Figure 1" illustrates the system of the present invention. This figure is a module architecture diagram of the system and method for querying words by voice according to the present invention, including: receiving module 1 10, used to receive audio data. Learners can download audio data through the Internet, and can also record listening exercises. At the same time, the receiving module 110 also has a storage function that can receive the audio data. The data is stored in chronological order. The playback module 1 2 0 is responsible for playing the received audio data. During playback, the playback speed can also be adjusted. In order to accurately retrieve the words to be queried, the playback speed can be slowed down. The audio capture module 130 is mainly responsible for capturing the audio clips in the audio data. The pronunciation of a word is selected as the selected word in the audio data being played. The audio capture button can be used to select the audio data being played. Retrieve the selected words for the desired query. The word information database 1 40 is mainly used to store word information, and the word information includes sound information and corresponding words such as spelling, interpretation, phonetic transcription, part of speech, usage, and other annotation information. There is also a comparison table stored,

Page 6 200421126 V. Description of the invention The correspondence in the comparison table should be related. If there is no information output from the comparison information database, if there is no output result, please refer to the word search step 210) as the selection and comparison based on the selection. Below, it is the operation information of the embodiment of the present invention, and the word annotation information. . The other table describes the sound information (4). The description of the word information and the annotation information of the word module 1 50, is responsible for comparing the selected selected word with the sound information in the word resource to get the comparison result. If the comparison module finds the sound information, it will find the corresponding word annotation information from the word library 1 40 by detecting the correspondence of the comparison table; if the matching sound information is found after the comparison, it will conclude that there is no such word. The display module 16 0 is mainly responsible for the comparison in the comparison module 150. If one sound information corresponds to multiple word comment information, all the comment information is displayed. See "Figure 2", which is a general flowchart of the method according to the present invention in accordance with speech. First receive an audio data (step, play the audio data, and simultaneously capture a word sound segment, word (step 2 2 0), and then search for word sound information that matches the word in the word information database (step 2 3 0), Finally, the corresponding word annotation information is output (step 2 40). "Figure 3" describes the operation flow of the present invention in detail. The figure shows the actual flow chart of the system and method for querying words by voice. First In the word information database, word information including word sound information and word comment information are stored. In addition, the word information includes word spelling, interpretation, phonetic transcription, part-of-speech, usage, etc. In addition, a comparison table is stored in the word information database. Information is linked to annotated information. In the comparison table, a sound corresponds to one or more annotated information. Learners practice listening

Page 7 200421126 5. In the description of the invention (5), a piece of audio data should be received as the listening practice content (step 3 1 0). The method of obtaining can be downloaded from the Internet, or through recording equipment. The content of audio data is stored and stored based on time. Then the recorded audio data is played (step 3 2 0). During playback, the user can adjust the playback speed according to the needs. The learner can slow down the playback speed in order to facilitate the extraction of the word to be queried. Then start the information retrieval module to retrieve the required selected words (step 3 3 0), that is, to extract the pronunciation of the word, and then search the word information database for sound information that matches the selected word (step 3 4 0), when performing comparisons, only similar comparisons are performed, and complete comparisons are not required, because not every language has unique pronunciation rules, and sometimes due to regional differences or original data The speaker's pronunciation causes the pronunciation of the word to be different from the sound information stored in the word information database, so only an approximate comparison is made here. The approximate comparison is based on a table of similar phonetic transcription rules. Taking English as an example, please refer to the following table for a similar phonetic rule table: Similar vowels P Similar consonants p Similar vowels and consonants ρ i: i ^ pb ^ ij ^ eei ae ^ tdpuw ^ o: o ^ fvw ^ 3 3 : 1 rps J ^ a: λ aie Θ 3 pu: uou-z 3 ^ ju: j UP kh 〇n θ 1 r ^

Page 8 200421126 V. Description of the invention (6)

According to the above comparison, in the sound information (the step information table finds the phase information and shows that there is only one in the library, you can get the display information, phonetic symbols, sound information, table, sharp information step 3 5 0). To (pronounce a word, pronounce it in multiple example sentences, display a similar search using speech recognition technology to approximate similar pronunciations. Then determine whether there is a corresponding sound, and if there is corresponding sound information, pass the interpretation Poor information (step 36), and then the found annotation step 3 7 0). If the pronunciation is the same as or similar to the word information, it will directly display the word, part-of-speech, phonetic transcription, example sentence, definition and other related information. The pronunciation database T has multiple words with the same pronunciation or corresponding sounds, and the related information such as the word and the word definition can be obtained. If no corresponding word is found, it does not exist (step 38 0).

