CN101751401A - Computer device, voice searching system and method - Google Patents
Computer device, voice searching system and method Download PDFInfo
- Publication number
- CN101751401A CN101751401A CN200810183989A CN200810183989A CN101751401A CN 101751401 A CN101751401 A CN 101751401A CN 200810183989 A CN200810183989 A CN 200810183989A CN 200810183989 A CN200810183989 A CN 200810183989A CN 101751401 A CN101751401 A CN 101751401A
- Authority
- CN
- China
- Prior art keywords
- audio frequency
- voice
- search
- order
- 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
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a computer device, a voice searching system and method. The method comprises the following steps. Firstly, the audio frequency with specific frequency is recorded. When the audio frequency presents key features, the audio frequency in the time interval after the key features appear is taken as the audio frequency data. And then, the audio frequency data is converted into character string data. And then, a plurality of vocabularies of the character string data are taken, and the vocabularies are used to form at least one searching condition. At last, the searching condition is used for data searching. Therefore, the question in voice status can be converted to text files, in order to conduct data search of questions through searching network station.
Description
Technical field
The present invention relates to a kind of voice searching system, particularly relating to a kind of is to utilize computer installation, voice searching system and the method thereof that search the website of searching behind the literal with speech conversion.
Background technology
In the modern times, except promoting individual's the ability by continuous study the period of ging to school, the in-service employee can see through the ability that constantly education promotes the individual equally, and the corporate boss also can hold different lectures and study at the employee simultaneously, to promote employee's ability to work.And study or the classroom of lecture on, the lecturer can put question to the student usually, comes to carry out interaction with the student.Yet after puing question to, nobody can answer lecturer's problem among suppose the student, causes the situation that can present unmanned answer after enquirement.
In addition, if the student carries notebook on class, or the place disposes personal computer with aided education on class, makes the student can see through computer internet and inquires about the problem that the lecturer puts question to.But, when the student inputs to problem computing machine and finds answer, may pass through the point on opportunity of answering a question, and the sound that keyboard beats may have influence on the lecturer on class.
Summary of the invention
The invention provides a kind of computer installation, the problem for voice status can be converted to string data.
The invention provides a kind of voice searching system, a plurality of glossarys in the fechtable string data, and utilize these glossarys to form a few search condition.
The invention provides a kind of speech search method, can see through the search website and come described search condition is carried out data search.
The present invention proposes a kind of speech search method, and it comprises the following steps.At first, record audio frequency with characteristic frequency.When key feature appearred in audio frequency, the acquisition key feature the interior audio frequency of back time interval occurred as voice data.Then, convert voice data to string data.Then, a plurality of glossarys in the acquisition string data, and utilize these glossarys to form at least one search condition.At last, utilize described search condition to carry out data search.
In one embodiment of this invention, the step of recording the audio frequency with characteristic frequency comprises: lock the audio frequency with characteristic frequency, and this audio frequency is recorded.
In one embodiment of this invention, be a little glossarys of noun and verb comprising in the acquisition string data of these glossarys in the acquisition string data.
In one embodiment of this invention, the step of utilizing described search condition to carry out data search comprises: be linked to and search the website, and through searching the website described search condition is searched.
The present invention proposes a kind of voice searching system, and it comprises voice receiving unit, speech recognition unit, analytic unit and searches the unit.Voice receiving unit is in order to receive audio frequency.The speech recognition unit couples voice receiving unit, and first audio frequency that has characteristic frequency in the audio frequency in order to acquisition, and when key feature appears in first audio frequency, export first audio frequency and keep a time interval is with as a voice data.Analytic unit couples the speech recognition unit, in order to voice data is converted to string data, and a plurality of glossarys in the acquisition string data, and utilize a little glossarys to form at least one search condition.Search the unit, couple analytic unit, described search condition is searched in order to see through the search website.
In one embodiment of this invention, this voice searching system more comprises button and record cell.Button couples the speech recognition unit, in order to the time span of whether pushing the control time interval of foundation button.Record cell is coupled to the speech recognition unit, in order to record first audio frequency.
