CN1228760C - System and method for searching word according to speech - Google Patents
System and method for searching word according to speech Download PDFInfo
- Publication number
- CN1228760C CN1228760C CNB2003101058995A CN200310105899A CN1228760C CN 1228760 C CN1228760 C CN 1228760C CN B2003101058995 A CNB2003101058995 A CN B2003101058995A CN 200310105899 A CN200310105899 A CN 200310105899A CN 1228760 C CN1228760 C CN 1228760C
- Authority
- CN
- China
- Prior art keywords
- word
- information
- module
- words
- playing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The present invention relates to a word searching system and a method thereof. The system comprises a receiving module for receiving audio data, a playing module for playing received audio data, an audio picking-up module for picking up word sound segment of the playing audio data for selecting words, a word information database for storing word information, a comparing module for comparing the selected words with the sound information in the word information to obtain a comparison result, and an output and display module for displaying and outputting the annotation information of corresponding words according to the comparison result. The present invention adopts a voce identification technique for searching words, and breaks through the bottleneck that words can only be searched through word spelling in a traditional word searching mode; particularly, words can be directly searched through pronunciation in the process of listening exercises, new words in listening are effectively solved, and great learning effects can be obtained with less time.
Description
One, technical field
The present invention relates to a kind of word enquiring system and method thereof.
Two, background technology
In foreign language learning and the process that exchanges of utilization foreign language, often need the information such as connotation, usage of looking up words.For example when the reading foreign language data, running into unacquainted word is very common situation, these words just are easy to by looking up the dictionary solve, more convenient is, electronic dictionary various in style and computer software have appearred at present, typing word on electronic dictionary or computing machine just can inquire the relevant information of word easily.
" hear " it is foreign language learning and very important technical ability of process of exchanging with foreign language, when carrying out aural learning, require the learner to hear a sentence, just can reflect the connotation of the words at once, sentence all is made up of word, if do not know the wherein meaning of certain word, will influence understanding to whole word.When the utilization foreign language exchanges, too, need in time reflect the mother tongue meaning of the word of being heard, can really accomplish to exchange accessible like this.When we run into some words of not understanding, common solution route all is to inquire about its connotation by dictionary, but only know the pronunciation of word and do not know the spelling of word that looking up the dictionary is the spelling that needs the input word this moment, the user must know that the spelling method of word could inquire about.Therefore the user can only guess its spelling according to pronunciation of words sometimes.After finding corresponding word; in its substitution sentence; verify whether this conjecture is correct; but there are a lot of words to pronounce simply by virtue of it; be to be difficult to its spelling of right judgement; because it all is that pronunciation is irregular that a lot of words are arranged, therefore waste a lot of times through regular meeting and guess and verify word, and the last connotation that still may can not find out respective word.
Three, summary of the invention
The invention solves the e-dictionary that exists in the background technology can not be by the technical matters of voice verification certificate speech.
Technical scheme of the present invention is: a kind of system according to the speech polling word, and its special character is: this system comprises:
Be used to receive the receiver module of voice data;
The playing module of the voice data that responsible broadcast receives;
Be used for capturing the audio frequency acquisition module of the word sound clip of the voice data in the playing process as selected word;
Be used for the word information database of the table of comparisons of bill of store word information and word acoustic information and annotation information;
Acoustic information in selected word and the word information is compared, and draw the comparison result module;
According to comparison result, show the output display module of the annotation information of output respective word.
Above-mentioned receiver module also comprises and is used for the storage device of stored audio data.
Above-mentioned audio playing module also comprises the broadcasting speed adjusting module.
Above-mentioned word information comprises acoustic information and corresponding annotation information thereof.
Above-mentioned annotation information comprises spelling, lexical or textual analysis, phonetic symbol, the part of speech of word, the combination in any of usage.
The present invention also provides a kind of How It Works of the system according to the speech polling word, and its special character is: this method comprises the steps:
1) receives voice data;
2) playing audio-fequency data captures the word sound clip simultaneously, as selected word;
3) the word acoustic information that is complementary with selected word in the searching words information database;
4), export corresponding word annotation information according to comparison result.
