CN101571752A - Input device of voice keyboard based on Chinese ideograph phrases - Google Patents
Input device of voice keyboard based on Chinese ideograph phrases Download PDFInfo
- Publication number
- CN101571752A CN101571752A CNA2008101052510A CN200810105251A CN101571752A CN 101571752 A CN101571752 A CN 101571752A CN A2008101052510 A CNA2008101052510 A CN A2008101052510A CN 200810105251 A CN200810105251 A CN 200810105251A CN 101571752 A CN101571752 A CN 101571752A
- Authority
- CN
- China
- Prior art keywords
- phrase
- display
- chinese character
- speech sound
- key
- 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
- Input From Keyboards Or The Like (AREA)
Abstract
The invention discloses an input device of a voice keyboard based on Chinese ideograph phrases, which relates to the field of voice keyboard input and is characterized by comprising a priority selection key used for recalling phrases relevant to received voice phonemes from a memory and displaying the phases on a display, wherein when a plurality of phrases are arrayed, the priority selection key of the keyboard is used for selecting phrases arranged preferentially, and the priority selection key is the spacebar. The invention overcomes deficiencies of voice technology and keyboard technology, integrates the advantages of the two technologies and enhances input speed of people on the basis of prior voice recognition technology.
Description
Technical field
The present invention relates to voice keyboard input field, proposed a kind of input media of the voice keyboard based on the Chinese character phrase.
Background technology
Finish jointly in the process of literal input at the composite set that carries out keyboard and voice entry system, how the keyboard input cooperates with phonetic entry is a very crucial content.
If cooperate the bad input efficiency that can not improve Chinese character, but the input efficiency that how to improve Chinese character is a technical matters that awaits solving.
How can improve the efficient of phonetic entry, or how can utilize the operation that helps of keyboard can improve the efficient of phonetic entry,
This is that background technology does not have related data, and the present invention solves will solve a problem exactly, improves the efficient of phonetic entry by keyboard.
Under the very universal situation of existing typewriting input equipment, still a lot of input technologies is being arranged in continuous appearance.
Main cause wherein is because existing input technology still can not solve the needs of people in the literal input of daily life in the middle of neutralization work.
If to rely on keyboard fully be not all right so want really to improve input speed, the keyboard input is not meet people's speech habits in addition, and people's speech habits are mainly finished in the mode by language.
So keyboard technique has brought very white elephant to people, the own ability that makes people must break away from oneself is gone extra a kind of new ability of obtaining, and carries out the input of language by this new ability.
People exactly because itself being people, this new ability do not have, so just must carry out other paying and this many times that will waste people, many energy of waste people, waste people's the many money paid.
People are being paid through these, elapsed time, money a large amount of pay after still can not well grasp input technology, this is very irrational.
So we should go to address this problem the deficiency that overcomes in the middle of the prior art as far as possible.
Summary of the invention
This is that background technology does not have related data, and the present invention solves will solve a problem exactly, improves the efficient of phonetic entry by keyboard.
Input technology is divided into keyboard technique and non-keyboard technology in the prior art, but not keyboard technique can comprise the phonetic entry technology.
But voice technology and keyboard technique break away from fully in the prior art, and this disengaging requires people or uses keyboard technique or use voice technology, and does not allow to adopt other mode, and this is irrational in fact.
Voice technology itself is incomplete, because voice technology can not be accomplished the hundred-percent identification to literal, and keyboard technique is because people's study and operation easier cause people to be difficult to grasp the input technology of keyboard when using.
So be that keyboard technique or voice technology all can not well solve the input problem, therefore to solve the input problem and just should try every possible means two technology to be carried out comprehensively the advantage of integrated voice technology and keyboard technique.
Be that voice technology or keyboard technique all have separately defective that separately advantage is also arranged certainly, if the invention with the advantages of two technology might produce a greatness can realize the speech recognition that some are basic on existing speech recognition technology.
For example can realize the identification of phrase and individual character in the middle of existing voice technology, though this identification can not be accurate to concrete and Chinese character and phrase, this has created condition as the combination of voice and two technology of keyboard this identification.
