CN1811697A - Pronunciation inputting method and device for hand carry-on device - Google Patents
Pronunciation inputting method and device for hand carry-on device Download PDFInfo
- Publication number
- CN1811697A CN1811697A CNA2005100062757A CN200510006275A CN1811697A CN 1811697 A CN1811697 A CN 1811697A CN A2005100062757 A CNA2005100062757 A CN A2005100062757A CN 200510006275 A CN200510006275 A CN 200510006275A CN 1811697 A CN1811697 A CN 1811697A
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- unit
- result
- database
- 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.)
- Granted
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
Present invention relates to a speech input method and system for handheld device. Said speech input method contains 1, selecting a language pattern, determining a sound basic identifying unit, 2, inputting a user sound and comparing said sound with said identifying unit for generating multi - identifying result,3, said user selecting one identifying result, searching a identifying result key word conversion table, using said multi - key word as unit to search a data base for finding out multi - screening result containing said key word, 4, when said user inputting next sound, repeating step 2 to step 3 for reducing screening resultant range, 5, when said user not inputting next sound, listing and displaying said screening result.
Description
Technical field
The present invention relates to a kind of pronunciation inputting method and system, relate in particular to a kind of pronunciation inputting method and system of device for hand carry-on.
Background technology
Storage Media capacity now is more and more big, and price is also more and more cheap, has become the product of a universalness.The capacity of the device for hand carry-on of selling on the market (for example carry-on dish, MP3 walkman, iPod) has reached several Giga, so it is unquestionable to put 200 first above songs.Like the song of listening slowly to look for by key one monic head up and down if will seek.
Device for hand carry-on does not have the interface of input characters, always can not external connection keyboard or device be abound with button on one's body, so just lose small and exquisite, be easy to carry, reached purpose simple to operate.With the MP3 walkman is example, and when the user wanted to listen certain first song, the existing practice can only be passed through device the small screen on one's body, by key, down searching stroke by stroke up and down.Problem is song when too many, and this method there is not efficient very much, and memory span constantly increases, and just the data that can store will be more and more many, make that the existing practice will be more and more inefficent.So, provide a method easily with voice input.
If interface by hommization, the method that is phonetic entry is sought song, not only can solve the problem that device for hand carry-on can't input characters, and the device for hand carry-on homogeneity in numerous brands all possesses in the function of " playback of songs ", " digital recording ", " hard disk with oneself ", " language learning ", take the course of its own the tool high additive value.
Therefore, in view of the defective of known technology, the present invention " pronunciation inputting method of device for hand carry-on and system " is proposed, in order to improve the defective of above-mentioned conventional means.
Summary of the invention
Pronunciation inputting method and the system of fundamental purpose of the present invention for a kind of device for hand carry-on is provided, it can support the function of multilingual input, and can select the basic identification unit of suitable voice according to existing hardware (for example central processing unit (CPU) and storer (Memory)).
Pronunciation inputting method and the system of another object of the present invention for a kind of device for hand carry-on is provided, the basic identification unit of its voice is what to separate with searching unit, therefore do not need exhaustive all glossarys, and database can expand infinitely.
Pronunciation inputting method and the system of another purpose of the present invention for a kind of device for hand carry-on is provided, it can be by a wireless network link to a remote server, with the database of this remote server of access.So not only can save the database volume of device for hand carry-on, more can strengthen the usefulness of device for hand carry-on.
According to above-mentioned conception, the invention provides a kind of pronunciation inputting method and system of device for hand carry-on, and the step of this pronunciation inputting method comprises: (a) select a language mode, determine the basic identification unit of voice; (b) input one user's voice, and contrast these voice and described identification unit, to produce a plurality of identification results; (c) this user select described identification result one of them, after searching one " identification result-key word " conversion table, serve as to search unit to search a database with these a plurality of key words, to find out a plurality of The selection result that contain described key word; (d) when this user imports next voice, repeating step (b) is to step (c), to dwindle the scope of described The selection result; And (e) when this user does not import next voice, arrange and show described The selection result.
