CN101441626A - Multimedia retrieval system and method - Google Patents

Multimedia retrieval system and method Download PDF

Info

Publication number
CN101441626A
CN101441626A CNA2007101246189A CN200710124618A CN101441626A CN 101441626 A CN101441626 A CN 101441626A CN A2007101246189 A CNA2007101246189 A CN A2007101246189A CN 200710124618 A CN200710124618 A CN 200710124618A CN 101441626 A CN101441626 A CN 101441626A
Authority
CN
China
Prior art keywords
multimedia
key word
input
module
search
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.)
Pending
Application number
CNA2007101246189A
Other languages
Chinese (zh)
Inventor
邓桂成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CNA2007101246189A priority Critical patent/CN101441626A/en
Publication of CN101441626A publication Critical patent/CN101441626A/en
Pending legal-status Critical Current

Links

Images

Abstract

The invention relates to computer-based data retrieval technology. Aiming at the disadvantages that the prior searching technology displays an excessively single searching means and can not output various natural language and speech expression forms of a keyword, the invention provides a multimedia retrieval system which comprises an input end and an output end; the system also comprises an identifier and a multimedia database; by receiving a multimedia keyword through the input end, the identifier searches an index entry corresponding to the multimedia keyword and emits a retrieval instruction containing the index entry; and the multimedia database receives the retrieval instruction, searches and outputs a multimedia record containing the index entry through the output end. The invention also provides a multimedia retrieval method. A multimedia input and output conversion system is implemented and has the following advantages: a multimedia keyword mode can enrich the searching means; and multi-language expression helps to break through foreign language bottleneck.

