CN101030130A - Manual device and method for inputting element by speech recognition - Google Patents
Manual device and method for inputting element by speech recognition Download PDFInfo
- Publication number
- CN101030130A CN101030130A CNA2006100242877A CN200610024287A CN101030130A CN 101030130 A CN101030130 A CN 101030130A CN A2006100242877 A CNA2006100242877 A CN A2006100242877A CN 200610024287 A CN200610024287 A CN 200610024287A CN 101030130 A CN101030130 A CN 101030130A
- Authority
- CN
- China
- Prior art keywords
- input
- voice
- recognition
- character
- unit
- 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
Links
Images
Landscapes
- Calculators And Similar Devices (AREA)
Abstract
A method of utilizing voice identification to realize character element input of hand device includes collecting an external voice by hand device through a voice collection unit in said hand device and converting collected voice to be voice data, identifying collected voice data by a voice identification databank of said hand device to generate an identification result of at least one character element, displaying identification result on display unit, selecting a character element according to an input signal generated by an input unit on said hand device and inputting said character element to operation image of display unit.
Description
Technical field
The present invention refers to a kind of handheld apparatus and method that can realize the character input according to speech recognition especially relevant for handheld apparatus.
Background technology
The world has marched toward the flourish scientific and technological epoch of an information now, and various information product development are not only very rapid, and has brought unlimited convenience for the mankind, and real life with us is closely bound up and inseparable.Along with constantly weeding out the old and bring forth the new of current all kinds of information products, people are for the function of information product, quality requirements is also more and more higher, and each tame dealer is for catering to consumer demand, constantly in information product, add new function, especially, mobile phone in these information products, become in the daily life of most of people and be important communication tool, this mobile phone also can utilize the news in brief transmission except that can conversing, link up, hence one can see that, information product market now, the fierce degree of its sales contest, real ineffable, on market, be flooded with the situation of countless labels with mobile phone, if can't cater to the more and more higher demand of consumer, will on the selling market, be eliminated by wash one's face, so, the manufacturer of mobile phone, whether following product newly developed provides more convenient, more effective function, just like become the manufacturing technology of estimating the manufacturer, whether taken the lead one of important indicator of industry.Especially, the adding of functions such as news in brief transmission, telephone directory and electronic dictionary makes this mobile phone must use on it existing button to carry out the literal input.
So, along with new function constantly is added into mobile phone, also bring new problem for mobile phone in the lump.For example: the manufacturer of mobile phone, for catering to consumer's demand easy to carry, constantly dwindle the volume of mobile phone, make this mobile phone not have identical size and the identical keyboard of number of keys with computer, with present prior mobile phone, button on it has only numerical key, * and # symbolic key and two function keys of 0～9 basically, and these buttons mate several English alphabets, phonetic symbol or other symbols usually, make button quite inconvenience aspect the literal input of mobile phone.For the shortcoming of existing input method is described, below lift two kinds of common input methods explanations now:
(1) repeatedly knock input method: this kind input method is for each letter in the English-word, mostly must be after same button be pushed several times, just correct letter can appear on the display of mobile phone, for example: the output English-word " student ", this mobile phone must be introduced under the pattern of English input, at numerical key " 7 " the position on push 4 times, and will occur 7 in regular turn at this display, p, q, s, after waiting certain hour, again in numerical key " 8 " the position on push 1 time, wait certain hour again, again in numerical key " 8 " the position on push 2 times, wait certain hour again, again in numerical key " 3 " the position on push 1 time, wait certain hour again, again in numerical key " 3 " the position on push 2 times, wait certain hour again, again in numerical key " 6 " the position on push 2 times, wait certain hour again, again in numerical key " 8 " the position on push 1 time, the pressing function key is determined input more at last, so, finish the output English-word " student " compression number 13 times altogether on each numerical key.
(2) intelligent (T9) input method: this kind input method is imported the letter of each individual character, only need push each button and once can show on this display.For example: English-word " student ", as long as on numerical key 7,8,8,3,3,6 and 8, respectively push once in regular turn, and when pushing numerical key at every turn, can not must wait, can finish input, and on display, show, so, finish the output English-word " student " compression number on each numerical key amounts to 7 times, and each pressing keys must not waited for.