Pronunciation inputting method as described, this device for hand carry-on are a walkman or a carry-on dish.
Pronunciation inputting method as described, the basic identification unit of these voice is phonetic symbol, syllable, speech or letter.
Pronunciation inputting method as described, this search unit is not for containing the key word of the basic identification unit of voice correspondences such as the syllable of tone, the syllable that contains tone, speech or letter.
Pronunciation inputting method as described, this identification unit produces via a multi-lingual unit.
Pronunciation inputting method as described, this multi-lingual unit is for determining to adopt the basic identification unit of which voice according to this language mode.
Pronunciation inputting method as described, described The selection result be via a syllable to the character conversion table, produce through searching this database, list the data that contain this character key word.
Pronunciation inputting method as described, described The selection result be via a character to the character conversion table, produce through searching this database, list the data that contain this character key word.
According to above-mentioned conception, the present invention provides a kind of voice entry system of device for hand carry-on in addition, and it comprises a multi-lingual unit, in order to responding the selected language mode of a user, and determines the basic identification unit of voice of this language mode; One database is in order to store data; And a conversion table, in order to responding at least one voice that this user imports and the comparing result of this basic identification unit of voice, and search this database to produce a plurality of The selection result.
Voice entry system as described, this device for hand carry-on are a walkman or a carry-on dish.
Voice entry system as described, the basic identification unit of these voice is phonetic symbol, syllable, speech or letter.
Voice entry system as described, these data are song files.
Voice entry system as described, this conversion table are that a syllable is to character map.
Voice entry system as described, this conversion table are that a character is to character map.
Voice entry system as described, this comparing result is searched unit as one and is searched this database, to produce described The selection result.
Pronunciation inputting method as described, this search unit is not for containing the key word of the basic identification unit of voice correspondences such as the syllable of tone, the syllable that contains tone, speech or letter.
Voice entry system as described, described The selection result is a song files, and deposits in this database.
Voice entry system as described also can be by a wireless network link to a remote server, with the database of this remote server of access.
According to above-mentioned conception, the present invention provides a kind of pronunciation inputting method of device for hand carry-on again, and its step comprises (a) and selects a language mode, determines the basic identification unit of voice; (b) input one user's voice, and contrast these voice and described identification unit, to produce a plurality of identification results; (c) this user select described identification result one of them, and serve as to search unit to search a database, to find out a plurality of The selection result that contain this search unit with this result; (d) when this user imports next voice, repeating step (b) is to step (c), to dwindle the scope of described The selection result; And (e) when this user does not import next voice, arrange and show described The selection result.
Pronunciation inputting method as described, this device for hand carry-on are a walkman or a carry-on dish.
Pronunciation inputting method as described, the basic identification unit of these voice is speech or letter.
Pronunciation inputting method as described, this search unit is speech or letter.
Pronunciation inputting method as described, this identification unit produces via a multi-lingual unit.
Pronunciation inputting method as described, this multi-lingual unit determines to adopt the basic identification unit of which voice according to this language mode.
Accompanying drawing is said figure
Fig. 1 is the process flow diagram of pronunciation inputting method of the device for hand carry-on of a preferred embodiment of the present invention.
Fig. 2 is that device for hand carry-on of the present invention is by the synoptic diagram of wireless network link to remote server.
Fig. 3 is the process flow diagram of pronunciation inputting method of the device for hand carry-on of another preferred embodiment of the present invention.
Wherein, description of reference numerals is as follows:
11: the user 13: multi-lingual unit
18: conversion table 19: database
21: device for hand carry-on 22: wireless network
23: remote server
Embodiment
In the present invention, we carry out identification with the basic identification unit of voice.With English is example, and letter is the basic identification units of voice; With Chinese is example, can adopt phonetic symbol or syllable.Because song, singer constantly weed out the old and bring forth the new, and all suitable limited of the computing power of general device for hand carry-on and memory resource, if carry out identification, can under the limited hardware resource, contain all databases with the basic identification unit of voice.If but hardware resource enough fills part, can consider that with " speech " be the basic identification units of voice.
