CN104796584A - Prompt device with voice recognition function - Google Patents
Prompt device with voice recognition function Download PDFInfo
- Publication number
- CN104796584A CN104796584A CN201510196636.2A CN201510196636A CN104796584A CN 104796584 A CN104796584 A CN 104796584A CN 201510196636 A CN201510196636 A CN 201510196636A CN 104796584 A CN104796584 A CN 104796584A
- Authority
- CN
- China
- Prior art keywords
- speech
- voice
- voice signal
- circuit
- display
- 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
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
A prompt device with a voice recognition function comprises a main controller, a display, a radio microphone, a radio voice receiving and recognizing module, a user-setting button circuit, a preset text accessing circuit and a USB (universal serial bus) interface circuit. The radio microphone receives voice signals from a speaker or announcer, the received voice signals are transmitted to the corresponding voice signal receiving and recognizing module wirelessly. The voice signal receiving and recognizing module converts the voice signals into texts to be transmitted to the main controller by processing of voice recognition technology of independent persons, continuous voice and many words; the main controller compares the texts with sentences in the preset texts to find out this sentence, and finally the display displays this sentence with double underlines, color and bolding and the following content is displayed by amplified, colored and bolded texts. The announcer can focus on broadcasting by the aid of the prompt device, and broadcasting quality can be improved.
Description
technical field:
The invention belongs to signal transacting field, particularly a kind of prompter device with speech identifying function.
background technology:
The eighties in 20th century, along with the successful Application of technology in speech recognition such as HMM model and artificial neural networks (ANN), people breach unspecified person, a large amount of vocabulary and this three large speech recognition obstacle of continuous speech finally in laboratory.On September 12nd, 2013, University of Science and Technology news fly to be proposed supports the off-line phonetic entry software of mandarin---news fly input method.Off-line voice directly can be embedded in news and fly in input method, and user, by the off-line voice packet of a download 15.39M, can use phonetic entry under the state of not networking.It is the input method that first item supports off-line voice that news fly input method.The discrimination that the discrimination of off-line voice flies input method 95% than the news based on cloud is lower slightly, probably more than 90%.
Investigation according to international conference finds, because the content of report is too much, what most of speaker can take contribution reads out speech.Find through statistics, wherein bow and see that the time of contribution accounts for 70% of total speech time.This can because lacking and the Eye contact of audience and make speech poor effect.For speaker, when sight line gets back to speech draft again from audience, appear in the problem being difficult in thickly dotted speech draft find rapidly hereafter.If can not find rapidly, speech effect will certainly be made to have a greatly reduced quality.
It is reported, there is the display screen of word extractor in TV station announcer front, shows the content of draft above.For television announcer, due to apart from distant, so the number of words that display screen holds is limited, this just needs captions rolling or frequently toggle screen content frequently.It is reported, although Chinese Central Television (CCTV) newsreader word speed does not accurately specify how many words per minute, the speed that roughly broadcasts is about 300 words per minute.It can thus be appreciated that, for different announcer'ss (such as, the word speed of Zhang Hongmin is 350 words/min, Li Rui English 265 words/min), owing to there is the difference of word speed, captions rolling speed or screen content switching frequency will need artificial setting.In use not only loaded down with trivial details, more can affect quality of broadcasting.And adopt other manual methods (tramp with one's feet pedal) to remove to switch captions, announcer's distraction can be made, be unfavorable for broadcast equally.
The patent name of patent CN101505397A is " method and system that a kind of voice and video captioning synchronization presents ", and what adopt in the method is the speech recognition that the mode of pattern matching removes to realize particular person.Particular person is only applicable to the process of this voice signal, and recognition effect is easily subject to the impact of the factor such as mood, health, the poor robustness of system.This speech recognition system must carry out a large amount of voice collecting work before using to someone, then makes speech model.So just significantly limit the scope of application of this system, and be the speech recognition system of a large amount of vocabulary, continuous speech according to Wen Yi, so need the plenty of time from voice collecting to making model library.