The present invention proposes a kind of computer installation, and it comprises voice receiving unit and disposal system.Voice receiving unit is in order to receive an audio frequency.Disposal system comprises speech recognition unit, analytic unit and searches the unit.The speech recognition unit couples voice receiving unit, and in order to first audio frequency that has characteristic frequency in the acquisition audio frequency, and this first audio frequency in a time interval is as a voice data.Analytic unit couples the speech recognition unit, in order to voice data is converted to string data, and a plurality of glossarys in the acquisition string data, and utilize these glossarys to form at least one search condition.Search the unit and couple analytic unit, described search condition is searched in order to see through the search website.
In one embodiment of this invention, this speech recognition unit when a key feature appears in first audio frequency, outputting audio data, and this key feature is first audio frequency in order to the amplitude that transmits a keyword or first audio frequency greater than a default value.
In one embodiment of this invention, this computer installation more comprises keyboard, and keyboard has a plurality of buttons, and couples disposal system, in order to the time span of pushing the control time interval according to these buttons.
In one embodiment of this invention, this processing system more comprises record cell, and record cell is coupled to the speech recognition unit, and in order to recording first audio frequency, and this record cell is a hard disk.
In one embodiment of this invention, this computer installation more comprises keyboard, and keyboard has a plurality of buttons, and couples disposal system.When one of them of button on the keyboard was pressed, the speech recognition unit can be from record cell acquisition recording audio data in the time interval before button is pressed.
In one embodiment of this invention, decide for the capacity of foundation record cell in this time interval.In one embodiment of this invention, and this voice receiving unit is a microphone, and this speech recognition unit, analytic unit and search unit are all an application program.
Comprehensive the above, computer installation of the present invention, voice searching system and method thereof, can will be converted to string data for the problem of voice status, and a plurality of glossarys of acquisition in string data, to utilize these glossarys to form a few search condition, see through the search website again and come described search condition is carried out data search.By this, can not come the input problem, and problem directly can be looked for relevant data through searching the website, to obtain the answer of problem via keyboard.
Above-mentioned explanation only is the general introduction of technical solution of the present invention, for can clearer understanding technological means of the present invention, and can be implemented according to the content of instructions, below with preferred embodiment of the present invention and conjunction with figs. describe in detail as after.
Description of drawings
Fig. 1 is the system block diagrams of computer installation according to an embodiment of the invention.
Fig. 2 is the system block diagrams of voice searching system according to an embodiment of the invention.
Fig. 3 is the process flow diagram of speech search method according to an embodiment of the invention.
Fig. 4 is the process flow diagram of speech search method according to another embodiment of the present invention.
Fig. 5 is the process flow diagram of speech search method according to yet another embodiment of the invention.
Embodiment
Fig. 1 is the system block diagrams of computer installation according to an embodiment of the invention.Please refer to Fig. 1, computer installation 100 comprises voice receiving unit 110, disposal system 120 and keyboard 130.Voice receiving unit 110 is in order to receive audio frequency, and wherein voice receiving unit 110 for example is a microphone.Disposal system 120 couples voice receiving unit 110.Keyboard 130 couples disposal system, and has a plurality of buttons.Disposal system 120 comprises speech recognition unit 121, analytic unit 122, searches unit 123 and record cell 124.Speech recognition unit 121 couples voice receiving unit 110, in order to first audio frequency that has characteristic frequency in the acquisition audio frequency.When key feature appearred in first audio frequency, a time interval (for example being 30 seconds) can also be kept by output first audio frequency in speech recognition unit 121, with as a voice data.Analytic unit 122 couples speech recognition unit 121, in order to voice data is converted to string data, and a plurality of glossarys in the acquisition string data, and utilize these glossarys to form at least one search condition.Search unit 123 and couple analytic unit 122, described search condition is searched in order to see through the search website.Record cell 124 is coupled to speech recognition unit 121, and in order to record first audio frequency, wherein record cell 124 for example is a hard disk.
For instance, when lecturer's class hour on the classroom, voice receiving unit 110 can receive the audio frequency that the lecturer goes up class hour, owing to have other student in the classroom, voice receiving unit 110 also can receive to the audio frequency of other student's speech.After voice receiving unit 110 receives these audio frequency, can be sent to speech recognition unit 121, those are sent by the lecturer in speech recognition unit 121 these audio frequency of meeting resolution, that is the characteristic frequency in the locking audio frequency.And the lock mode of this characteristic frequency can be pushed the button on the keyboard (for example being "enter" key") via the user, when pushing with 121 lockings of notice speech recognition unit, the frequency of voice receiving unit 110 received audio frequency is perhaps analyzed the frequency of audio frequency of the most normal appearance as this characteristic frequency via speech recognition unit 121.