See also Fig. 1, it is the process flow diagram of pronunciation inputting method of the device for hand carry-on of a preferred embodiment of the present invention.At first, user 11 selects a language mode (for example Chinese, amoyese, English, Japanese etc.), (step 12) with button input or phonetic entry; And simultaneously, multi-lingual unit 13 can decide the basic identification unit of voice (step 14) according to this language mode.Then, (step 15), these voice can compare with the basic identification unit of these voice user's 11 inputs one voice, to produce a plurality of identification results (step 16).Then, user 11 select described identification result one of them, search conversion table 18, to find out a plurality of search units (step 17) of this identification result correspondence.Then, seek the The selection result (step 110) that to contain these a plurality of search units in the database 19 be key word, at this moment, user 11 can determine whether continue to import next voice (step 111), when the user imports next voice, system is rebound step 15, and continuing to dwindle search area from described The selection result, so the result will be more and more accurately and fast; And when the user does not import next voice, then arrange and show described The selection result (step 112).
Above-mentioned described The selection result is via the key word of the selected identification result correspondence of user in the conversion table 18, search and to contain the data of this key word in the database 19 and produce, this conversion table 18 can be a syllable to character conversion table (syllable to character mapping table) or a character to the character conversion table.This database 19 has been deposited all song files.In addition, device for hand carry-on 21 of the present invention more can be attached to a remote server 23 by a wireless network 22, with the database of this remote server 23 of access, as shown in Figure 2.So not only can save the database volume of device for hand carry-on 21, more can strengthen the usefulness of device for hand carry-on 21.Below embodiment one～two be the preferred embodiment of said method.
Embodiment one
Searching Chinese songs, is the basic identification units of voice with the phonetic symbol, serves as to search unit with the pairing Chinese character of the syllable that does not contain tone, supposes that user 11 wants " liking as the sea " of listening singer " Li Xinjie " to sing, and then its step is as follows:
1, user 11 says: " ㄌ " (Lee: ㄌ one ˇ's: ㄌ).
2, identification result: " ㄌ ", " ㄋ ", " ㄉ " ..., select " ㄌ " by the user.
3, user's 11 nows are said: " one ".
4, the syllable of seeking everyday character is to the character conversion table:
ㄌ one
Go through the person in servitude from the strict example grain thunderbolt of encouraging of multitude's pears Li Lilililililili Li Lili
5, list the song files that contains these characters:
Blessing dawn-the heart of fast-wedding that I sharp figured woven silk material-Ai Tai of Tao Jingying-leave far opens schoolmate-1,000 sad reason Deng Li monarch-very sweet Chen Yi jump Lee Min-Aegean Lee's heart clean-Ai is as the excellent objective Li Lin in sea-admit one's mistake
6, at this moment, user 11 can press key searching up and down from results of screening, or continues screening from above-mentioned results of screening.
For example: user 11 says: ㄞ (likes: ㄞ ｀)
Identification result: " ㄞ ", " ㄢ ", " " ..., select " ㄞ " by user 11.
The syllable of seeking everyday character is to the character conversion table:
ㄞ
Dust suffer the sorrow delay short love hinder the Chinese mugwort dim mountain pass
List the song files that contains these characters:
Sharp figured woven silk material-Ai Tai Lee Min far away-Aegean Li Xingu-Ai is as the sea
Embodiment two
Searching Chinese songs, is the basic identification units of voice with the syllable, serves as to search unit with the pairing Chinese character of the syllable that contains tone, supposes that user 11 wants " liking as the sea " of listening singer " Li Xinjie " to sing, and its step is as follows:
1, user 11 says: ㄌ one ˇ
2, Bian Shi Knot fruit: " ㄌ one ˇ ", " ㄋ Shu ˇ ", " ㄌ one ' ", " ㄉ Shu ˇ " ..., select " ㄌ one ˇ " by user 11.