Summary of the invention
Goal of the invention: the present invention proposes a kind of prompter device, first it is the speech recognition based on unspecified person, a large amount of vocabulary, continuous speech, this makes the use of this device have popularity, overcomes the shortcoming of particular person speech recognition system needs for each user modeling.Secondly it can make speaker have the more time to go, in the face of audience, also can see the ensuing disclosure that will read rapidly, exactly when sight line returns speech draft.Last in tv announcing field, it also can be eliminated, and needs manually to arrange captions rolling speed or screens switch frequency to the inconvenience brought that broadcasts because of the announcer of different word speed.Due to the content on display always can with speech or the content automatic synchronization that broadcasts, so without the need to presetting captions rolling speed, screens switch frequency or taking other modes to carry out captions switching.
technical scheme is as follows:
There is the prompter device of speech identifying function
,comprise master controller 5, display 6, wireless microphone 1, wireless speech receive identification module 2, user and arrange button circuit 7, preset text access circuit 4 and usb circuit 3.
Master controller 5 accepts identification module 2, preset text access circuit 4, display 6 respectively as CPU with wireless speech, user arranges button circuit 7 and usb circuit 3 is connected with hardware.It is that transmission medium is connected with free space that wireless microphone and wireless speech accept module, and wireless microphone 1 accepts voice signal and modulates this signal, and the radio wave with characteristic frequency after having modulated is sent in space.Wireless speech accepts the radio wave that module accepts this characteristic frequency from space, then through demodulation, extracts voice signal.Wireless speech accepts module and is connected with hardware with sound identification module, under the effect of master controller 5, the voice signal demodulated is mated with sound template storehouse, finally the result of coupling is converted into word and mates with the content of text in preset text access circuit 4.After reaching the matching condition of setting, under the control of master controller 5, display 6 by this sentence arranged in the preset text of requirement display, and shows this following sections content by the requirement arranged.When there being External memory equipment to be connected with usb circuit 3 by USB interface, text can be selected in file directory to copy in preset text access circuit 3, as the coupling foundation of voice identification result.User arranges button circuit 7 and is connected with some I/O mouth of master controller 5, by the level changing corresponding I/O mouth, program running parameter (font, size, color etc.) is changed, thus changes display effect.
Be described in detail with regard to each module below:
Wireless microphone is used for received speech signal, and voice signal can be sent in space environment in the mode of radio wave after treatment.
Wireless speech receives, identification module 2, and comprise two aspects, one is speech reception module, and another is sound identification module.The effect of speech reception module is the composite signal receiving wireless microphone generation, extracts voice signal by demodulator circuit from carrier wave.The effect of sound identification module is the identification voice signal demodulated being carried out voice, voice signal is converted into word and passes to master controller 5 and process.
Usb circuit 3, for importing preset text to preset text access circuit under the control of master controller.So-called preset text is exactly our speech draft or the electronic document of news release, and it needs to import in advance in prompter apparatus system, for display provides template, simultaneously also for the result of speech recognition provides the foundation of contrast.This circuit can also be used for the renewal of voice packet, specific practice is under the control of master controller, remove the new speech bag in movable storage device to override the voice packet of the reception of original wireless speech, identification module, reaches and upgrades voice packet to improve the object of discrimination.
Preset text access circuit, for saving presets text message.
Master controller, for the treatment of the information of modules.Specifically comprise wireless speech is received, the Word message that identifies of identification module compared with preset text, find the word meeting similarity.And the parameter that control display is arranged according to user shows.
Display, for showing the partial content of speech draft or news release, allow speechmaker and announcer eye-catching enlarge font outstanding under intuitively, clearly see that they will read hereafter.
User arranges button circuit, for the input of user.Consider that different users has different hobbies or custom, different user oneself can set some parameters.These parameters have font, word size, text color, background, display sentence number etc. hereafter.
beneficial effect
Under the help of this prompter device, speaker can have the more time to go in the face of audience.Also can see the ensuing disclosure that will read rapidly, accurately when sight line returns speech draft, these are all conducive to strengthening speech effect.For television announcer, under the help of this prompter device, can eliminate and need manually to arrange captions rolling speed or screens switch frequency because of the announcer of different word speed to the inconvenience brought that broadcasts, also can avoid adopting other manual methods to go to switch captions simultaneously.This can make announcer concentrate one's energy to broadcast, and is conducive to the raising of quality of broadcasting.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of this prompter apparatus system.1 is wireless microphone; 2 is that wireless speech accepts, identification module; 3 is usb circuits; 4 is preset text access circuits; 5 is master controllers; 6 is displays; 7 is the female mouths of USB.
Fig. 2 is the structural representation of this prompter device, display; Button 21 is mains switches; Button 22 is beginning/Pause key; Button 23 arranges key; Button 24 is up keys; Button 25 is down key; Button 26 is acknowledgement keys; Socket 27 is the female mouths of USB; 28 is display screen main windows, for showing content of text.