After the characteristic frequency of locking lecturer audio frequency (following lecturer's audio frequency abbreviates first audio frequency as), this first audio frequency can be recorded unit 110 and record.And voice receiving unit 110 can constantly receive these audio frequency, and the continuous acquisition of speech recognition unit 121 meetings first audio frequency, and record cell 110 can constantly be recorded first audio frequency.Whether in the process of first audio recording, speech recognition unit 121 can be analyzed first audio frequency and key feature whether occur, differentiate the lecturer and begin to put question to.Because puing question to, the lecturer may first talk about preposition vocabulary such as " may I ask ", this key feature perhaps improves the tone, so can improve the preposition vocabulary (that is keyword) of (that is the amplitude of first audio frequency is greater than default value) or the enquirement of first audio delivery for the first audio frequency tone.With key feature be the amplitude of first audio frequency greater than default value, its default value can be set via the mxm. that speech recognition unit 121 measures the tone of lecturers at school the time.And be the first audio delivery keyword with key feature, this keyword can be the preposition vocabulary that " may I ask ", " who knows ", " saying something ", " who can tell me ", " asking you ", " asking " etc. are putd question to.
After the key feature appearance, first audio frequency can be made output in real time in speech recognition unit 121, and keeps a time interval, with the voice data of first audio frequency in this time interval as lecturer's enquirement.And the time span in this time interval can be via the operation of keyboard 130 being done set (for example being set at 20 seconds); Perhaps, the user has putd question to then the lecturer and has finished voice identification unit 121 output these first audio frequency (that is the end point in control time interval), the time span in same this time interval of may command by the button in the lower keyboard 130 (for example being the Esc key).Behind speech recognition unit 121 outputting audio datas, analytic unit 122 can be converted to voice data string data (also be about to voice document and be converted to text file).Owing to be the emphasis that searches with noun and verb mostly in the problem,, capture out with glossary with noun and verb so analytic unit 122 deletion earlier is not the literal (for example being Jie's copula or subject term) of noun and verb.Then different combinations done in these glossarys that acquisition is come out, and these combinations then can be as the search condition of this problem, and search condition is understood at least more than one.
After search condition comes out, search unit 123 and these search conditions can be input to the word dialog box (input box) of searching the website, search to see through the search website, wherein search the website and for example be knowledge or the Google Search of very rubbing.And different search conditions can utilize different webpages to show, and the mode that shows can utilize display or alternate manner to be shown to user's reference, and present embodiment is not as limit.After showing search result, the envoy use just can therefrom learn problem answer why, if the user can not find answer from these search results, can revise search condition, and do search again from word dialog box.Because the user need not use keyboard to come the input problem, so can obtaining the search of problem laborsaving and fast, the user finishes, to obtain the answer of problem indirectly or directly.
And in other embodiments, voice data can be come out by acquisition in the record cell 124.Equally with reference to Fig. 1, suppose after the lecturer puts question to end, the user can push the button (for example being the F12 key) on the Jian dish 130, and first audio frequency that speech recognition unit 121 can be recorded in the time interval (for example being 30 seconds) of record cell 124 acquisitions before button is pressed is as voice data.In other words, after the F12 key is pressed, can capture the speech data of pushing the first preceding 30 seconds audio frequency.Person more, this time interval can be decided according to the capacity of record cell 124, and for example record cell can write down 30 seconds voice datas, and this time interval just is set at 30 seconds.
In addition, speech recognition unit 121 also can button be pressed on keyboard 130 after, export first audio frequency in real time, and when the button on keyboard 130 is pressed once more, stop to export first audio frequency, and first audio frequency in the time interval of pushing for twice also is voice data, and wherein the button of pushing for this twice can be same button or different key, as long as whether can control speech recognition unit 121 outputs first audio frequency.And after voice data captured out, the program of its processing can then not given unnecessary details at this as the explanation of above-mentioned embodiment.
What deserves to be mentioned is, speech recognition unit 121, analytic unit 122 and search unit 123 can utilize software or hardware mode to realize, that is the function of speech recognition unit 121, analytic unit 122 and search unit 123 can be written as application program, perhaps utilize the mode that writes chip to realize.And speech recognition unit 121, analytic unit 122 and search unit 123 can be respectively hardware or software, as long as can finish the action of the foregoing description computer installation 100, all can be considered one embodiment of the invention.