3, the syllable of seeking everyday character is to the character conversion table:
ㄌ one ˇ
In the Li Lilili
4, list the song files that contains these characters:
Open schoolmate-1,000 a sad reason Chen Yi fast-blessing Lee Min-Aegean Lee's heart of wedding is clean-Ai is as the excellent objective Li Lin in sea-admit one's mistake
5, user 11 can press key searching up and down from results of screening, or continues screening from above-mentioned results of screening.
For example: user 11 says: ㄞ ｀
Identification result: " ㄞ ｀ ", " ㄌ ㄞ ｀ ", " ㄋ ㄞ ｀ ", " ㄘ ㄞ ｀ ",
Select " ㄞ ｀ " by user 11.
The syllable of seeking everyday character is to the character conversion table:
ㄞ ｀
Like to hinder the warm mountain pass of Chinese mugwort to like
List the song files that contains these characters:
Lee Min-Aegean Lee's heart is clean-and Ai is as the sea
See also Fig. 3, it is the process flow diagram of pronunciation inputting method of the device for hand carry-on of another preferred embodiment of the present invention.At first, user 11 selects a language mode f for example Chinese, amoyese, English, Japanese etc. with button input or phonetic entry), (step 12); And simultaneously, multi-lingual unit 13 can decide the basic identification unit of voice (step 14) according to this language mode.Then, (step 15), these voice can compare with the basic identification unit of these voice user's 11 inputs one voice, to produce a plurality of identification results (step 16).Then, user ll select described identification result one of them, and serve as to search unit with this result, containing this search unit in the searching database 19 is the The selection result (step 31) of keyword, and at this moment, user 11 can determine whether continue to import next voice (step 111), when the user imports next voice, system is rebound step 15, and continuing to dwindle search area from described The selection result, so the result will be more and more accurately and fast; And when the user does not import next voice, then arrange and show described The selection result (step 112).Following embodiment three～five is the preferred embodiment of said method.
Embodiment three
Searching English song, is the basic identification units of voice with the English alphabet, with the English alphabet is to search unit, supposes that user 11 wants " Can ' t Fight The Moonlight " that listens singer " LeAnn Rimes " to sing, and its step is as follows:
1, user 11 says: " L ".
2, identification result: " l ", " a ", " r " selects " l " by user 11.
3, seek character to the character conversion table:
l
l/L
4, only list the song files (looking into English-word) that shelves invention beginning contains L or l character as e-dictionary.
5, filter out the song files of L beginning, can continue to say that character late proceeds to search this moment, to dwindle search area.
Embodiment four
Searching Chinese songs, is the basic identification units of voice with " speech ", serves as to search unit with " speech ", supposes that user 11 wants " liking as the sea " of listening singer " Li Xinjie " to sing, and its step is as follows:
1, user 11 says: Li Xinjie.
2, identification result: Li Xinjie, Li Yijun, Lee Min, Li Jia ..., select " Li Xinjie " by user 11.
3, search the song files that contains character " Li Xinjie " in the database, and the result is listed.
4, at this moment, user 11 can press key searching up and down from this result, or continues screening from this result.
Embodiment five
Searching Jealousy, is the basic identification units of voice with the Japanese 50 tone, serves as to search unit with hiragana or katakana.
For example, the user reads ka, a plurality of identification possible outcomes: か, さ,, は, ま ..., select hiragana " か " by user 11, search the song that occurs " か " key word in the title of the song, this moment, user 11 can press key searching up and down from results of screening, or continued to read the further screening of next voice to reduce the scope.
In sum, the present invention has following characteristics and advantage:
One, supports the function of multilingual input.
Two, can select according to existing hardware (for example central processing unit (CPU) and memory (Memory)) The basic identification unit of suitable voice.