In addition, along with speech recognition technology is ripe gradually, also in various electronic equipments, add speech recognition technology one after another, but because the diversity factor and the complicacy height of human language, the real input that is difficult to entirely true ground in each electronic equipment, so, be provided with a speech recognition library in the general electronic equipment (as computer), by comparing existing identification data in received sound message and this speech recognition library, improve phonetic recognization rate, but be subjected to various restrictions such as speed, storage volume at all kinds of mobile phones, its discrimination will be far below general computer.
So, by above-mentioned two kinds of input methods and speech recognition technology as can be known, respectively the time of the number of times of this input method required input and cost is still too many, and speech recognition technology has many restrictions in the sky earlier in the application of mobile phone, especially, when news in brief transmits, usually the literal of being imported is not only one, it will be more using this two input method or time that speech recognition technology spent, in the epoch of stressing efficient now, this two input method and speech recognition technology are the practices that is not inconsistent very much the tendency of the day, so, if can there be a kind of input method faster to occur, believe it is that consumer and dealer find pleasure in and see.
Summary of the invention
Because aforesaid many shortcoming inventors are through the permanent research and experiment of making great efforts, finally development and Design goes out a kind of handheld apparatus and method of utilizing speech recognition to realize the character input of the present invention, in the hope of by proposition of the present invention, can contribute to some extent society.
One object of the present invention is to provide a kind of handheld apparatus that utilizes speech recognition to realize the character input, this device is provided with a voice collecting unit, one voice recognition unit, one storage unit, one display unit and an input block, wherein this voice collecting module is gathered and is produced one to the outside voice that produce of this device and gathers speech data, this voice recognition unit system utilizes the interior set speech recognition database of this storage unit that this collection speech data is discerned, in order to produce a recognition result with at least one character, this recognition result can be sent to the input of one on this display unit picture and show, and these characters can be according to the input signal that this input block produced, and on the selected operation screen that is input to this display unit.
Another object of the present invention is a kind of method of utilizing speech recognition to realize the character input, this method is that a handheld apparatus utilizes its set voice collecting unit that the outside voice of this device are gathered, and this speech conversion become a speech data, then, the set voice recognition unit of this handheld apparatus receives this speech data, and utilize the set speech recognition database of this handheld apparatus that this collection speech data is discerned, in order to produce a recognition result with at least one character, then, the input picture that this recognition result is sent to the set display unit of this handheld apparatus shows, an input signal that is produced according to the set input block of this handheld apparatus is chosen a character that should input signal again, and this character is input on the operation screen of this display unit.
For ease of to the object, the technical characteristics and the effect of the present invention, do further understanding and understanding, for the embodiment conjunction with figs., be described in detail as follows now:
Description of drawings
Fig. 1 is a configuration diagram of the present invention;
Fig. 2 is the synoptic diagram of input picture of the present invention and operation screen;
Fig. 3 is an action flow chart of the present invention;
Fig. 4 is the action flow chart that recognition result of the present invention is imported into operation screen;
Fig. 5 is the action flow chart that recognition result of the present invention is presented at display unit.
Embodiment
The invention provides a kind of handheld apparatus and method of utilizing speech recognition to realize the character input, see also shown in Figure 1, this device is provided with a voice collecting unit 1, one voice recognition unit 2, one storage unit 3, one display unit 4 and an input block 5, wherein the outside voice that produce of 1 pair of this device in this voice collecting unit are gathered and are produced one and gather speech data, this voice recognition unit 2 utilizes these storage unit 3 interior set 30 pairs of these collection speech datas of a speech recognition database to discern, in order to produce a recognition result 302 with at least one character, this recognition result 302 can be sent to the input of one on this display unit 4 picture 40 and show, and the input signal that these characters can be produced according to this input block 5, and on the selected operation screen 42 that is input to this display unit 4.
In the present invention, this input block 5 can be a keyboard, one mouse or touch-control firefly screen wait one of them, this input block 5 was triggered and can produces this input signal when this recognition result showed at this input picture 40, this display unit 4 can be a LCD, this display unit 4 can be according to producing this input picture 40 and this operation screen 42 in these storage unit 3 set application programs 32, this speech recognition database 30 is provided with a plurality of sample voice data 300 and recognition result 302, respectively these sample voice data 300 are distinguished corresponding recognition results 302, this voice recognition unit 2 has a sample speech data 300 of identical content with this collection speech data search, the sample voice data 300 that this voice recognition unit 2 searches according to this quilt again, all characters of the sample voice data 300 pairing recognition results 302 that this quilt is searched are sent to this input picture and show 40 and illustrate, this voice collecting unit 1 can be a microphone (Microphone), and this memory bank unit 3 can be one and only reads a memory bank (ROM) or a flash body (Flash).