In a further embodiment, the voice receiving unit 110 in the foregoing description, speech recognition unit 121, analytic unit 122 and search unit 123 and can be integrated into voice searching system below are carried an embodiment again and are explained.Fig. 2 is the system block diagrams of voice searching system according to an embodiment of the invention.Please refer to Fig. 2, voice searching system 200 comprises voice receiving unit 201, speech recognition unit 202, analytic unit 203, searches unit 204, record cell 205 and button 206.Speech recognition unit 202 couples voice receiving unit 201, analytic unit 203, record cell 205 and button 206.Search unit 204 and couple analytic unit 203.Wherein, the function of voice receiving unit 201, speech recognition unit 202, analytic unit 203, search unit 204 and record cell 205 can be implemented according to the explanation of the similar part among Fig. 1 embodiment, does not give unnecessary details at this.The part function of the then alternative keyboard 130 of button 206 for example when button 206 is pressed, can finish the output of voice identification unit 202, comes the time span in control time interval by this; Perhaps, after button 206 was pressed, first audio frequency in a time interval was used as voice data before speech recognition unit 202 can capture from record cell 205 and be pressed.
From another viewpoint, it is a speech search method that the foregoing description can converge whole.Fig. 3 is the process flow diagram of speech search method according to an embodiment of the invention.Please refer to Fig. 3, at first, in step S302, can record the audio frequency with characteristic frequency earlier, wherein this audio frequency for example is lecturer's a audio frequency.Then, shown in step S304, when key feature appearred in audio frequency, after can capturing key feature and occurring, the audio frequency in time interval was as voice data, and wherein this key feature for example be an audio frequency in order to the amplitude of transmission keyword or audio frequency greater than default value.Then, step S306 can convert voice data to string data.And step S308 can capture a plurality of glossarys in the string data, and step S310 can utilize these glossarys to form at least one search condition, and wherein these glossarys for example are the glossary of noun or verb.At last, step S312 can utilize described search condition to carry out data search.Wherein, this keyword and default value can be with reference to the explanations of the foregoing description, and succinct for instructions then do not given unnecessary details at this.By this, the user can see through the data of searching gained, learns the answer of problem indirectly or directly.
Below can carry an embodiment again, so that Fig. 3 embodiment is further described.Fig. 4 is the process flow diagram of speech search method according to another embodiment of the present invention.Please refer to Fig. 3 and Fig. 4, in the present embodiment, at first step S402 can lock the audio frequency with characteristic frequency, to avoid being recorded to unwanted audio frequency.Then, step S404 can record this audio frequency.Shown in step S406, when transmitting keyword, after picking the key word and occurring, the audio frequency in time interval is as voice data at audio frequency.Then, step S408 can convert voice data to string data equally.And step S410 can capture in the string data a plurality of glossarys for noun and verb, and step S412 can utilize these glossarys to form at least one search condition.Then, in step S414, can be linked to earlier and search the website, and step S416 can search described search condition through searching the website.At last, step S418 can show search result.Wherein, the mode of described search website and demonstration search result can then not given unnecessary details at this with reference to the explanation of the foregoing description.
Because the difference of key feature, Fig. 3 embodiment can extend an embodiment again.Fig. 5 is the process flow diagram of speech search method according to yet another embodiment of the invention.Please refer to Fig. 4 and Fig. 5, the difference of its maximum is step S502, at the amplitude of audio frequency during greater than default value, acquisition after this audio frequency in time interval as voice data.And other step in the present embodiment can be finished with reference to the explanation of similar part among Fig. 4 embodiment, does not then give unnecessary details at this.
In sum, the computer installation of the foregoing description, voice searching system and method thereof, the audio recording that can will have characteristic frequency is got off, and the audio frequency of output in a time interval is as voice data, then voice data can be converted to string data, so that acquisition is a plurality of glossarys of noun and verb in string data, utilizes these glossarys to form at least one search condition simultaneously, and come described search condition is carried out data search through searching the website.By this, the problem of voice status can be converted to text file, and not come the input problem, and can directly look for the relevant data of problem therewith, to obtain answer indirectly or directly through searching the website via keyboard.