Embodiment
Below in conjunction with example and accompanying drawing, the technical scheme to this invention is specifically described.
Fig. 1 is the schematic diagram of this prompter apparatus system.As shown in Figure 1, this system comprises master controller, display, wireless microphone, wireless speech receive identification module, user and arrange button circuit, preset text access circuit and usb circuit.Below the relation between the function of each several part and each several part is elaborated.
Wireless microphone 1, is also wireless microphone, can be used for received speech signal, and voice signal can be sent in space environment after treatment wirelessly.Detailed process is, the wheat head of wireless microphone uses capacitive post collective, will the capacitance of wheat head be changed when receiving acoustic pressure.Wheat head is connected in oscillator loop, and due to the change of wheat head capacitance, corresponding change will occur its oscillator frequency, and this frequency just contains voice signal.Also comprise the carrier wave of a fixed frequency in circuit, be used for carrying this voice signal.After overmodulated circuit, carrier wave can be compounded to form a composite signal with voice signal, and then composite signal is sent in space environment by radio transmitter.Here adopt wireless microphone to be strong because of its mobility, near with source of sound, more original voice signal can be received, be conducive to the accuracy of follow-up speech recognition.
Wireless speech receives, identification module 2, and comprise two aspects, one is speech reception module, and another is sound identification module.The effect of speech reception module is the composite signal that reception 1 produces, and is extracted the voice signal in 1 by demodulator circuit from carrier wave.The effect of sound identification module is the identification voice signal demodulated being carried out voice, voice signal is converted into word and passes to master controller 5 and process.
Below introduce all with this language of Chinese for background, can develop according to country variant or area and be applicable to local device.
Speech recognition system of the present invention have employed the principle of pattern matching.Around this principle, the pattern of unknown voice will compare one by one with the reference model of known voice, and the reference model of optimum Match is by as recognition result.Detailed process comprises the output of the training of ATL, the preliminary treatment of voice signal, the feature extraction of voice signal, pattern matching and differentiation result.
The training of ATL is carried out before recognition, being by collecting sound representative in a large number, from raw tone sample, removing redundant information, retains critical data.Again data are birdsed of the same feather flock together to data by certain rule, formed ATL.It is reported, the tap of domestic voice industry---University of Science and Technology news fly, its product " news rumours phonetic input method " is after the voice packet (sound template storehouse) of a download about 15.39M, and unspecified person, a large amount of vocabulary, continuous print voice signal can be converted into word, discrimination reaches more than 90%.If take cloud, discrimination can reach 95%.The preliminary treatment of voice signal comprises speech signal samples, anti-aliasing band filter, removes the noise effect etc. that individual pronunciation difference and equipment, environment cause, and relates to choosing and end-point detection problem of speech recognition primitive, sometimes also comprises analog-to-digital conversion.The feature extraction of voice signal is used for the parameters,acoustic of abstraction reaction substantive characteristics.Conventional feature has short-time average energy or amplitude, short-time average zero-crossing rate, short-time autocorrelation function, linear predictor coefficient, unvoiced or voiced sound or the initial and the final mark, fundamental frequency, cepstrum etc.Pattern matching is the core of whole speech recognition system, is according to certain criterion and expertise (such as word-building rule, syntax rule, semantic rules etc.), calculates the similarity between input feature vector and inventory mode.The most backward master controller 5 exports the highest matching result of similarity.
Usb circuit 3, for importing preset text to preset text access circuit 4 under the control of master controller 5.So-called preset text is exactly our speech draft or the electronic document of news release, and it needs to import in advance in prompter apparatus system, for display provides template, simultaneously also for the result of speech recognition provides the foundation of contrast.And usb circuit 3 provides the approach inputting preset text and voice packet to prompter apparatus system.We can be connected with usb circuit 3 by movable storage device, by the speech draft file in movable storage device, copy in preset text access circuit 4 by the selection of user.This circuit can also be used for the renewal of voice packet, and specific practice removes the new speech bag in movable storage device to override the voice packet of the reception of original wireless speech, identification module, reaches and upgrade voice packet to improve the object of discrimination.Usb circuit 3 and the interface of movable storage device are the female mouths of a USB, are positioned at display lower right, as shown in Figure 2.After USB device inserts USB interface, by the resistance of two 10K, the control chip of USB peripheral hardware can check whether USB device has accessed the USB port of main frame.If these two pins are high level, one in order just to represent during low level that USB peripheral hardware normally has really been connected into USB interface, at this moment the control chip of peripheral hardware is started working, and passes through DATA+, DATA-and outwards send data.At this moment, after host receiving data, will point out and find new hardware, and start new hardware driving is installed.After drive installation success, we just can operate the file of movable storage device.