Above-mentioned steps 1) also comprises the step of stored audio data.
Above-mentioned steps 2) the search comparison is right according to the analog phonetic symbol approximation ratio.
Above-mentioned steps 4) in,, then point out word not exist if there is not the word information that is complementary.
The present invention has following advantage:
System and method according to the speech polling word of the present invention, utilization speech recognition technology is carried out word enquiring, broken through the bottleneck that traditional word enquiring can only carry out unidirectional inquiry by the spelling of word, especially in the aural learning process, directly carry out word enquiring by pronunciation, effectively solved the new word of the appearance in the hearing, with the time of weak point has exchanged bigger learning effect for.
Four, description of drawings
Fig. 1 is the module rack composition of system of the present invention;
Fig. 2 carries out the method flow diagram of word enquiring according to voice for the present invention;
Fig. 3 is embodiment of the invention operation workflow figure;
Fig. 4～Fig. 7 is one embodiment of the invention interface synoptic diagram.
Five, embodiment
See also Fig. 1, the present invention includes according to the system of speech polling word:
Playing module 120, its voice data of being responsible for receiving plays back, and when playing, can also adjust broadcasting speed, and the word for the ease of acquisition accurately will be inquired about can slow down broadcasting speed.
Audio frequency acquisition module 130, the main sound clip of being responsible in the acquisition voice data, the pronunciation of a word of acquisition can capture button by audio frequency as selected word in the voice data of playing, the selected word of the required inquiry of acquisition in progress voice data.
Comparing module 150, acoustic information in selected word that responsible comparison captures and the word information database, draw comparison result, if comparing module finds the acoustic information that is complementary, then from word information database 140, find corresponding word annotation information by the corresponding relation that detects the table of comparisons; If through comparison, do not find the acoustic information of coupling, then draw the conclusion of not having this word.
Referring to Fig. 2, the present invention comprises following steps according to the method that voice carry out word enquiring:
Step 210 at first receives voice data;
Step 220 playing audio-fequency data captures a word sound clip simultaneously, as selected word;
Step 230 is selected the word acoustic information that word is complementary with this in the searching words information database then;
Step 240 is exported corresponding word annotation information at last according to comparison result.
Referring to Fig. 3, one embodiment of the invention operation workflow comprises following steps:
Step 310 at first stores word information in the word information database, word information comprises word acoustic information and word annotation information, and the word annotation information includes information such as word spelling, lexical or textual analysis, phonetic symbol, part of speech, usage.In addition, also store comparison list in the word information database, the table of comparisons connects acoustic information and annotation information.An acoustic information may be corresponding to one or more annotation information in the table of comparisons.When the learner practises hearing, all will receive section audio data as the aural learning content, acquisition mode can be downloaded from the Internet, also can record by sound pick-up outfit, and be that standard stores with time with audio data content in the time of reception.
Step 320 is play the voice data of typing then, can regulate broadcasting speed as required by the user during broadcast, and the learner can slow down broadcasting speed for the ease of extracting the word that will inquire about.
Step 330 by activating the audio frequency acquisition module, captures required selected word then, just captures the pronunciation of word.
Step 340 acoustic information that then search and selected word are complementary in the word information database, when comparing, it is right just to carry out ratio of similitude, and do not require fully comparison, because be not that each language all has unique pronunciation rule, sometimes owing to regional difference, or the reason of raw data teller pronunciation, thereby the pronunciation that causes word be stored in the word information storehouse in the different situation of acoustic information, therefore only do approximate comparison here.Approximation ratio is to carrying out according to the analog phonetic symbol rule list.With English is example, sees also following table, is the analog phonetic symbol rule list:
According to last table, utilize the speech recognition technology that approximate comparison is done in similar pronunciation, in acoustic information, search for.