The above, it only is preferred embodiment of the present invention, be not that the present invention is done any pro forma restriction, though the present invention discloses as above with preferred embodiment, yet be not in order to limit the present invention, any those skilled in the art, in not breaking away from the technical solution of the present invention scope, when the structure that can utilize above-mentioned announcement and technology contents are made a little change or be modified to the equivalent embodiment of equivalent variations, but every content that does not break away from technical solution of the present invention, according to technical spirit of the present invention to any simple modification that above embodiment did, equivalent variations and modification all still belong in the scope of technical solution of the present invention.
Claims (24)
1. speech search method is characterized in that comprising:
Record a audio frequency with a characteristic frequency;
When a key feature appears in this audio frequency, capture this key feature and this audio frequency in one time interval, back occurs as a voice data;
Convert this voice data to a string data;
Capture a plurality of glossarys in this string data;
Utilize those glossarys to form at least one search condition; And
Utilize described search condition to carry out data search.
2. speech search method according to claim 1 is characterized in that, wherein records this audio frequency with this characteristic frequency and comprises:
This audio frequency that locking has this characteristic frequency; And
This audio frequency is recorded.
3. speech search method according to claim 1 is characterized in that, wherein this key feature is that this audio frequency is in order to transmit a keyword.
4. speech search method according to claim 1 is characterized in that, wherein this key feature is that the amplitude of this audio frequency is greater than a default value.
5. speech search method according to claim 1 is characterized in that, those glossarys that wherein capture in this string data comprise:
Capture in this string data is those glossarys of noun and verb.
6. speech search method according to claim 1 is characterized in that, wherein utilizes described search condition to carry out data search and comprises:
Be linked to one and search the website; And
Seeing through this search website searches described search condition.
7. voice searching system is characterized in that comprising:
One voice receiving unit is in order to receive an audio frequency;
One speech recognition unit couples this voice receiving unit, in order to capturing one first audio frequency that has a characteristic frequency in this audio frequency, and when a key feature appears in this first audio frequency, exports this first audio frequency and keeps a time interval, with as a voice data;
One analytic unit couples this speech recognition unit, in order to this voice data is converted to a string data, and captures a plurality of glossarys in this string data, and utilizes those glossarys to form at least one search condition; And
One searches the unit, couples this analytic unit, in order to see through a search website described search condition is searched.
8. voice searching system according to claim 7 is characterized in that more comprising:
One button couples this speech recognition unit, in order to control the time span of this time interval according to whether pushing of this button.
9. voice searching system according to claim 7 is characterized in that more comprising:
One record cell is coupled to this speech recognition unit, in order to record this first audio frequency.
10. voice searching system according to claim 9 is characterized in that, wherein this record cell is a hard disk.
11. voice searching system according to claim 7 is characterized in that, wherein this voice receiving unit is a microphone.
12. voice searching system according to claim 7 is characterized in that, wherein this key feature is that this first audio frequency is in order to transmit a keyword.
13. voice searching system according to claim 7 is characterized in that, wherein this key feature is that the amplitude of this first audio frequency is greater than a default value.
14. a computer installation is characterized in that comprising:
One voice receiving unit is in order to receive an audio frequency;
One disposal system comprises:
One speech recognition unit couples this voice receiving unit, and in order to capturing one first audio frequency that has a characteristic frequency in this audio frequency, and this first audio frequency in a time interval is as a voice data;
One analytic unit couples this speech recognition unit, in order to this voice data is converted to a string data, and captures a plurality of glossarys in this string data, and utilizes those glossarys to form at least one search condition; And
One searches the unit, couples this analytic unit, in order to see through a search website described search condition is searched.
15. computer installation according to claim 14 is characterized in that, wherein this voice data is exported in this speech recognition unit when a key feature appears in this first audio frequency.
16. computer installation according to claim 15 is characterized in that, wherein this key feature is that this first audio frequency is in order to transmit a keyword.
17. computer installation according to claim 15 is characterized in that, wherein this key feature is that the amplitude of this first audio frequency is greater than a default value.
18. computer installation according to claim 15 is characterized in that more comprising:
One keyboard has a plurality of buttons, couples this disposal system, in order to control the time span of this time interval according to pushing of those buttons.
19. computer installation according to claim 14 is characterized in that, wherein this disposal system more comprises:
One record cell is coupled to this speech recognition unit, in order to record this first audio frequency.