Description

A kind of multimedia retrieval system and search method thereof
Technical field
The present invention relates to the computer based data retrieval technology, more particularly, relate to a kind of multimedia retrieval system and search method thereof.
Background technology
From the manual information retrieval to the internet search engine, development of computer network is that retrieval mode has brought revolutionary variation.No matter be ubiquitous search column in the market value of stock of Google company or the Vista of the Microsoft operating system, all explanations invariably, we come up search epoch forward.
A pith as internet search engine, stored the lot of data record in the search database, this had wherein both comprised Word message, also comprise multimedia messagess such as voice messaging, video information, by searching algorithm and transworld internet efficiently, internet search engine is developing into encyclopedia maximum on the human history.
Yet although stored a large amount of multimedia messagess in the search database, its search key still can only adopt mode word, and it is too single that the search means seem.In addition, present search technique still can not be exported the literal and the phonetic representation form of the corresponding various natural languages of key word, therefore can't eliminate the foreign language bottleneck that exists in the Search Results.
Therefore, need a kind of searching system, the key word that can adopt various ways is as the search means, and can export the various natural language expressing forms of key word.
Summary of the invention
The technical problem to be solved in the present invention is, at having the defective that search technique search means seem too single and can't export the various natural language speech expression-forms of key word now, provides a kind of multimedia retrieval system and search method thereof.
The technical solution adopted for the present invention to solve the technical problems is: construct a kind of multimedia retrieval system, comprise input end and output terminal, also comprise:
Recognizer receives the multimedia key word by input end, searches the directory entry corresponding with it, sends the search instruction that comprises this directory entry;
Multimedia database receives search instruction, searches and comprise by output terminal output the multimedia recording of described directory entry.
In system of the present invention, described recognizer comprises:
Type judging module;
At least one matching module;
Type judging module is judged the type of described multimedia key word, and it is mail to the matching module corresponding with its type.
In system of the present invention, described at least one matching module comprises at least a in the following matching module:
The characters matching module;
The voice match module; And
The picture matching module.
In system of the present invention, described input end comprises:
Simplify load module, receive the multimedia key word of simplifying input, generate the multimedia key word corresponding with it.
In system of the present invention,
The multimedia key word of described simplification input comprises character formation element information;
Described simplification load module comprises:
The character generation module receives character formation element information, searches character map, generates its corresponding characters.
In system of the present invention,
The multimedia key word of described simplification input comprises structure sentence character information;
Described simplification load module comprises:
The statement generation module receives structure sentence character information, and the search statement mapping table generates its corresponding statement.
In system of the present invention,
The multimedia key word of described simplification input comprises sound bite and voice command;
Described simplification load module comprises:
The speech production module receives described sound bite and voice command, searches the voice mapping table, generates corresponding voice content.
In system of the present invention, described input end comprises:
Data typing module by described input end receiving multimedia information or instruction code, generates multimedia recording or operational order.
In system of the present invention, described multimedia recording comprises at least a in Word message, voice messaging and the pictorial information; Described voice messaging comprises multiple natural language speech information.
The present invention also provides a kind of multimedia retrieval method, comprises the steps:
A, reception multimedia key word;
B, search the directory entry of corresponding above-mentioned multimedia key word, send the search instruction that comprises directory entry;
C, search the multimedia recording that comprises above-mentioned directory entry;
The multimedia recording that D, output are found.
Implement a kind of multimedia retrieval system of the present invention and search method thereof, have following beneficial effect, multimedia key word mode can be enriched the search means, and multilingual expression helps to break through the foreign language bottleneck.
Description of drawings
The invention will be further described below in conjunction with drawings and Examples, in the accompanying drawing:
Fig. 1 is the structural representation of multimedia input and output converting system of the present invention;
Fig. 2 is the process flow diagram of the multimedia input and output converting system course of work of the present invention.
Embodiment
Embodiment according to a kind of multimedia retrieval provided by the invention system, can search for as key word with the information of multiple forms such as literal, voice and picture, and the various natural language expressing forms of exportable key word, below constipation to close accompanying drawing described.
Fig. 1 is the structural representation of multimedia retrieval of the present invention system.As shown in Figure 1, multimedia retrieval of the present invention system comprises input end 100, recognizer 102, multimedia database 104 and output terminal 106.Wherein input end 100 further comprises data typing module 1002, character generation module 1004, statement generation module 1006 and speech production module 1008; Recognizer 102 further comprises type judging module 1020, characters matching module 1022, voice match module 1024 and picture matching module 1026.