If we utilize speech recognition technology to carry out oral account person's Chinese character and word are discerned substantially, cooperate the content of speech recognition to carry out the work in second step again by keyboard, just might produce an extraordinary technology.
This technology can solve language input problem substantially, and the input problem that also solved high-level efficiency though some people can read out some word in the input process of reality, allows him this word is write out to be actually not necessarily to write draw.
If but phonetically similar word is all listed to him, he might select fully accurately by its words of selecting, and this is a kind of special memory effect and memory phenomenon.
It is because people are superficial to the memory degree of this word or individual character that but people can select can accurately not propose in advance.
If we can make people will remember more shallow Chinese character or phrase by equipment of the present invention can to import by prompting so, undoubtedly will improve people's input efficiency, certainly also alleviated people's memory burden greatly, this present invention just can play positive efficient.
The objective of the invention is finally to improve people's input efficiency in order to bring into play phonetic entry technology and keyboard input technology advantage separately.
A kind of input media of the voice keyboard based on the Chinese character phrase, it is characterized in that, comprise a preferential options button, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display, when being arranged as a plurality of phrase, select the phrase of prioritization by the preferential options button of keyboard, preferential options button is a space bar.
By phonetic entry the time after the oral account of finishing a phoneme of speech sound unit, show the phrase relevant in the display with oral account, select by keyboard, when the shown phrase of display for not only one the time, the frequency difference difference that puts in order puts in order with frequency as foundation, carries out advantage by frequency order and arranges, frequency is the highest be arranged in before frequency minimum be arranged in after, arrange the most preceding phrase and select by preferential options button.
Space bar is served as preferential options button, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display, be used for selecting being arranged in the first phrase, also comprise other options button of phrase, phrase after first is used for selecting to put in order.
Numerical key can be used as options button, is used for selecting phrase shown in the display, is used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
Part key in the numerical key can be used as options button, is used for selecting phrase shown in the display, is used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
Whole keys in the numerical key can be used as options button, are used for selecting phrase shown in the display, are used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
Letter key can be used as options button, is used for selecting phrase shown in the display, is used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
Part key in the letter key can be used as options button, can be used for selecting phrase shown in the display, is used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
Whole keys in the letter key can be used as options button, can be used for selecting phrase shown in the display, are used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
The punctuation mark key can be used as options button, can be used for selecting phrase shown in the display, is used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
Part key in the punctuation mark key can be used as options button, can be used for selecting phrase shown in the display, is used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
Whole keys in the punctuation mark key can be used as options button, can be used for selecting phrase shown in the display, are used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
By the options button of letter key as phrase, be used for selecting a phoneme receive after a shown phrase, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
Comprise a page turning key, when being used for after first screen shows, can not comprising the Chinese character of being correlated with in the middle of whole storeies, carry out page turning by page turning key.
Comprise a page turning key, when being used for after first screen shows, can not comprising the phrase of being correlated with in the middle of whole storeies, carry out page turning by page turning key.
Add key is used for carrying out page turning as page turning key.
May further comprise the steps:
Receive phoneme of speech sound;
Show the Chinese character relevant with phoneme of speech sound;
Select by options button;
Or carry out page turning by page turning key;
Confirm by confirming device;
Return.
Comprise a speech recognition equipment, Chinese character individual character and the Chinese character phrase that the importer gives an oral account discerned in the voice that are used for sending according to the importer.
The discriminating device that comprises a Chinese character or phrase phoneme of speech sound, being used for distinguishing the phoneme of speech sound that the importer sends is that Chinese character still is the Chinese character phrase.
The receiving trap that comprises a voice individual character phoneme is used for receiving the phoneme of speech sound of the Chinese character individual character that the importer sends.
The receiving trap that comprises a voice Chinese character phrase phoneme is used for receiving the phoneme of speech sound of the Chinese character phrase that the importer sends.
The dictionary memory storage that comprises a Chinese character is used for storing and a Chinese character that the phonetic Chinese character phoneme is relevant, accesses relevant Chinese character when the receiving trap of voice individual character phoneme receives the phoneme of speech sound of the Chinese character individual character that the importer sends from the dictionary of Chinese character.