20. computer installation according to claim 19 is characterized in that, wherein this record cell is a hard disk.
21. computer installation according to claim 19 is characterized in that more comprising:
One keyboard has a plurality of buttons, couples this disposal system, when one of them of those buttons is pressed, and this voice data that this speech recognition unit can be recorded in this time interval before this button is pressed from this record cell acquisition.
22. computer installation according to claim 21 is characterized in that, wherein the time span of this time interval is decided for the capacity according to this record cell.
23. computer installation according to claim 14 is characterized in that, wherein this voice receiving unit is a microphone.
24. computer installation according to claim 14 is characterized in that, wherein this speech recognition unit, analytic unit and search unit are all an application program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810183989A CN101751401A (en) | 2008-12-19 | 2008-12-19 | Computer device, voice searching system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810183989A CN101751401A (en) | 2008-12-19 | 2008-12-19 | Computer device, voice searching system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101751401A true CN101751401A (en) | 2010-06-23 |
Family
ID=42478392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810183989A Pending CN101751401A (en) | 2008-12-19 | 2008-12-19 | Computer device, voice searching system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101751401A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016058425A1 (en) * | 2014-10-17 | 2016-04-21 | 百度在线网络技术（北京）有限公司 | Voice search method, apparatus and device, and computer storage medium |
| CN105528440A (en) * | 2015-12-17 | 2016-04-27 | 合肥联宝信息技术有限公司 | Information prompting method and system and electronic equipment |
| CN111123714A (en) * | 2018-10-31 | 2020-05-08 | 仁宝电脑工业股份有限公司 | Intelligent wine cabinet and wine money searching method |
-
2008
- 2008-12-19 CN CN200810183989A patent/CN101751401A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016058425A1 (en) * | 2014-10-17 | 2016-04-21 | 百度在线网络技术（北京）有限公司 | Voice search method, apparatus and device, and computer storage medium |
| CN105528440A (en) * | 2015-12-17 | 2016-04-27 | 合肥联宝信息技术有限公司 | Information prompting method and system and electronic equipment |
| CN111123714A (en) * | 2018-10-31 | 2020-05-08 | 仁宝电脑工业股份有限公司 | Intelligent wine cabinet and wine money searching method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11157490B2 (en) | Conversational virtual assistant | |
| US20150254061A1 (en) | Method for user training of information dialogue system | |
| US7865501B2 (en) | Method and apparatus for locating and retrieving data content stored in a compressed digital format | |
| KR20180025121A (en) | Method and apparatus for inputting information | |
| US20030187632A1 (en) | Multimedia conferencing system | |
| US10685655B2 (en) | Leveraging natural language processing | |
| CN101998107A (en) | Information processing apparatus, conference system and information processing method | |
| CN105912527A (en) | Method, device and system outputting answer according to natural language | |
| CN104573099A (en) | Topic searching method and device | |
| CN111919249A (en) | Continuous detection of words and related user experience | |
| KR20010100883A (en) | a technique for providing continuous speech recognition as an alternative input device to limited processing power devices | |
| US10089898B2 (en) | Information processing device, control method therefor, and computer program | |
| US20240153492A1 (en) | Method and apparatus for generating hint words for automated speech recognition | |
| KR101618084B1 (en) | Method and apparatus for managing minutes | |
| CN108710653B (en) | On-demand method, device and system for reading book | |
| CN111563182A (en) | Voice conference record storage processing method and device | |
| CN101751401A (en) | Computer device, voice searching system and method | |
| US20170154264A1 (en) | Autonomous collaboration agent for meetings | |
| CN112163084B (en) | Problem feedback method, device, medium and electronic equipment | |
| US11205430B2 (en) | Method and apparatus for generating hint words for automated speech recognition | |
| CN113111658A (en) | Method, device, equipment and storage medium for checking information | |
| KR102222637B1 (en) | Apparatus for analysis of emotion between users, interactive agent system using the same, terminal apparatus for analysis of emotion between users and method of the same | |
| CN109637541A (en) | The method and electronic equipment of voice conversion text | |
| US20160110159A1 (en) | Input information support apparatus, method for supporting input information, and computer-readable recording medium | |
| CN110890095A (en) | Voice detection method, recommendation method, device, storage medium and electronic equipment |
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 |
Open date: 20100623 |