The invention provides a kind of method of utilizing speech recognition to realize the character input, see also shown in Fig. 1 and 2, this method is that a handheld apparatus utilizes voice of its set 1 pair of this device outside, a voice collecting unit to gather, and become one to gather speech data this speech conversion, then, the set voice recognition unit 2 of this handheld apparatus receives this and gathers speech data, this voice recognition unit 2 also utilizes 3 pairs of these collection speech datas of the set speech recognition database of this handheld apparatus to discern, in order to produce a recognition result 300 with at least one character, then, the input picture 40 that this recognition result 300 is sent to the set display unit 4 of this handheld apparatus shows, an input signal that is produced according to the set input block 5 of this handheld apparatus is chosen a character that should input signal again, and this character is input on the operation screen 42 of this display unit 4.
Because, character in this recognition result 300 may have only one, if when the character in this recognition result 300 only has one, also want the user to trigger this input block 5, can cause the inconvenience in the use in fact, so, in the present invention, see also shown in Figure 3, when this recognition result 300 is sent to after this input picture 40 shows, can handle according to the following step, with the character that makes this recognition result more easily mode be imported on this operation screen 42:
(401) recognition result 300 that this voice recognition unit 2 is produced judges whether only to have a character, if carry out the following step, otherwise carries out step (404);
(402), then produce an input signal of choosing this character automatically if this recognition result 300 only has a character;
(403) again according to the input signal that should produce automatically, this character is input on this operation screen 42;
(404) if this recognition result 300 is not only had a character, then all characters with this recognition result 300 are sent to this input picture 40, and are presented at this input picture 40;
(405) choose a character that should input signal when an input signal that is produced according to this input block 5, and this character is input on this operation screen 42.
In the present invention, this speech recognition database 30 is located in the set storage unit 3 of this handheld apparatus, and this speech recognition database 30 is provided with a plurality of sample voice data 300 and recognition result 302, respectively these sample voice data 300 are distinguished corresponding recognition results 302, and this handheld apparatus can be presented at arbitrary recognition result 300 on this display unit 4 according to the following step:
(501) at first, this voice recognition unit 2 be search whether to have a sample speech data 300 that has identical content with this collection speech data in this speech recognition database 30, if carry out the following step, otherwise carry out step (503);
(502) the sample voice data 300 that search according to this quilt again of this voice recognition unit 2, all characters of the sample voice data 300 pairing recognition results 302 that this quilt is searched are sent to this input picture 40 and show;
(503) prompting message of speech data can't identification be gathered in 4 outputs of this display unit.
For more understanding this case, below illustrate an input process of the present invention, this voice collecting unit 2 receives a collection speech data of being received and is " kai (opening) ", then this voice recognition unit 2 searches the sample voice data 300 of " kai " in this speech recognition database, and all characters of sample voice data 300 pairing recognition results 302 that should " kai " are " 1. open; 2. wipe, 3., 4.; 5.; 6.K ", and these characters " 1. open, 2. wipe; 3.; 4., 5., 6.K " be displayed on this input picture 40, and this input block 5 can be a keyboard, after making that the numerical key (as numerical key " 1 ") of these characters of this keyboard correspondence is pressed, this keyboard can produce an input signal and choose a character that should input signal " is held ", and this character is input on the operation screen of this display unit.
By as can be known above-mentioned, this speech recognition database 30 all is collected in the character of akin pronunciation in the same recognition result 302, and will all characters that should recognition result 302 be presented on this input picture 40, make the user only will choose the pairing numeral of the literal that to import mutually, can finish input, so, this handheld apparatus will not need the high capacity speech recognition database of the speech recognition technology of high-res, the solution speech recognition technology will be located at the problem in the restriction of handheld apparatus, in addition, also make this handheld apparatus the time of input number of times of required input and cost will become less, other traditional input methods of fullsized are quicker.
The above only is a specific embodiment of the best of the present invention, but structural attitude of the present invention is not limited thereto, and anyly is familiar with present technique field person in field of the present invention, can think easily and variation or modification, all can be encompassed in the claim of following this case.