The dictionary memory storage that comprises a Chinese character, be used for storing and a Chinese character that the phonetic Chinese character phoneme is relevant, when the receiving trap of voice Chinese character phrase phoneme receives the phoneme of speech sound of the Chinese character phrase that the importer sends, from the dictionary of Chinese character, access relevant Chinese character.
Comprise an indexing unit, be used for from storer, accessing relevant Chinese character or phrase tabulation according to the received phoneme of speech sound of receiving trap of voice Chinese character or phrase phoneme.
Comprise a display device, be used for from storer, accessing relevant Chinese character or phrase and show individual character relevant or the tabulation of Chinese character phrase with phoneme of speech sound according to indexing unit.
Comprise a keyboard selecting arrangement, be used for showing that according to display device shown from storer, access relevant Chinese character or phrase individual character relevant with phoneme of speech sound or the tabulation of Chinese character phrase select, and confirm.
Comprise that one is selected information receiver, is used for receiving the select command of being sent from the keyboard selecting arrangement.
Comprise an affirmation device, be used for finally confirming to select the information that information receiver received and finally lock its Chinese character confirmed or phrase and be transferred to text area to show.
Comprise a control device, be used for to dictionary memory storage and indexing unit and the display device and the keyboard selecting arrangement of the receiving trap of the discriminating device of speech recognition equipment and Chinese character or phrase phoneme of speech sound and voice individual character phoneme and Chinese character and select information receiver and confirm that device carries out work control.
Comprise a control device that postpones the reception of phoneme of speech sound, be used for postponing the reception of phoneme of speech sound.
Comprise a reception rebooting device that carries out phoneme of speech sound again, the reception that is used for restarting phoneme of speech sound.
Whether the judgment means that comprises a reset command is used for finally choosing Chinese character or word in the tabulation to determine whether to restart the new phoneme of speech sound of reception by keyboard according to the importer.
Comprise a control device, be used for to the control device of the reception that postpones phoneme of speech sound and carry out the reception rebooting device of phoneme of speech sound again and the judgment means of reset command is carried out work and controlled.
Description of drawings
Accompanying drawing 1 is a kind of implementation method of voice keyboard input control device.
Wherein 1 is to receive phoneme of speech sound.
Wherein 2 is to show the Chinese character relevant with phoneme of speech sound.
Wherein 3 is to be selected by options button.
Wherein 4 are or carry out page turning by page turning.
Wherein 5 is to be confirmed by the affirmation device.
Embodiment
Embodiment 1:
Wherein 1 is to receive phoneme of speech sound.
Wherein 2 is to show the Chinese character relevant with phoneme of speech sound.
Wherein 3 is to be selected by options button.
Wherein 4 are or carry out page turning by page turning.
Wherein 5 is to be confirmed by the affirmation device.
The present invention's statement:
Content disclosed in this invention can make those skilled in the art with reference to enforcement, and the present invention is related The content itself that reaches and improvement on its basis and amplification all belong to protection scope of the present invention.
The applied in any combination of feature of the present invention:
All features of the present invention all are to realize the scheme key element of technique effect, and one of feature of the present invention can structure Become a technical scheme of the present invention, feature two, three, by that analogy to whole any combination of features Also be technical scheme of the present invention, the combination that consolidates former any one or more features of invention all is institute of the present invention The technical scheme of protecting.
The present invention has overcome voice technology and keyboard technique defective separately, with the advantages of these two technology And on existing speech recognition technology, improved people's input speed.
Claims (8)
1. input media based on the voice keyboard of Chinese character phrase, it is characterized in that: comprise a preferential options button, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display, when being arranged as a plurality of phrase, select the phrase of prioritization by the preferential options button of keyboard, preferential options button is a space bar.
2. the input media of a kind of voice keyboard based on the Chinese character phrase according to claim 1, it is characterized in that: by phonetic entry the time after the oral account of finishing a phoneme of speech sound unit, show the phrase relevant in the display with oral account, select by keyboard, when the shown phrase of display for not only one the time, the frequency difference difference that puts in order, put in order with frequency as foundation, carrying out advantage by frequency order arranges, frequency is the highest be arranged in before frequency minimum be arranged in after, arrange the most preceding phrase and select by preferential options button.
3. the input media of a kind of voice keyboard based on the Chinese character phrase according to claim 1, it is characterized in that: space bar is served as preferential options button, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display, be used for selecting to be arranged in the phrase of first place, other options button that also comprises phrase, phrase after first is used for selecting to put in order.
4. the input media of a kind of voice keyboard based on the Chinese character phrase according to claim 1, it is characterized in that: numerical key is key alternatively, be used for selecting phrase shown in the display, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
5. the input media of a kind of voice keyboard based on the Chinese character phrase according to claim 1, it is characterized in that: the part key in the numerical key is key alternatively, be used for selecting phrase shown in the display, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
6. the input media of a kind of voice keyboard based on the Chinese character phrase according to claim 1, it is characterized in that: the whole keys in the numerical key are key alternatively, be used for selecting phrase shown in the display, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
7. the input media of a kind of voice keyboard based on the Chinese character phrase according to claim 1, it is characterized in that: letter key is key alternatively, be used for selecting phrase shown in the display, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
8. the input media of a kind of voice keyboard based on the Chinese character phrase according to claim 1, it is characterized in that: the part key in the letter key is key alternatively, can be used for selecting phrase shown in the display, be used for the phrase relevant with received phoneme of speech sound accessed from storer and showing at display.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2008101052510A CN101571752A (en) | 2008-04-28 | 2008-04-28 | Input device of voice keyboard based on Chinese ideograph phrases |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2008101052510A CN101571752A (en) | 2008-04-28 | 2008-04-28 | Input device of voice keyboard based on Chinese ideograph phrases |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101571752A true CN101571752A (en) | 2009-11-04 |
Family
ID=41231116
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2008101052510A Pending CN101571752A (en) | 2008-04-28 | 2008-04-28 | Input device of voice keyboard based on Chinese ideograph phrases |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101571752A (en) |
-
2008
- 2008-04-28 CN CNA2008101052510A patent/CN101571752A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4463526B2 (en) | Voiceprint authentication system | |
CN104937603B (en) | terminal, unlocking method and program | |
TWI281146B (en) | Apparatus and method for synthesized audible response to an utterance in speaker-independent voice recognition | |
JP2006023860A (en) | Information browser, information browsing program, information browsing program recording medium, and information browsing system | |
CN110473523A (en) | A kind of audio recognition method, device, storage medium and terminal | |
CN103578467A (en) | Acoustic model building method, voice recognition method and electronic device | |
CN103578464A (en) | Language model establishing method, speech recognition method and electronic device | |
CN103578465A (en) | Speech recognition method and electronic device | |
Jowitt | Patterns of Nigerian English intonation | |
JP2001521188A (en) | System and method for realizing a user interface for Japanese characters | |
CN104142796A (en) | Unlocking method of terminal and terminal | |
CN108604268B (en) | A kind of voice unlocking method and terminal of terminal | |
TWI222596B (en) | Character generation system | |
JP2010198241A (en) | Chinese input device and program | |
CN102970618A (en) | Video on demand method based on syllable identification | |
CN105718781A (en) | Method for operating terminal equipment based on voiceprint recognition and terminal equipment | |
CN101571752A (en) | Input device of voice keyboard based on Chinese ideograph phrases | |
CN101572085A (en) | Speech input control device | |
CN101753666A (en) | Mobile phone for blind user | |
CN100517186C (en) | Letter inputting method and apparatus based on press-key and speech recognition | |
JP2007240688A (en) | Speech recognition device and navigation device using the same, and speech authentication device, method and program | |
CN103824008A (en) | Computer operation control system on basis of face recognition | |
CN1936786A (en) | Fuzzy sound inputting method for Chinese phonetic alphabet | |
CN109359307B (en) | Translation method, device and equipment for automatically identifying languages | |
CN109658933B (en) | Voice recognition unlocking method, mobile terminal and memory |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20091104 |