Next, please refer to "Fig. 4a" to "4bll", which is the interface of the preferred embodiment of the system and method for querying by words according to the present invention. It is not intended. "Picture 4a" is the interface for extracting pronunciation. Learners use the button to record the pronunciation. The dlsagreement am〇ng the &;;; members healed 〇ver with time • When you need to unfamiliar words in sentences When inquiring, extract unfamiliar words from the sentence 'In order to accurately extract the pronunciation, you can set the playback speed to k according to the speed adjustment button. Then use the capture pronunciation button to manipulate the pronunciation to achieve accurate capture. After capturing the pronunciation, press the query button to find the same or similar pronunciation. If words with the same or similar pronunciation are found, the single " Division's Pinyin 'is displayed as shown in Figure 4b. The figure shows three similarly pronounced words. You can find the relevant word information by directly clicking the word.

Page 9 200421126 V. Description of the invention (7) For example, if you click on the word n healn, the interface as shown in "Figure 4c" will be displayed. The figure lists the phonetic symbols and definitions of the word n h e a 1π. , The learner can judge the _ word corresponding to the pronunciation according to the interpretation of the word. If no corresponding word is found, the system will display a prompt box as shown in "Figure 4d", prompting the learner whether to retrieve the pronunciation again. If the learner chooses "π", the system will return to "4a The pronunciation interface of "pic map". If the learner selects "no π", the pronunciation query is ended and the program is exited. Although the present invention is disclosed above with the foregoing preferred embodiment, it is not intended to limit the present invention. Artists can make some modifications and retouching without departing from the spirit and scope of the invention. Therefore, the scope of patent protection of the invention must be defined by the scope of the patent application attached to this specification.

Page 10 200421126 Brief description of the drawings. Figure 1 is a block diagram of the system for querying words according to speech according to the present invention; Figure 2 is a general flowchart of the method for querying words according to speech according to the present invention; FIG. 3 is a flowchart of an embodiment of a system and method for performing a word query according to speech according to the present invention; and FIGS. 4a to 4d are schematic diagrams of an embodiment of a system and method for performing a word query according to speech according to the present invention. . [Illustration of graphical symbols] 110 receiving module 120 playing module 130 audio capturing module 140 word information database 150 comparison module 16 0 output display module step 2 1 0 receiving an audio step 2 2 0 playing the Audio data, while simultaneously capturing a word sound segment as the selected word. Step 2 3 0 Search for word sound information in the word information database that matches the selected word. Step 2 4 0 According to the comparison result, output the corresponding word annotation information. 3 1 0Receive and store audio lean material Step 3 2 0Play audio data Step 3 3 0Retrieve selected selected words

Page 11 200421126 Schematic description step 3 4 0 Compare the corresponding sound information in the word information database Step 3 5 0 Whether there is a corresponding sound information Step 3 6 0 Look up the table to find the comment information corresponding to the selected word Step 3 7 0 Display comment information Step 3 8 0 Display word does not exist < 1

Page 12

Claims (1)

200421126 VI. Scope of patent application 1. A system for querying words according to voice includes: a receiving module for receiving an audio data; a playback module for playing the received audio data; a An audio capture module is used to capture the word sound segment in the audio data as the selected word during playback; a word information database is used to store more than one word of information; a comparison module that The selected word is compared with the sound information in the word information and a comparison result is obtained; and an output display module displays and outputs the comment information of the corresponding word according to the comparison result. 2. The system for querying words by voice as described in item 1 of the scope of the patent application, wherein the receiving module further includes a storage function for storing the audio tribute. 3. The system for querying words by voice as described in item 1 of the scope of patent application, wherein the audio playback module can adjust the playback speed. 4. The system for querying words by voice as described in item 1 of the scope of patent application, wherein the word information includes sound information and corresponding annotation information. 5. The system for querying words by voice as described in item 1 of the scope of patent application, wherein the annotation information can be selected from any combination of word spelling, definition, phonetic transcription, part of speech, usage. 6. Word search by voice as described in item 1 of the scope of patent application Page 13 200421126 6. The patent application system, in which the word information database also stores a comparison table of single word sound information and annotation information. 7. A method for querying words according to speech, including the following steps: receiving an audio data; playing the audio data, and simultaneously capturing a sound segment of a word as a selected word; searching a word information database for matching the selected word Sound information of the word; and output corresponding early word annotations based on the comparison result. 8. The method for searching a word by voice as described in item 7 of the scope of patent application, wherein the step of receiving an audio data is to receive and store an audio lean material. 9. The method for querying words by speech as described in item 7 of the scope of patent application, wherein the search comparison is an approximate comparison based on similar phonetic symbols. 10. The method for querying words by voice as described in item 7 of the scope of patent application, wherein the step of outputting corresponding word annotation information according to the comparison result, if there is no matching word information, prompt the word does not exist. 11. The method for querying words according to speech as described in item 7 of the scope of patent application, wherein the annotation information can be selected from any combination of word spelling, definition, phonetic transcription, part of speech, usage. Page 14