Preset text access circuit 4, for saving presets text message.When recognition result is exported to master controller 5 by module 2, master controller 5 can allow the statement in recognition result and preset text compare.We can set a similarity, and when similarity is greater than how many (such as 80%), what just expression speaker or announcer read just now is this statement.Then after this or several (can set according to user the sentence number changing and highlight) words adopt eye-catching enlarge font to show on the display 6 by we, this completes the function of prompter.
Master controller 5, for the treatment of the information of modules.Specifically comprise the Word message that module 2 identified compared with preset text, find the word meeting similarity.And the parameter that control display is arranged according to user shows.
Display 6, for showing the partial content of speech draft or news release, allow speechmaker and announcer eye-catching enlarge font outstanding under intuitively, clearly see that they will read hereafter.
The external structure of display as shown in Figure 2.
User arranges button circuit 7, for the input of user.Consider that different users has different hobbies or custom, different user oneself can set some parameters.These parameters have font, word size, text color, background, display sentence number etc. hereafter.These arrange button distribution over the display, and particular location as shown in Figure 2.Concrete button has mains switch 21, beginning/Pause key 22, arranges key 23, up key 24, down key 25 and acknowledgement key 26.
Whether mains switch 21, being energized for controlling whole prompter apparatus system, is the master switch of whole system.
Whether beginning/Pause key 22, carry out for controlling speech recognition, selects to represent time " beginning " and carry out speech recognition, select " time-out " to represent and do not carry out speech recognition.
Key 23 is set, for the setting of font, word size, text color, background, display sentence hereafter (be a sentence with the word between any two punctuation marks) number and enter U disk file catalogue.For Chinese, font has the conventional fonts such as the Song typeface, Chinese-language row pattern, regular script, lishu and the new Song typeface, is defaulted as the Song typeface.Word size has 24pt, 30pt, 36pt, 48pt and 60pt, is defaulted as 30pt.Word and background color have black, white, redness, the conventional color such as orange, are defaulted as white background, black font, and the font component highlighted is for red.Have 1,2,3,4 for display sentence number hereafter, be defaulted as and highlight hereafter 2.
Up key 24, at system parameter setting interface, for controlling moving up of cursor.Down key 25, at system parameter setting interface, for controlling moving down of cursor.Concrete enforcement can realize the movement of cursor by changing the pointer pointing to cursor.
Acknowledgement key 26, at system parameter setting interface, for the content of selection cursor position.Concrete enforcement can go by button the value changing variable, and then the operational mode of reprogramming.
Socket 27, in display screen side, for being connected, to import preset text with USB device such as USB flash disks.
28 is display screen main windows.For showing content of text.
Do text description to the display effect in real process below: in use the statement of double underline represents it is the statement just identified, the font component of amplification represents will be read hereafter.Such display mode is convenient to people and is read aloud, and prompter is effective.2 needs are had to illustrate: how one, judge a sentence? here we are a sentence with the word between any two punctuation marks, and the preset text chosen can be divided into sentence one by one by this system in advance, and is numbered.But often occur the situation that between two punctuation marks, number of words is very few in article, number of words can affect the result of identification and the accuracy of location very little undoubtedly.So the number of words between two punctuation marks is less than a timing (being such as 7), we can by it and in lower a word.Its two, in order to solve screens switch to speech or the inconvenience that brings of broadcasting, we allow the part highlighted be in the position, upper middle of screen all the time, also can not bring sense of discomfort to reader when captions refresh.Detailed process the part read is removed fast above screen when displaying contents changes, and the part do not read is from rapid loading below screen.