Claims (14)
1, a kind of handheld apparatus that utilizes speech recognition to realize the character input comprises:
One voice collecting unit, this voice collecting unit is gathered the outside voice that produce of this device, and produces a collection speech data;
One storage unit is provided with a speech recognition database
One voice recognition unit is connected respectively to this voice collecting unit and storage unit, and this voice recognition unit utilizes this speech recognition database that this collection speech data is discerned, and has at least one character and a recognition result in order to produce;
One display unit is connected with this voice recognition unit, and can receives this recognition result, and exportable to an input picture that should recognition result;
One input block is connected with this display unit, and can produces an input signal, and this device can be input to a selecteed character on one operation screen of this display unit according to this input signal.
2, device as claimed in claim 1 is characterized in that, this input block be a keyboard, a mouse or a Touch Screen one of them.
3, device as claimed in claim 2 is characterized in that, this input block system and this display unit are under the state that demonstrates this input picture, and just can be triggered produces this input signal.
4, device as claimed in claim 3 is characterized in that, this display unit is a LCD.
5, device as claimed in claim 4 is characterized in that, this storage unit is provided with an application program, and this display unit produces this input picture and this operation screen according to this application program.
6, device as claimed in claim 5 is characterized in that, this speech recognition database comprises:
A plurality of recognition results;
A plurality of sample voice data, the respectively respectively corresponding recognition result of these sample voice data;
And should gather under the state of a sample speech data of speech data coupling identical content, this voice recognition unit can be sent to this input picture with all characters of the pairing recognition result of sample voice data of this coupling and show.
7, device as claimed in claim 6 is characterized in that, this voice collecting unit is a microphone.
8, device as claimed in claim 6 is characterized in that, this memory bank unit can be a read-only memory bank.
9, device as claimed in claim 6 is characterized in that, this memory bank unit can be flash body one by one.
10, a kind of method of utilizing speech recognition to realize the character input is that a handheld apparatus carries out speech recognition realization character input processing according to the following step:
The set voice collecting unit of this handheld apparatus is gathered the outside voice of this device, and becomes one to gather speech data this speech conversion;
Then, the set voice recognition unit of this handheld apparatus receives this collection speech data;
This collection speech data is discerned according to the set speech recognition database of this handheld apparatus by this voice recognition unit again, in order to produce a recognition result with at least one character;
Then, this recognition result be sent to the set display unit of this handheld apparatus one the input picture show;
An input signal that is produced according to the set input block of this handheld apparatus is chosen a character that should input signal again, and this character is input on the operation screen of this display unit.
11, method as claimed in claim 10 is characterized in that, when this recognition result is sent to after this input picture shows, can handle according to the following step, with the character that makes this recognition result more easily mode be imported on this operation screen:
The recognition result that this voice recognition unit produced is judged whether only to have a character;
If this recognition result only has a character, then produce an input signal of choosing this character automatically;
According to the input signal that should produce automatically, this character is input on this operation screen again.
12, method as claimed in claim 11 is characterized in that, when this recognition result not only being had a character, then all characters with this recognition result are sent to this input picture, and are presented at this input picture;
When an input signal that is produced according to the set input block of this handheld apparatus is chosen a character that should input signal, and this character is input on the operation screen of this display unit.
13, method as claimed in claim 12, it is characterized in that, this speech recognition database is located in the set storage unit of this handheld apparatus, and this speech recognition database is provided with a plurality of sample voice data and recognition result, respectively these sample voice data are distinguished corresponding recognition result, and this handheld apparatus can be presented at arbitrary recognition result on this display unit according to the following step:
Whether this voice recognition unit search is to have a sample speech data that has identical content with this collection speech data in this speech recognition database;
If have a sample speech data that has identical content with this collection speech data, the sample voice data that this voice recognition unit searches according to this quilt again, all characters of the pairing recognition result of sample voice data that this quilt is searched are sent to this input picture and show.