Step 350 has judged whether corresponding acoustic information then;
If step 360 has corresponding acoustic information, then find corresponding annotation information by the table of comparisons;
Step 370 shows the annotation information that finds again.If this pronunciation only has a pronunciation same or similar with it in the word information database, then directly show this word, can obtain relevant informations such as this word, part of speech, phonetic symbol, example sentence, lexical or textual analysis.If this pronunciation has a plurality of pronunciations same or similar with it in the pronunciation data storehouse, then show the pairing word of a plurality of pronunciations, can obtain relevant informations such as this word, part of speech, phonetic symbol, example sentence, lexical or textual analysis.If do not find corresponding acoustic information, show that then there be not (step 380) in word.
Next referring to Fig. 4～Fig. 7, be the interface synoptic diagram of another preferred embodiment of the present invention.Fig. 4 is acquisition pronunciation interface, the learner by record button record down pronunciation The disagreement among thefamily members healed over time. when needs to sentence in unfamiliar word when inquiring about, unfamiliar word to be extracted from sentence, for acquisition pronunciation accurately, can broadcasting speed be slowed down according to the button of regulating the speed.Again by acquisition pronunciation button acquisition pronunciation, to realize acquisition accurately.After the acquisition pronunciation finishes, press inquire button and search identical or close pronunciation.For example captured the pronunciation of " healed ".If find identical or the word of close pronunciation, then demonstrate and three similar words of heal pronunciation, directly select shown word just can find relevant word information.For example click word " heal ", will show the word information such as phonetic symbol, lexical or textual analysis of " heal ".The learner just can judge the pairing word of pronunciation of broadcast according to the lexical or textual analysis of word.If do not search corresponding word, then prompting can appear in system, and whether the prompting learner needs to capture again pronunciation, if the learner has selected "Yes", acquisition pronunciation interface will be got back to by system, if the learner has selected "No", then finish the pronunciation inquiry, quit a program.
Claims (9)
1, a kind of system according to the speech polling word, it is characterized in that: this system comprises:
Be used to receive the receiver module of voice data;
The playing module of the voice data that responsible broadcast receives;
Be used for capturing the audio frequency acquisition module of the word sound clip of the voice data in the playing process as selected word;
Be used for the word information database of the table of comparisons of bill of store word information and word acoustic information and annotation information;
Acoustic information in selected word and the word information is compared, and draw the comparison result module;
According to comparison result, show the output display module of the annotation information of output respective word.
2, the system according to the speech polling word according to claim 1 is characterized in that: described receiver module also comprises and is used for the storage device of stored audio data.
3, the system according to the speech polling word according to claim 1, it is characterized in that: described audio playing module also comprises the broadcasting speed adjusting module.
4, the system according to the speech polling word according to claim 1 is characterized in that: described word information comprises acoustic information and corresponding annotation information thereof.
5, the system according to the speech polling word according to claim 4 is characterized in that: described annotation information comprises spelling, lexical or textual analysis, phonetic symbol, the part of speech of word, the combination in any of usage.
6, the How It Works of the system according to the speech polling word according to claim 1, it is characterized in that: this method comprises the steps:
1) receives voice data;
2) playing audio-fequency data captures the word sound clip simultaneously, as selected word;
3) the word acoustic information that is complementary with selected word in the searching words information database;
4), export corresponding word annotation information according to comparison result.
7, according to claim 6ly carry out the method for word enquiring, it is characterized in that described step 1) also comprises the step of stored audio data according to voice.
8, according to claim 6ly carry out the method for word enquiring, it is characterized in that described step 2 according to voice) the search comparison is right according to the analog phonetic symbol approximation ratio.