Claims (2)
1. there is the prompter device of speech identifying function, it is characterized in that, comprise wireless microphone (1), wireless speech receives identification module (2), usb circuit (3), preset text access circuit (4), master controller (5), display (6), user arranges button circuit (7), master controller (5) accepts identification module (2) respectively as CPU with wireless speech, preset text access circuit (4), display (6), user arranges button circuit (7) and usb circuit (3) is connected with hardware, wireless microphone (1) and wireless speech module (2) take free space as transmission medium, the voice signal from speaker or announcer is received by wireless microphone (1), the voice signal received is wirelessly sent to voice signal corresponding with it and receives identification module (2), this module is through the process of speech recognition technology, voice signal is converted into word and passes to master controller (5), by master controller (5), the statement in this section of word and preset text access circuit (4) is contrasted, and find this statement, finally display in display (6).
2. prompter device as claimed in claim 1, it is characterized in that, it is speech reception module and a sound identification module that described wireless speech reception identification module (2) comprises one, speech reception module receives the composite signal that wireless microphone produces, and extracts voice signal by demodulator circuit from carrier wave; The effect of sound identification module is the identification voice signal demodulated being carried out voice, voice signal is converted into word and passes to master controller (5) process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510196636.2A CN104796584A (en) | 2015-04-23 | 2015-04-23 | Prompt device with voice recognition function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510196636.2A CN104796584A (en) | 2015-04-23 | 2015-04-23 | Prompt device with voice recognition function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104796584A true CN104796584A (en) | 2015-07-22 |
Family
ID=53561082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510196636.2A Pending CN104796584A (en) | 2015-04-23 | 2015-04-23 | Prompt device with voice recognition function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104796584A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106896746A (en) * | 2017-01-09 | 2017-06-27 | 深圳前海勇艺达机器人有限公司 | Robot with function of presiding over the meeting |
| CN106910504A (en) * | 2015-12-22 | 2017-06-30 | 北京君正集成电路股份有限公司 | A kind of speech reminding method and device based on speech recognition |
| CN107257448A (en) * | 2017-08-09 | 2017-10-17 | 成都全云科技有限公司 | A kind of video conferencing system exchanged with font |
| CN107527623A (en) * | 2017-08-07 | 2017-12-29 | 广州视源电子科技股份有限公司 | Screen transmission method, device, electronic equipment and computer-readable recording medium |
| WO2018036466A1 (en) * | 2016-08-24 | 2018-03-01 | 中兴通讯股份有限公司 | Voice recognition processing method and device |
| CN109089018A (en) * | 2018-10-29 | 2018-12-25 | 上海理工大学 | A kind of intelligence prompter devices and methods therefor |
| CN109639935A (en) * | 2019-01-25 | 2019-04-16 | 合肥学院 | The automatic word extractor system and method for video record |
| CN110164442A (en) * | 2019-06-21 | 2019-08-23 | 上海乂学教育科技有限公司 | Acoustic control word extractor system based on speech recognition |
| CN110708441A (en) * | 2018-07-25 | 2020-01-17 | 南阳理工学院 | Word-prompting device |
| CN111902831A (en) * | 2019-01-25 | 2020-11-06 | 互动解决方案公司 | Demonstration support system |
| CN111919251A (en) * | 2019-01-25 | 2020-11-10 | 互动解决方案公司 | Voice analysis system |
| CN113257246A (en) * | 2021-04-19 | 2021-08-13 | 歌尔股份有限公司 | Prompting method, device, equipment, system and storage medium |
| CN113468319A (en) * | 2021-07-21 | 2021-10-01 | 深圳市亿莱顿科技有限公司 | Internet-based multi-application-scene conference interaction system and method |
| CN113506550A (en) * | 2021-07-29 | 2021-10-15 | 北京花兰德科技咨询服务有限公司 | Artificial intelligent reading display and display method |
| CN113724709A (en) * | 2021-08-31 | 2021-11-30 | 北京字跳网络技术有限公司 | Text content matching method and device, electronic equipment and storage medium |