Three, the basic identification unit of voice is what to separate with searching unit, does not therefore need exhaustive all glossarys, And database can infinitely expand.
Four, device for hand carry-on of the present invention can pass through a wireless network link to a remote server, with The database of this remote server of access. So not only can save the database volume of device for hand carry-on, More can strengthen the usefulness of device for hand carry-on.
As from the foregoing, the present invention can effectively improve the defective of known technology. The present invention is by the art technology people The member appoints and to execute the craftsman and think and do some and modify, however neither scope of taking off institute of the present invention wish protection.
Claims (13)
1. the pronunciation inputting method of a device for hand carry-on, its step comprises:
(a) select a language mode, determine the basic identification unit of voice;
(b) input one user's voice, and contrast these voice and described identification unit, to produce a plurality of identification results;
(c) this user select described identification result one of them, after searching one " identification result-key word " conversion table, serve as to search unit to search a database with these a plurality of key words, to find out a plurality of The selection result that contain described key word;
(d) when this user imports next voice, repeating step (b) is to step (c), to dwindle the scope of described The selection result; And
(e) when this user does not import next voice, arrange and show described The selection result.
2. pronunciation inputting method according to claim 1, wherein this device for hand carry-on is a walkman or a carry-on dish.
3. pronunciation inputting method according to claim 1, wherein:
The basic identification unit of these voice is phonetic symbol, syllable, speech or letter; And/or
This search unit is the key word that does not contain the basic identification unit of the voice correspondence of the syllable of tone, the syllable that contains tone, speech or letter.
4. pronunciation inputting method according to claim 1, wherein:
This identification unit produces via a multi-lingual unit; And/or
This multi-lingual unit determines to adopt the basic identification unit of which voice according to this language mode.
5. pronunciation inputting method according to claim 1, wherein said The selection result are via a syllable character conversion table to be produced through searching this database, list the data that contain this character key word.
6. pronunciation inputting method according to claim 1, wherein said The selection result are via a character character conversion table to be produced through searching this database, list the data that contain this character key word.
7. the voice entry system of a device for hand carry-on, it comprises:
One multi-lingual unit in order to responding the selected language mode of a user, and determines the basic identification unit of voice of this language mode;
One database is in order to store data; And
One conversion table in order to responding at least one voice that this user imports and the comparing result of this basic identification unit of voice, and is searched this database to produce a plurality of The selection result.
8. voice entry system according to claim 7, wherein these data are song files.
9. voice entry system according to claim 7, wherein this conversion table is that a syllable or a character are to the character conversion table.
10. voice entry system according to claim 7, wherein:
This comparing result is searched unit as one and is searched this database, to produce described The selection result; And/or
This search unit is the key word that does not contain the basic identification unit of the voice correspondence of the syllable of tone, the syllable that contains tone, speech or letter.
11. voice entry system according to claim 7, wherein said The selection result is a song files, and deposits in this database.
12. voice entry system according to claim 7 wherein also can be by a wireless network link to a remote server, with the database of this remote server of access.