14, method as claimed in claim 13 is characterized in that, if do not have a sample speech data that has identical content with this collections speech data, and the prompting message that this display unit output can't identification collection speech data then.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006100242877A CN101030130A (en) | 2006-03-02 | 2006-03-02 | Manual device and method for inputting element by speech recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006100242877A CN101030130A (en) | 2006-03-02 | 2006-03-02 | Manual device and method for inputting element by speech recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101030130A true CN101030130A (en) | 2007-09-05 |
Family
ID=38715505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2006100242877A Pending CN101030130A (en) | 2006-03-02 | 2006-03-02 | Manual device and method for inputting element by speech recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101030130A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871409A (en) * | 2012-12-17 | 2014-06-18 | 联想(北京)有限公司 | Voice identifying method, information processing method and electronic equipment |
| CN104400784A (en) * | 2014-11-26 | 2015-03-11 | 深圳控石智能***有限公司 | Voice-controllable industrial robot system |
| CN104463393A (en) * | 2013-09-17 | 2015-03-25 | 中国农业科学院农业信息研究所 | Speech-based agricultural product price collection method |
| CN107004416A (en) * | 2014-11-20 | 2017-08-01 | 雅马哈株式会社 | Information transmitting apparatus, method for sending information, guiding system and communication system |
| US9959865B2 (en) | 2012-11-13 | 2018-05-01 | Beijing Lenovo Software Ltd. | Information processing method with voice recognition |
| CN110308886A (en) * | 2018-03-27 | 2019-10-08 | 三星电子株式会社 | The system and method for voice command service associated with personalized task are provided |
-
2006
- 2006-03-02 CN CNA2006100242877A patent/CN101030130A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9959865B2 (en) | 2012-11-13 | 2018-05-01 | Beijing Lenovo Software Ltd. | Information processing method with voice recognition |
| CN103871409A (en) * | 2012-12-17 | 2014-06-18 | 联想(北京)有限公司 | Voice identifying method, information processing method and electronic equipment |
| CN103871409B (en) * | 2012-12-17 | 2018-01-23 | 联想(北京)有限公司 | A kind of method of speech recognition, the method for information processing and electronic equipment |
| CN104463393A (en) * | 2013-09-17 | 2015-03-25 | 中国农业科学院农业信息研究所 | Speech-based agricultural product price collection method |
| CN107004416A (en) * | 2014-11-20 | 2017-08-01 | 雅马哈株式会社 | Information transmitting apparatus, method for sending information, guiding system and communication system |
| CN104400784A (en) * | 2014-11-26 | 2015-03-11 | 深圳控石智能***有限公司 | Voice-controllable industrial robot system |
| CN110308886A (en) * | 2018-03-27 | 2019-10-08 | 三星电子株式会社 | The system and method for voice command service associated with personalized task are provided |
| CN110308886B (en) * | 2018-03-27 | 2024-03-01 | 三星电子株式会社 | System and method for providing voice command services associated with personalized tasks |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6864809B2 (en) | Korean language predictive mechanism for text entry by a user | |
| CN101030130A (en) | Manual device and method for inputting element by speech recognition | |
| CN104468959A (en) | Method, device and mobile terminal displaying image in communication process of mobile terminal | |
| CN1619585A (en) | Apparatus and method for inputting character using touch screen in portable terminal | |
| TW201234213A (en) | Multimedia input method | |
| CN100374991C (en) | Portable keyboard and fingerprint feature information extracting method thereof | |
| CN102394960A (en) | Dialing system and method and mobile communication terminal | |
| CN102129319A (en) | Fast information interactive system and interactive method thereof | |
| CN101341531A (en) | A method and apparatus for accessing a digital file from a collection of digital files | |
| CN110413106B (en) | Augmented reality input method and system based on voice and gestures | |
| EP2851891B1 (en) | Mobile user terminal and method for controlling such a terminal | |
| CN108536653A (en) | A kind of input method, device and the device for input | |
| CN116595069A (en) | Big data-based filtering display method and system | |
| CN202795331U (en) | Electronic device with sound control keying function | |
| CN2507203Y (en) | Mobile telephone set with full screen hand write input function | |
| CN1752906A (en) | Cell phone Chinese character input method | |
| CN101242599A (en) | Mobile phone command input device and method | |
| CN1105985C (en) | Device and method for Chinese input by hand writing and speech sound | |
| CN104699775A (en) | Contact person dialing searching method and system thereof for mobile terminal | |
| CN1674603A (en) | Method for realizing one-hand inputting on hand writing screen of mobile phone | |
| KR100750634B1 (en) | Device for input and output Chinese characters | |
| CN1627320A (en) | Hand held type electronic equipment possessing inputting function of inducing locus | |
| KR101643563B1 (en) | Apparatus and method for processing text recognition using camera of portable terminal | |
| CN1466039A (en) | Electronic remote controller capable of inputting Chinese and various characters | |
| RU2005122408A (en) | METHOD FOR ENTERING SIGNS INTO MOBILE TERMINAL |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |