CN102262524A - Method for recognizing and inputting sound based on wireless input equipment and device for implementing method - Google Patents
Method for recognizing and inputting sound based on wireless input equipment and device for implementing method Download PDFInfo
- Publication number
- CN102262524A CN102262524A CN2010101865710A CN201010186571A CN102262524A CN 102262524 A CN102262524 A CN 102262524A CN 2010101865710 A CN2010101865710 A CN 2010101865710A CN 201010186571 A CN201010186571 A CN 201010186571A CN 102262524 A CN102262524 A CN 102262524A
- Authority
- CN
- China
- Prior art keywords
- input
- voice
- wireless
- information
- main frame
- 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
Abstract
The invention discloses a method for recognizing and inputting a sound based on wireless input equipment. The method comprises the following steps that: 1) a user inputs voices literally, and a voice acquisition module acquires input information and wirelessly transmits the input information to a host; 2) after receiving the information, the host recognizes the information by using voice recognition software, displays a plurality of items of recognition results on a host screen, and puts corresponding words in the first item if the voice of which the pronunciation is similar to that of the previous voice is input; 3) the users checks whether the expected words appear in the displayed results, selects the corresponding words through keys if the expected words appear in the displayed results, and returns to the voice acquisition module if the expected words do not appear in the displayed results; 4) after word input is selected, the sound is associated with the corresponding word input, and a recognition software library is updated; and 5) if the expected words appear in the displayed results, recognition is restarted, and if the expected words do not appear in the displayed results, the recognition is ended. By the method for recognizing and inputting the sound, the wireless input equipment can support transmission of voice data under the condition of supporting of the conventional wireless control function.
Description
Technical field
The present invention relates to a kind of voice recognition input method of a kind of design, particularly a kind ofly import based on wireless identification.
Background technology
Along with the development of new digital TV, set-top box, PC, new requirement has been proposed input equipment.The appearance of electromagnetic wave wireless communication technique has overcome the traditional infrared input equipment defective at aspects such as directive property, anti-interference, data transmission rates, has become control more common in the consumer electronics product, data transmission technology.By add the wireless communication module of voice module and support voice transmission at input equipment, make original traditional input equipment have the voice-frequency telephony function.
At present, along with the portable equipment of supporting wireless telecommunications is increasing, the basic condition of the realization that provides for the diversity of input equipment.Such as, support Bluetooth function mobile phone, support the handheld device etc. of the wireless telecommunications of general 2.4G, by setting up wireless connections, above equipment can be become the input equipment of main frame such as computer with computer, new digital TV and set-top box.
The input mode of keyboard is generally adopted in the input of Word message, considers input equipment user group's diversity, and the needs of some special group (such as the elderly) propose an input method easy and simple to handle.
Summary of the invention
The technical problem to be solved in the present invention provides a kind of voice recognition input method based on wireless input device, and it can carry out effective phonetic entry.
For solving the problems of the technologies described above, voice recognition input method based on wireless input device of the present invention, embedded voice acquisition module in this wireless input device, with the embedded speech recognition software of main frame that this wireless input device carries out wireless telecommunications, this voice recognition input method comprises the steps:
1) user adopts word for word or carries out phonetic entry by the method for speech input, the information that the voice acquisition module collection in the described wireless input device is imported, and be transferred to described main frame by wireless communication mode;
2) after main frame receives information, use described speech recognition software to discern, the multinomial result who discerns is presented on the main frame screen, have and the similar phonetic entry of pronouncing before, corresponding literal is placed on first of optional literal term as finding;
3) user checks the literal that whether has expectation to occur among the shown result, if any then selecting corresponding character by the button on the described wireless input device, does not then return voice acquisition module as having;
4) select literal after, this sound and corresponding character input are done related, adopt the speech recognition self-learning function, upgrade the identification software storehouse;
5) then restart identification if any continuing input, finish as not importing promptly.
The present invention also provides a kind of device of realizing voice recognition input, comprise wireless input device and with the main frame of wireless input device wireless telecommunications, wherein wireless input device includes voice acquisition module, is used to gather voice messaging; Main frame is equipped with speech recognition software, is used for the voice messaging that voice acquisition module collects is identified as the literal input.
Voice recognition input method of the present invention makes wireless input device under the condition of supporting the conventional wireless control function, transmission that can the support voice data.The word for word employing of input mode, after literal identification, provide a plurality of recognition results to select in the recognition methods of the present invention simultaneously for the user, and selection mode can be realized by the button on the input equipment, can improve the accuracy of identification input, and the convenience on using.
Description of drawings
The present invention is further detailed explanation below in conjunction with accompanying drawing and embodiment:
Fig. 1 is the phonetic entry synoptic diagram of wireless input device of the present invention;
Fig. 2 is a voice recognition input method schematic flow sheet of the present invention.
Embodiment
Voice recognition input method based on wireless input device of the present invention, embedded voice acquisition module in this wireless input device, the main frame that carries out wireless telecommunications with wireless input device is equipped with speech recognition software, comprises the steps:
1) user adopts word for word or carries out phonetic entry by the method for speech input, and the voice acquisition module in the wireless input device is gathered this phonetic entry, and is transferred to the main frame (see figure 1) by wireless communication mode;
2) after main frame received information, the utilization speech recognition software was discerned, and the multinomial result who discerns is presented on the main frame screen, had and the similar phonetic entry of pronouncing before as finding, corresponding literal was placed on first of optional literal term;
3) user checks the literal that whether has expectation to occur among the shown result, if any then selecting corresponding character to get final product by the button on the wireless input device (can be numerical key, directionkeys and/or air mouse), does not then return voice acquisition module as having;
4) select literal after, this sound and corresponding character input are done related, adopt the speech recognition self-learning function, upgrade the identification software storehouse;
5) then restart identification if any continuing input, finish as not importing promptly.
Method of the present invention before carrying out speech recognition, can comprise that also the button that adopts on the wireless input device carries out the step of input characters type selecting.
A concrete implementation process is analyzed as follows, and the concrete enforcement of this programme mainly is divided into the following aspects:
1. the collection of sound and transmission
By on wireless input device, adding microphone, filtering and amplifying circuit, analog-to-digital conversion module, can realize the processing and the digitizing of voice signal.Wherein microphone is used for receiving speech information (being sound); The information that filtering and amplifying circuit are used for microphone is received is carried out denoising and processing and amplifying; D/A converter module then is used for the information digitalization after handling from filtering and amplifying circuit.Consider the cost problem of realization, analog-to-digital conversion module can adopt special chip to realize, directly adopts the analog-to-digital conversion module that carries on the microprocessor to realize.Information after the digitizing is transferred in the main frame by wireless communication mode.In order to improve the efficient of voice data wireless transmission, can to guarantee under the situation of limited message transmission rate, can transmit more effectively voice data through a cataloged procedure through analog-to-digital voice data.The mode of coding is a lot, such as using at present more widely pcm encoder etc.And main frame is handled through after the corresponding decoding data message being delivered to speech recognition software after receiving voice data.
2. speech recognition and selection that need to determine input characters
The key of speech recognition software is that the feature of voice data is analyzed, and the feature description in the comparison identification software storehouse obtains the otherness between the alternative sounds data, again according to certain similarity degree analyzing speech data word information relates.
In order to improve the accuracy rate of language and characters identification, adopted the input method (being the word for word method of input) of single independent word or phrase in the method for the present invention.Such as, in order to discern in short " I plan to go tomorrow tourism ", the user splits into following several sections with the words and imports " I " " plan " " tomorrow " " going " " tourism ", after finishing " I ", stop pronunciation, speech recognition software can be enumerated the literal similar to " I " pronunciation on display interface and (see Table 1), selects for the user:
Table 1
I | 2. fertile | 3. hold | 4. crouch | 5. | 6. revolve | 7. tent |
▲ | ▼ |
On the display interface, the user can select the corresponding character input according to the button on the wireless input device (can be digital keys, air mouse, directionkeys or definite key).Such as, in the above example, can set by importing as actual by numerical key " 1 " selection " I ".If the literal imported do not occur wanting, can also check down the literal of one page by choice direction key " ▲ " and " ▼ " in current display interface.
For the input mode of word, identical with top example.Import when inaccurate if find word, can also by will in short split into fully each word separately input discern, such as " I " " meter " " draw " " bright " " my god " " going " " trip " " trip ".
3. the selection of input language type
In order further to improve the accuracy of speech recognition, simplify the recognizer of speech recognition software, the literal that needs are imported can be classified in the method for present embodiment, before identification starts, the literal type that the user needs selection earlier will import at present.
Host application software can provide a place for the selection of input language type, and the mode that the user can add acknowledgement key by the air mouse function on the wireless input device, directionkeys at any time, numerical key are selected the input mode of needs.
Table 2
1. Chinese character input | 2. letter input | 3. numeral input | 4. other type input |
Select such as input mode as shown in table 2, the user can select " 1. Chinese character input " by air mouse when needs input Chinese character, also can directly realize the selection of input language by the mode by numerical key 1.
4. the self study process of language and characters input
A difficult point of speech recognition is because everyone pronunciation is inconsistent, causes the erroneous judgement of speech recognition software easily.In order to address this problem, introduced the method for a self study in the method for the present invention.The key of self study is by former pronunciation and corresponding character being selected, being carried out the self of speech recognition mechanism, to reach the effect that realizes best identified according to user's custom.
Such as, the user wants input characters " wind ", because the accent problem, the actual pronunciation of user is " fen ", when importing for the first time, the user could select from more identification literal possibly to literal " wind ", in case selected, speech recognition software can be done a related update speech recognition library with " wind " and pronunciation " fen ", when the user sends out " fen " sound next time again, identification software can be placed on literal " wind " the forward position of textual list, so that the user can find easily.
Fig. 2 is a concrete voice recognition input method schematic flow sheet:
A) the literal classification that need import by the numerical key on the wireless input device, directionkeys or air mouse selection, such as: Chinese character, English alphabet, numeral or the like.
B) according to selected literal classification, speech recognition mode is set.
C) wireless input device is gathered phonetic entry by inner voice acquisition module, and is transferred to host side by the mode of wireless telecommunications.
D) main frame obtains a plurality of possible literal input results by speech recognition software and selects for the user after receiving speech data, if pronounce similar phonetic entry before finding to have, corresponding literal is placed on first of optional literal term.
E) if comprised the literal of user's needs among all optional results, execution in step f if do not have, gets back to step c.
F) from recognition result, select the result that needs by the numerical key on the wireless input device, directionkeys or air mouse, finish the input of this word or speech.
G) write down the input of this sound and corresponding character, set up the speech recognition self-learning function, upgrade the identification software storehouse.
H) judge whether to need to continue input characters, if desired, execution in step i if do not need, finishes input.
I) judge whether next literal needs to change the literal classification, if desired, gets back to step a, if do not need, gets back to step c.
Be used to realize that the device of voice recognition input method of the present invention comprises wireless input device, the main frame with this wireless input device carries out wireless telecommunications includes voice acquisition module in wireless input device, is used to gather the voice messaging of user's input; And speech recognition software is installed in main frame, be used for voice messaging is identified as the input of literal.In device of the present invention, wireless input device mainly contains following 3 effects:
1) gathers user's voice information, and voice messaging is uploaded to main frame;
2) integrated air mouse function on this wireless input device can cooperate relevant selection and the control of speech recognition among the present invention;
3) standard key and multimedia buttons such as integrated direction acknowledgement key, numerical key on the wireless input device, input that also can assistant voice identification.
Claims (6)
1. the voice recognition input method based on wireless input device is characterized in that, comprises the steps:
1) user adopts word for word or carries out phonetic entry by the method for speech input, and the voice acquisition module in the described wireless input device is gathered voice messaging, and is transferred to described main frame by wireless communication mode;
2) after main frame receives information, use described speech recognition software to discern, the multinomial result who discerns is presented on the main frame screen, have and the similar phonetic entry of pronouncing before, corresponding literal is placed on first of optional literal term as finding;
3) user checks the literal that whether has expectation to occur among the shown result, if any then selecting corresponding character by the button on the described wireless input device, does not then return voice acquisition module as having;
4) select literal after, this sound and corresponding character input are done related, adopt the speech recognition self-learning function, upgrade the identification software storehouse;
5) then restart identification if any continuing input, finish as not importing promptly.
2. according to the described voice recognition input method of claim 1, it is characterized in that: described before carrying out speech recognition, comprise that also the button that adopts on the wireless input device carries out the selection step of input characters type.
3. according to the described voice recognition input method of claim 1, it is characterized in that: the button in the described step 3 is numerical key, directionkeys and/or air mouse.
4. according to the described voice recognition input method of each claim in the claim 1 to 3, it is characterized in that: the voice acquisition module in the described step 1 comprises microphone, filtering and amplifying circuit, analog-to-digital conversion module; Wherein microphone is used for receiving speech information; The information that filtering and amplifying circuit are used for described microphone is received is carried out denoising and processing and amplifying; Described D/A converter module is used for the information digitalization after handling from described filtering and amplifying circuit.
5. according to the described voice recognition input method of claim 4, it is characterized in that: the information of step 1 also comprised the step with described information coding before being transferred to main frame; And after the step 2 main frame receives information, earlier described information is decoded, then use described speech recognition software to discern.
6. a device of realizing the described method of claim 1 comprises wireless input device and the main frame that carries out wireless telecommunications with described wireless input device, it is characterized in that:
Described wireless input device includes voice acquisition module, and described voice acquisition module is used to gather voice messaging;
Described main frame is equipped with speech recognition software, and described speech recognition software is used for the voice messaging that voice acquisition module collects is identified as the literal input.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010101865710A CN102262524A (en) | 2010-05-27 | 2010-05-27 | Method for recognizing and inputting sound based on wireless input equipment and device for implementing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010101865710A CN102262524A (en) | 2010-05-27 | 2010-05-27 | Method for recognizing and inputting sound based on wireless input equipment and device for implementing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102262524A true CN102262524A (en) | 2011-11-30 |
Family
ID=45009162
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2010101865710A Pending CN102262524A (en) | 2010-05-27 | 2010-05-27 | Method for recognizing and inputting sound based on wireless input equipment and device for implementing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102262524A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103794214A (en) * | 2014-03-07 | 2014-05-14 | 联想(北京)有限公司 | Information processing method, device and electronic equipment |
CN105426155A (en) * | 2014-09-23 | 2016-03-23 | 联想(北京)有限公司 | Operation input method and electronic device |
WO2018133656A1 (en) * | 2017-01-19 | 2018-07-26 | 黄玉玲 | Method of converting voice input into text input, device, and voice input apparatus |
CN108491179A (en) * | 2018-03-13 | 2018-09-04 | 黄玉玲 | A kind of method and system of word input |