13. the pronunciation inputting method of a device for hand carry-on, its step comprises:
(a) select a language mode, determine the basic identification unit of voice;
(b) input one user's voice, and contrast these voice and described identification unit, to produce a plurality of identification results;
(c) this user select described identification result one of them, and serve as to search unit to search a database, to find out a plurality of The selection result that contain this search unit with this result;
(d) when this user imports next voice, repeating step (b) is to step (c), to dwindle the scope of described The selection result; And
(e) when this user does not import next voice, arrange and show described The selection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100062757A CN100349109C (en) | 2005-01-27 | 2005-01-27 | Pronunciation inputting method and device for hand carry-on device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100062757A CN100349109C (en) | 2005-01-27 | 2005-01-27 | Pronunciation inputting method and device for hand carry-on device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1811697A true CN1811697A (en) | 2006-08-02 |
| CN100349109C CN100349109C (en) | 2007-11-14 |
Family
ID=36844645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2005100062757A Expired - Fee Related CN100349109C (en) | 2005-01-27 | 2005-01-27 | Pronunciation inputting method and device for hand carry-on device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100349109C (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923854A (en) * | 2010-08-31 | 2010-12-22 | 中国科学院计算技术研究所 | Interactive speech recognition system and method |
| US8463609B2 (en) | 2008-04-30 | 2013-06-11 | Delta Electronics Inc. | Voice input system and voice input method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02110600A (en) * | 1988-10-20 | 1990-04-23 | Matsushita Electric Ind Co Ltd | Voice rule synthesizing device |
| US6480819B1 (en) * | 1999-02-25 | 2002-11-12 | Matsushita Electric Industrial Co., Ltd. | Automatic search of audio channels by matching viewer-spoken words against closed-caption/audio content for interactive television |
| US6907397B2 (en) * | 2002-09-16 | 2005-06-14 | Matsushita Electric Industrial Co., Ltd. | System and method of media file access and retrieval using speech recognition |
| KR100547858B1 (en) * | 2003-07-07 | 2006-01-31 | 삼성전자주식회사 | Mobile terminal and method capable of text input using voice recognition function |
| CN2653596Y (en) * | 2003-07-24 | 2004-11-03 | 李希哲 | MP3 voice item requesting device |
-
2005
- 2005-01-27 CN CNB2005100062757A patent/CN100349109C/en not_active Expired - Fee Related
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8463609B2 (en) | 2008-04-30 | 2013-06-11 | Delta Electronics Inc. | Voice input system and voice input method |
| CN101923854A (en) * | 2010-08-31 | 2010-12-22 | 中国科学院计算技术研究所 | Interactive speech recognition system and method |
| CN101923854B (en) * | 2010-08-31 | 2012-03-28 | 中国科学院计算技术研究所 | Interactive speech recognition system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100349109C (en) | 2007-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101223572B (en) | System, program, and control method for speech synthesis | |
| CN1168068C (en) | Speech synthesizing system and speech synthesizing method | |
| CN1113305C (en) | Language processing apparatus and method | |
| CN1304988C (en) | Character input device | |
| CN100565525C (en) | A kind of computer Chinese input method and system | |
| CN1942875A (en) | Dialogue supporting apparatus | |
| JP2008520122A (en) | Method and system for searching for television content using reduced text input | |
| CN103021412A (en) | Voice recognition method and system | |
| CN101415259A (en) | System and method for searching information of embedded equipment based on double-language voice enquiry | |
| JP2012079252A (en) | Information terminal, character input method and character input program | |
| WO2014101410A1 (en) | Input processing method and apparatus | |
| CN106959999A (en) | Voice search method and device | |
| CN1117156A (en) | Kanji conversion result amending system | |
| CN101038508A (en) | GB phoneticize input method | |
| CN101901276A (en) | Intelligent query system and method | |
| CN1928860A (en) | Method, search engine and search system for correcting key errors | |
| CN1811697A (en) | Pronunciation inputting method and device for hand carry-on device | |
| CN1855102A (en) | Information processing apparatus, information processing method and program | |
| CN101042656A (en) | Application program engines startup method and system for hand held equipment | |
| WO2003044691A1 (en) | Method and apparatus for retrieving relevant information | |
| US20060149548A1 (en) | Speech input method and system for portable device | |
| CN1190773C (en) | Voice identifying system and compression method of characteristic vector set for voice identifying system | |
| CN1679023A (en) | Method and system of creating and using chinese language data and user-corrected data | |
| CN1144141C (en) | Change-over processor for Chinese input and method of change-over processing for Chinese input | |
| CN1881147A (en) | Apparatus for inputting Chinese character considering radicals and method thereof |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20071114 Termination date: 20160127 |
|
| EXPY | Termination of patent right or utility model |