9, according to claim 6ly carry out the method for word enquiring, it is characterized in that in the described step 4),, then point out word not exist if there is not the word information that is complementary according to voice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2003101058995A CN1228760C (en) | 2003-11-07 | 2003-11-07 | System and method for searching word according to speech |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2003101058995A CN1228760C (en) | 2003-11-07 | 2003-11-07 | System and method for searching word according to speech |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1542733A CN1542733A (en) | 2004-11-03 |
| CN1228760C true CN1228760C (en) | 2005-11-23 |
Family
ID=34333920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2003101058995A Expired - Fee Related CN1228760C (en) | 2003-11-07 | 2003-11-07 | System and method for searching word according to speech |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1228760C (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101645190B (en) * | 2009-07-22 | 2011-03-30 | 合肥讯飞数码科技有限公司 | Word inquiring system and inquiring method thereof |
| CN101944092B (en) * | 2009-07-06 | 2012-07-18 | 英业达股份有限公司 | Word pronunciation system and method thereof |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100418095C (en) * | 2006-10-20 | 2008-09-10 | 无敌科技(西安)有限公司 | Word-sound synchronous playing system and method |
| CN103310666A (en) * | 2013-05-24 | 2013-09-18 | 深圳市九洲电器有限公司 | Language learning device |
| CN105760356B (en) * | 2016-03-17 | 2018-10-19 | 广东小天才科技有限公司 | Automatic generation method and system for English word dictation question alternative options |
| CN109545014A (en) * | 2018-12-28 | 2019-03-29 | 杭州晶智能科技有限公司 | A kind of foreign language word exercising method based on interactive voice |
| CN110428668B (en) * | 2019-07-31 | 2022-08-26 | 平安科技（深圳）有限公司 | Data extraction method and device, computer system and readable storage medium |
| CN110598012B (en) * | 2019-09-23 | 2023-05-30 | 听典（上海）教育科技有限公司 | Audio and video playing method and multimedia playing device |
| CN110825906A (en) * | 2019-11-20 | 2020-02-21 | 安康学院 | English listening comprehension analysis method and system |
-
2003
- 2003-11-07 CN CNB2003101058995A patent/CN1228760C/en not_active Expired - Fee Related
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101944092B (en) * | 2009-07-06 | 2012-07-18 | 英业达股份有限公司 | Word pronunciation system and method thereof |
| CN101645190B (en) * | 2009-07-22 | 2011-03-30 | 合肥讯飞数码科技有限公司 | Word inquiring system and inquiring method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1542733A (en) | 2004-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7240003B2 (en) | Database annotation and retrieval | |
| US8892565B2 (en) | Method and apparatus for accessing an audio file from a collection of audio files using tonal matching | |
| CN1559042A (en) | Multi-lingual transcription system | |
| CN1555553A (en) | Correcting a text recognized by speech recognition through comparison of phonetic sequences in the recognized text with a phonetic transcription of a manually input correction word | |
| CN1228760C (en) | System and method for searching word according to speech | |
| CN110335625A (en) | The prompt and recognition methods of background music, device, equipment and medium | |
| CN1356628A (en) | Speech recognition correction for equipment wiht limited or no displays | |
| CN111986656B (en) | Teaching video automatic subtitle processing method and system | |
| CN101472082A (en) | Log keeping system and method | |
| CN101226526A (en) | Method for searching music based on musical segment information inquest | |
| CN108710653B (en) | On-demand method, device and system for reading book | |
| CN1645363A (en) | Portable realtime dialect inter-translationing device and method thereof | |
| CN1189836C (en) | Study method and apparatus using digital audio and caption data | |
| CN1204511C (en) | Device capable of playing background music and reading electronic book aloud and its method | |
| CN1156871A (en) | Personal information database system | |
| CN113032537A (en) | Voice-controlled finished automobile query operation method | |
| CN113129856A (en) | Music score automatic correction method based on big data | |
| TWI270052B (en) | System for selecting audio content by using speech recognition and method therefor | |
| CN1144175C (en) | voice training system and training method | |
| CN1512402A (en) | Sound searching method and video and audio information searching system using said method | |
| CN106095910A (en) | The label information analytic method of a kind of audio file, device and terminal | |
| CN1167999C (en) | Method for converting hypermedia file into voice | |
| CN111356022A (en) | Video file processing method based on voice recognition | |
| CN1371090A (en) | Method of converting phonetic file into text file | |
| WO2021017302A1 (en) | Data extraction method and apparatus, and computer system and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20051123 Termination date: 20091207 |