CN109616113A (en) * | 2018-12-29 | 2019-04-12 | 中商物联行(广州)商务有限公司 | Sound control method, phonetic controller and speech control system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN86105459A (en) * | 1985-08-01 | 1987-06-17 | 株式会社东芝 | Imput process system |
CN1373406A (en) * | 2001-08-15 | 2002-10-09 | 安平 | Chinese-character 'speech recognition' input method for mobile telephone |
CN2518278Y (en) * | 2001-12-31 | 2002-10-23 | 海尔集团公司 | Acoustic controlled telephone remote controller |
CN1737902A (en) * | 2005-09-12 | 2006-02-22 | 周运南 | Text-to-speech interchanging device |
CN1991743A (en) * | 2005-12-30 | 2007-07-04 | 西门子(中国)有限公司 | Method and device for voice input method |
CN201113996Y (en) * | 2007-08-22 | 2008-09-10 | 刘德强 | Radio microphone system |
-
2010
- 2010-05-27 CN CN2010101865710A patent/CN102262524A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN86105459A (en) * | 1985-08-01 | 1987-06-17 | 株式会社东芝 | Imput process system |
CN1373406A (en) * | 2001-08-15 | 2002-10-09 | 安平 | Chinese-character 'speech recognition' input method for mobile telephone |
CN2518278Y (en) * | 2001-12-31 | 2002-10-23 | 海尔集团公司 | Acoustic controlled telephone remote controller |
CN1737902A (en) * | 2005-09-12 | 2006-02-22 | 周运南 | Text-to-speech interchanging device |
CN1991743A (en) * | 2005-12-30 | 2007-07-04 | 西门子(中国)有限公司 | Method and device for voice input method |
CN201113996Y (en) * | 2007-08-22 | 2008-09-10 | 刘德强 | Radio microphone system |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103794214A (en) * | 2014-03-07 | 2014-05-14 | 联想(北京)有限公司 | Information processing method, device and electronic equipment |
CN105426155A (en) * | 2014-09-23 | 2016-03-23 | 联想(北京)有限公司 | Operation input method and electronic device |
WO2018133656A1 (en) * | 2017-01-19 | 2018-07-26 | 黄玉玲 | Method of converting voice input into text input, device, and voice input apparatus |
US11087758B2 (en) | 2017-01-19 | 2021-08-10 | Shenzhen Dongting Automobile Brokerage Co., Ltd. | Method and voice input apparatus for converting voice input to text input |
CN108491179A (en) * | 2018-03-13 | 2018-09-04 | 黄玉玲 | A kind of method and system of word input |
CN109616113A (en) * | 2018-12-29 | 2019-04-12 | 中商物联行(广州)商务有限公司 | Sound control method, phonetic controller and speech control system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101605171B (en) | Mobile terminal and text correcting method in the same | |
CN1918578B (en) | Handwriting and voice input with automatic correction | |
US9123341B2 (en) | System and method for multi-modal input synchronization and disambiguation | |
US11494161B2 (en) | Coding system and coding method using voice recognition | |
CN102543071B (en) | Voice recognition system and method used for mobile equipment | |
CN108305626A (en) | The sound control method and device of application program | |
WO2018125288A1 (en) | Modality learning on mobile devices | |
WO2018014341A1 (en) | Method and terminal device for presenting candidate item | |
CN101576901B (en) | Method for generating search request and mobile communication equipment | |
US10191716B2 (en) | Method and apparatus for recognizing voice in portable device | |
KR101545881B1 (en) | Input Processing Device For Portable Device And Method including the same | |
CN111261144A (en) | Voice recognition method, device, terminal and storage medium | |
EP2765473A1 (en) | Input processing method and apparatus | |
WO2014190732A1 (en) | Method and apparatus for building a language model | |
CN103281581A (en) | Human-computer interaction system and method controlling IP set-top box through smart phone voice | |
CN101082836A (en) | Chinese characters input system integrating voice input and hand-written input function | |
CN107608532A (en) | A kind of association-feeding method, device and electronic equipment | |
CN104202455A (en) | Intelligent voice dialing method and intelligent voice dialing device | |
CN102262524A (en) | Method for recognizing and inputting sound based on wireless input equipment and device for implementing method | |
CN101876887A (en) | Voice input method and device | |
CN101170757A (en) | A method and device for controlling text input in mobile device | |
CN104462058A (en) | Character string identification method and device | |
CN105912725A (en) | System for calling vast intelligence applications through natural language interaction | |
CN109920309A (en) | Sign language conversion method, device, storage medium and terminal | |
CN105323392A (en) | Method and apparatus for quickly entering IVR menu |
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 |
Application publication date: 20111130 |