Input end 100 is used to receive the multimedia key word, and this multimedia key word can be multimedia messagess such as literal key word, voiced keyword or picture key word.Especially, when input information is the literal key word, the present invention also provides a kind of " freely writing " scheme especially, i.e. this literal key word simplification input that can also be common word content, for example, under stroke input method, if the user wants input " companion " word, then can simplify input " Ren mouth ", search in the character map Chinese character that comprises " Ren mouth " by character generation module 1004 then, and export " companion " word automatically.Simultaneously, if the user wants to import a phrase, also can realize in the manner described above, for example, under stroke input method, if the user wants input " People's Republic of China (PRC) ", then can simplify input " mouthful people ... mouth " by " freely writing " scheme, wherein " mouth " representative " in " part of word, the part of " mouth " representative " state " word, " " is omission mark.At this moment, after character generation module 1004 receives input, comprise " mouth ", " people ", " mouth " these radicals by which characters are arranged in traditional Chinese dictionaries, number of characters in the search statement mapping table and be 7 and the position consistency of the character that character position and input information referred to (promptly " in " the position be 1, the position of " people " is 3, the position of " state " is 7) statement, and output " People's Republic of China (PRC) " automatically.Certainly, those skilled in the art is understood that, except that stroke input method, the literal that the present invention discloses is simplified input method and also is applicable to spelling input method, three-stroke input method, building blocks input method, five other input methods such as character-shape input method, as long as the corresponding character formation element information of input (as phonetic etc.).If what the user wanted to import is a phrase, for example " People's Republic of China (PRC) ", then can simplify and be input as " middle people ... state ", wherein " in ", " people ", " state " is structure sentence character information, " " is omission mark, this mode is called the simplification input of specified format, at this moment, after load module 1006 reception inputs simplified in statement, comprise in the search statement mapping table character " in ", " people ", " state ", number of characters is 7, and character position consistent with character position in the input information (promptly " and in " the position be 1, the position of " people " is 3, the position of " state " is 7) statement, and automatically output " People's Republic of China (PRC) ".Except that this mode, the user also can directly simplify input " China ... " (statement with " China " beginning and number of characters 7 simplified in the input table in search statement) and wait other to simplify input information.Except that the simplification input process of above telling about, input mode is also further simplified, for example, have " warmly celebrating that Chinese Communist Party's Fifteenth National Congress convenes successfully " a word and simplification input " heat---five---open " thereof like this in the if statement mapping table, then the user can directly import " heat---five---open "; Have " the new Central Committee and Central Commission for Discipline Inspection of the CPC are being elected in the Seventeenth National Congress of the Communist Party of China; by about the resolution of 16 Central Committee report, about after the resolution of Central Commission for Discipline Inspection of the CPC's work report, the resolution about " Constitution of the Chinese Communist Party (amendment) "; conclude successfully at the Great Hall of the People morning on the 21st " such one section word in the if statement mapping table and simplify input " in---21---curtain ", then the user can directly import " in---21---curtain ".Same situation also is applicable to phonetic entry, and the user can import one section brief sound bite and simplify input command as " extremely " etc., searches the voice messaging that matches in the voice mapping table by speech production module 1008 again, and exports.For example, if store " the new Central Committee and Central Commission for Discipline Inspection of the CPC are being elected in the Seventeenth National Congress of the Communist Party of China; by the resolution about 16 Central Committee's reports; about the resolution of Central Commission for Discipline Inspection of the CPC's work report; after the resolution about " Constitution of the Chinese Communist Party (amendment) "; conclude successfully at the Great Hall of the People morning on the 21st " such one section word in the voice mapping table and simplify input " the Seventeenth National Congress of the Communist Party of China is being elected the new Central Committee and Central Commission for Discipline Inspection of the CPC to concluding successfully ", wherein " extremely " is for simplifying input command, then directly phonetic entry of user " the Seventeenth National Congress of the Communist Party of China is being elected the new Central Committee and Central Commission for Discipline Inspection of the CPC to concluding successfully ".The user can be input to respectively in literal mapping table, statement mapping table or the voice mapping table by the 1002 prior simplification inputs with literal, statement or voice and correspondence thereof of data typing module, directly imports its simplification input then and get final product when input.It should be noted that, in various simplification input tables, same content can be imported in corresponding a plurality of simplification, for example for " the new Central Committee and Central Commission for Discipline Inspection of the CPC are being elected in the Seventeenth National Congress of the Communist Party of China; by the resolution about the report of 16 Central Committee; about the resolution of Central Commission for Discipline Inspection of the CPC's work report; after the resolution about " Constitution of the Chinese Communist Party (amendment) "; conclude successfully at the Great Hall of the People morning on the 21st " such one section word, it simplifies input can be such as but not limited to " in---21---curtain ", " in---21---curtain ", " in---21 ... ", " in---21 days ... ", " in---curtain ", " in ... curtain ".Simultaneously, omission mark also is not limited only to "---" mentioned above, " ... ", " " etc., can also be other symbols that are easy to import.Above-mentioned simplification input scheme is referred to as " freely writing " scheme.
Recognizer 102 receives the multimedia key word by input end 100, searches the directory entry corresponding with the multimedia key word, sends the search instruction that comprises directory entry.Wherein, type judging module 1020 is used to judge the type of multimedia key word, judge that promptly this multimedia key word is literal key word, voiced keyword or picture key word, then it is mail to corresponding matching module, be about to Word message and mail to characters matching module 1022, voice messaging mails to voice match module 1024, and pictorial information mails to picture matching module 1026.After various matching modules are received the multimedia key word, search corresponding directory entry in concordance list of each leisure self such as text index table, speech index table, the picture indices table, send the search instruction that comprises directory entry then.
Store multimedia recording in the multimedia database 104, comprise Word message, voice messaging and pictorial information in every multimedia recording.Wherein, Word message can comprise that the multi country language and characters of same section word content represents, as Chinese (traditional font/simplified), English, Japanese, Korean, German, French etc., for example to for word " China ", the expression in its Chinese-traditional, English, Japanese, the Korean be respectively " middle Country ", " china ", " Chi ゅ ぅ ご く " and "
Figure A200710124618D0009143244QIETU
".Voice record can comprise the multi-lingual voice of same section voice content, as Chinese (traditional font/simplified), English, Japanese, Korean, German, French language voice etc., wherein, Chinese can be further divided into mandarin, Cantonese, GuangZhou native language, Teochew, Hakka, local nationalities' language voice etc. again.After multimedia database 104 is received search instruction, search corresponding multimedia recording and mail to output terminal 106 according to directory entry wherein.After output terminal 106 is received multimedia recording, show wherein written record and picture record, and play voice record.As selection, the output command that output terminal 106 also can receive by input end 100, according to the requirement output multimedia recording of output command, for example, and if output command only requires the output character record, output terminal 106 output character record only then.
The user also can be by the data typing module 1002 typing multimedia recordings in the input end 100.For example, if the user needs this record of typing " pigeon ", then can distinguish input characters record as " pigeon ", voice record as the pronunciation of " pigeon " and picture record as " picture of pigeon ".In addition, the user also can pass through data typing module 1002 input instruction codes, and the order line of this instruction code correspondence or phonetic order, generates homemade order line order of user or phonetic order.
Fig. 2 is the process flow diagram of multimedia retrieval system work process of the present invention.As shown in Figure 2, this flow process starts from step 200, receives the multimedia key word, and this multimedia key word can be multimedia messagess such as Word message, voice messaging or pictorial information, for example, the multimedia key word can be the pronunciation of literal " monkey ", " monkey " or the picture of " monkey ".In step 202, corresponding directory entry searched in the multimedia key word of identification input, promptly comprises the directory entry of this key word with the input keyword search.After finding corresponding directory entry, it is encapsulated in search instruction sends.In step 204, receive search instruction, search the multimedia recording of manipulative indexing clauses and subclauses.In step 206, the output multimedia recording.As selection, can need export content in the multimedia recording according to the user.If for example the multimedia key word is the picture of " monkey ", customer requirements is exported phonetic, input method information, English and the standard Chinese pronunciation of this picture correspondence, then will export the pronunciation of phonetic (houzi), five (qtbb), three (qrzv), English (monkey) and " monkey " mandarin.Again for example, the multimedia key word is literal " U.S. ", corresponding phonetic, input method information, English, Japanese and the Japanese pronunciation of customer requirements output then will be exported phonetic (meiguo), five (khlg), three (ewow), English (usa) and Japanese (ア メ リ カ).Again for example, input multimedia key word is literal " China ", corresponding English, the Korean of customer requirements output, then will export English (china) and Korean (
Figure A200710124618D0010143302QIETU
).In addition, the multimedia key word can also be a foreign language, and for example, the multimedia key word is English (USA), requires the output Japanese, then will export " ア メ リ カ ".Especially, the present invention can also be input with the mandarin, is output with the local dialect.For example, the input mandarin pronunciation " you where? ", output Guangdong language voice " your Bei limit degree? "In addition, can also be input with the local dialect, with the mandarin output.For example import Guangdong language voice “ Wo Mi ", output mandarin pronunciation " we ".
Native system can be integrated among the multiple application, can software mode be integrated in the chat softwares such as existing QQ, msn on phone, the computer as native system, so, exchange to transform and export the spoken and written languages that just can make both sides can both understand the other side, and the language that can understand the other side.For example in the two parties side in China and the opposing party in Korea S, both sides only understand the language of self, promptly in the side only understand Chinese mandarin, the Korean is only understood by South Korea.Both sides can be provided with the input of one's own side's literal so, and with the output of the other side's literal, middle side is provided with Chinese and mandarin input, and the output Korean shows and the Korean pronunciation that South Korea is provided with Korean and the input of Korean pronunciation, and output Chinese shows and standard Chinese pronunciation.So just can solve bipartite communication disorders.
The present invention also can realize by hardware mode.For example, the present invention can be embodied as portable system, when out on tours, if be ignorant of local language then can be by the setting to system, realizes with the input of one's own side's literal, with the purpose of local literal output.
The present invention can pass through hardware, software, and perhaps soft, combination of hardware realizes.The present invention can realize with centralized system at least one computer system, perhaps be realized with dispersing mode by the different piece in the computer system that is distributed in several interconnection.Anyly can realize that the computer system of described method or miscellaneous equipment all are applicatory.The combination of software and hardware commonly used can be the general-purpose computing system that computer program is installed, and by installing and carry out described program-con-trolled computer system, it is moved by described method.In computer system, utilize processor and storage unit to realize described method.
The present invention can also implement by computer program, and described program comprises whole features that can realize the inventive method, when it is installed in the computer system, by operation, can realize method of the present invention.Computer program in the present specification refers to: one group of any expression formula of instructing that can adopt any program language, code or symbol to write, this instruction group makes system have information processing capability, with direct realization specific function, or after carrying out following one or two step, a) convert other Languages, coding or symbol to; B) reproduce with different forms, realize specific function.
The present invention describes by several specific embodiments, it will be appreciated by those skilled in the art that, without departing from the present invention, can also carry out various conversion and be equal to alternative the present invention.In addition, at particular condition or concrete condition, can make various modifications to the present invention, and not depart from the scope of the present invention.Therefore, the present invention is not limited to disclosed specific embodiment, and should comprise the individual portion embodiment that falls in the claim scope of the present invention.

Claims (9)

1, a kind of multimedia retrieval system comprises input end and output terminal, it is characterized in that, also comprises:
Recognizer receives the multimedia key word by input end, searches the directory entry corresponding with it, sends the search instruction that comprises this directory entry;
Multimedia database receives search instruction, searches and comprise by output terminal output the multimedia recording of described directory entry.
2, system according to claim 1 is characterized in that, described recognizer comprises:
Type judging module;
At least one matching module;
Type judging module is judged the type of described multimedia key word, and it is mail to the matching module corresponding with its type.
3, system according to claim 2 is characterized in that, described at least one matching module comprises at least a in the following matching module:
The characters matching module;
The voice match module; And
The picture matching module.
4, system according to claim 1 is characterized in that, described input end comprises:
Simplify load module, receive the multimedia key word of simplifying input, generate the multimedia key word corresponding with it.
5, system according to claim 4 is characterized in that,
The multimedia key word of described simplification input comprises character formation element information;
Described simplification load module comprises:
The character generation module receives character formation element information, searches character map, generates its corresponding characters or statement.
6, according to claim 4 or 5 described systems, it is characterized in that,
The multimedia key word of described simplification input comprises structure sentence character information;
Described simplification load module comprises:
The statement generation module receives structure sentence character information, and the search statement mapping table generates its corresponding statement.
7, system according to claim 6 is characterized in that,
The multimedia key word of described simplification input comprises sound bite and voice command;
Described simplification load module comprises:
The speech production module receives described sound bite and voice command, searches the voice mapping table, generates corresponding voice content.
8, system according to claim 1 is characterized in that, described input end comprises:
Data typing module by described input end receiving multimedia information or instruction code, generates multimedia recording or operational order.
9, system according to claim 1 is characterized in that, described multimedia recording comprises at least a in Word message, voice messaging and the pictorial information; Described voice messaging comprises multiple natural language speech information.
10, a kind of multimedia retrieval method is characterized in that, comprises the steps:
A, reception multimedia key word;
B, search the directory entry of corresponding above-mentioned multimedia key word, send the search instruction that comprises directory entry;
C, search the multimedia recording that comprises above-mentioned directory entry;
The multimedia recording that D, output are found.
CNA2007101246189A 2007-11-20 2007-11-20 Multimedia retrieval system and method Pending CN101441626A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CNA2007101246189A CN101441626A (en) 2007-11-20 2007-11-20 Multimedia retrieval system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CNA2007101246189A CN101441626A (en) 2007-11-20 2007-11-20 Multimedia retrieval system and method

Publications (1)

Publication Number Publication Date
CN101441626A true CN101441626A (en) 2009-05-27

Family

ID=40726064

Family Applications (1)

Application Number Title Priority Date Filing Date
CNA2007101246189A Pending CN101441626A (en) 2007-11-20 2007-11-20 Multimedia retrieval system and method

Country Status (1)

Country Link
CN (1) CN101441626A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102831213A (en) * 2012-08-16 2012-12-19 广东小天才科技有限公司 Method and device for searching learning content and electronic product
CN103365970A (en) * 2013-06-25 2013-10-23 广东小天才科技有限公司 Method and device for automatically acquiring learning material information
CN104050188A (en) * 2013-03-15 2014-09-17 上海斐讯数据通信技术有限公司 Music search method and system
CN104462354A (en) * 2014-12-05 2015-03-25 国家电网公司 Multimedia system with multiple retrieval modes and processing method
CN104484426A (en) * 2014-12-18 2015-04-01 天津讯飞信息科技有限公司 Multi-mode music searching method and system
WO2017206861A1 (en) * 2016-05-29 2017-12-07 陈勇 Human-machine conversation platform
CN110110099A (en) * 2019-04-12 2019-08-09 华勤通讯技术有限公司 A kind of multimedia document retrieval method and device

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102831213A (en) * 2012-08-16 2012-12-19 广东小天才科技有限公司 Method and device for searching learning content and electronic product
CN102831213B (en) * 2012-08-16 2015-08-05 广东小天才科技有限公司 A kind of searching method of learning content, device and electronic product
CN104050188A (en) * 2013-03-15 2014-09-17 上海斐讯数据通信技术有限公司 Music search method and system
CN103365970A (en) * 2013-06-25 2013-10-23 广东小天才科技有限公司 Method and device for automatically acquiring learning material information
CN104462354A (en) * 2014-12-05 2015-03-25 国家电网公司 Multimedia system with multiple retrieval modes and processing method
CN104462354B (en) * 2014-12-05 2017-06-23 国家电网公司 A kind of multimedia system and processing method with various retrieval modes
CN104484426A (en) * 2014-12-18 2015-04-01 天津讯飞信息科技有限公司 Multi-mode music searching method and system
WO2017206861A1 (en) * 2016-05-29 2017-12-07 陈勇 Human-machine conversation platform
CN110110099A (en) * 2019-04-12 2019-08-09 华勤通讯技术有限公司 A kind of multimedia document retrieval method and device

Similar Documents

Publication Publication Date Title
EP0168814B1 (en) Language processing dictionary for bidirectionally retrieving morphemic and semantic expressions
CN102193643B (en) Word input method and input method system having translation function
CN101441626A (en) Multimedia retrieval system and method
CN101008864A (en) Multifunctional and multilingual input system for numeric keyboard and method thereof
US20050010391A1 (en) Chinese character / Pin Yin / English translator
CN106383814A (en) Word segmentation method of English social media short text
US20050010392A1 (en) Traditional Chinese / simplified Chinese character translator
CN1945692B (en) Intelligent method for improving prompting voice matching effect in voice synthetic system
CN102929865A (en) PDA (Personal Digital Assistant) translation system for inter-translating Chinese and languages of ASEAN (the Association of Southeast Asian Nations) countries
CN111553157A (en) Entity replacement-based dialog intention identification method
CN103164398B (en) Utilize the method that Chinese dimension language translated automatically by Chinese dimension e-dictionary
CN103164397A (en) Chinese-Kazakh electronic dictionary and automatic translating Chinese- Kazakh method thereof
CN109086285B (en) Intelligent Chinese processing method, system and device based on morphemes
CN103164396B (en) Use the method that Han Weihake language translated automatically by Han Weihake e-dictionary
CN103164395A (en) Chinese-Kirgiz language electronic dictionary and automatic translating Chinese-Kirgiz language method thereof
CN100561469C (en) Create and use the method and system of Chinese language data and user-corrected data
KR100463376B1 (en) A Translation Engine Apparatus for Translating from Source Language to Target Language and Translation Method thereof
CN110874527A (en) Cloud-based intelligent paraphrasing and phonetic notation system
Li et al. The study of comparison and conversion about traditional Mongolian and Cyrillic Mongolian
Cailliau et al. Enhanced search and navigation on conversational speech
CN103605755A (en) Hangul database, Hangul database construction method and Hangul database retrieval system
Miyagawa et al. Building Okinawan Lexicon Resource for Language Reclamation/Revitalization and Natural Language Processing Tasks such as Universal Dependencies Treebanking
Nazi et al. Byakto speech: Real-time long speech synthesis with convolutional neural network: Transfer learning from english to bangla
Gardner-Chloros et al. Coding and analysing multilingual data: the LIDES project
Lin et al. A Tibetan input method based on syllable word for mobile phone

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C12 Rejection of a patent application after its publication
RJ01 Rejection of invention patent application after publication

Open date: 20090527