| CN113874827A (en) * | 2020-01-06 | 2021-12-31 | 互动解决方案公司 | Demonstration support system |
| CN114554031A (en) * | 2022-03-07 | 2022-05-27 | 云知声智能科技股份有限公司 | Method, device, terminal and storage medium for prompting |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1870728A (en) * | 2005-05-23 | 2006-11-29 | 北京大学 | Method and system for automatic subtilting |
| CN101064177A (en) * | 2006-04-26 | 2007-10-31 | 松下电器产业株式会社 | Caption display control apparatus |
| CN101505397A (en) * | 2009-02-20 | 2009-08-12 | 深圳华为通信技术有限公司 | Method and system for audio and video subtitle synchronous presenting |
| CN102568312A (en) * | 2010-12-20 | 2012-07-11 | 邓凯 | Multifunctional electronic seat card |
| CN102714708A (en) * | 2010-02-12 | 2012-10-03 | 汤姆森特许公司 | Method for synchronized content playback |
-
2015
- 2015-04-23 CN CN201510196636.2A patent/CN104796584A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1870728A (en) * | 2005-05-23 | 2006-11-29 | 北京大学 | Method and system for automatic subtilting |
| CN101064177A (en) * | 2006-04-26 | 2007-10-31 | 松下电器产业株式会社 | Caption display control apparatus |
| CN101505397A (en) * | 2009-02-20 | 2009-08-12 | 深圳华为通信技术有限公司 | Method and system for audio and video subtitle synchronous presenting |
| CN102714708A (en) * | 2010-02-12 | 2012-10-03 | 汤姆森特许公司 | Method for synchronized content playback |
| CN102568312A (en) * | 2010-12-20 | 2012-07-11 | 邓凯 | Multifunctional electronic seat card |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106910504A (en) * | 2015-12-22 | 2017-06-30 | 北京君正集成电路股份有限公司 | A kind of speech reminding method and device based on speech recognition |
| WO2018036466A1 (en) * | 2016-08-24 | 2018-03-01 | 中兴通讯股份有限公司 | Voice recognition processing method and device |
| CN106896746A (en) * | 2017-01-09 | 2017-06-27 | 深圳前海勇艺达机器人有限公司 | Robot with function of presiding over the meeting |
| CN107527623A (en) * | 2017-08-07 | 2017-12-29 | 广州视源电子科技股份有限公司 | Screen transmission method, device, electronic equipment and computer-readable recording medium |
| CN107257448A (en) * | 2017-08-09 | 2017-10-17 | 成都全云科技有限公司 | A kind of video conferencing system exchanged with font |
| CN110708441A (en) * | 2018-07-25 | 2020-01-17 | 南阳理工学院 | Word-prompting device |
| CN110708441B (en) * | 2018-07-25 | 2021-12-10 | 南阳理工学院 | Word-prompting device |
| CN109089018A (en) * | 2018-10-29 | 2018-12-25 | 上海理工大学 | A kind of intelligence prompter devices and methods therefor |
| CN109639935A (en) * | 2019-01-25 | 2019-04-16 | 合肥学院 | The automatic word extractor system and method for video record |
| CN109639935B (en) * | 2019-01-25 | 2020-10-13 | 合肥学院 | Video recording automatic prompting method and computer readable storage medium |
| CN111902831A (en) * | 2019-01-25 | 2020-11-06 | 互动解决方案公司 | Demonstration support system |
| CN111919251A (en) * | 2019-01-25 | 2020-11-10 | 互动解决方案公司 | Voice analysis system |
| US11922929B2 (en) | 2019-01-25 | 2024-03-05 | Interactive Solutions Corp. | Presentation support system |
| CN111902831B (en) * | 2019-01-25 | 2021-11-05 | 互动解决方案公司 | Demonstration support system |
| CN110164442A (en) * | 2019-06-21 | 2019-08-23 | 上海乂学教育科技有限公司 | Acoustic control word extractor system based on speech recognition |
| CN113874827A (en) * | 2020-01-06 | 2021-12-31 | 互动解决方案公司 | Demonstration support system |
| CN113257246B (en) * | 2021-04-19 | 2023-03-14 | 歌尔股份有限公司 | Prompting method, device, equipment, system and storage medium |
| CN113257246A (en) * | 2021-04-19 | 2021-08-13 | 歌尔股份有限公司 | Prompting method, device, equipment, system and storage medium |
| CN113468319A (en) * | 2021-07-21 | 2021-10-01 | 深圳市亿莱顿科技有限公司 | Internet-based multi-application-scene conference interaction system and method |
| CN113468319B (en) * | 2021-07-21 | 2022-01-14 | 深圳市亿莱顿科技有限公司 | Internet-based multi-application-scene conference interaction system and method |
| CN113506550A (en) * | 2021-07-29 | 2021-10-15 | 北京花兰德科技咨询服务有限公司 | Artificial intelligent reading display and display method |
| CN113724709A (en) * | 2021-08-31 | 2021-11-30 | 北京字跳网络技术有限公司 | Text content matching method and device, electronic equipment and storage medium |
| WO2023029904A1 (en) * | 2021-08-31 | 2023-03-09 | 北京字跳网络技术有限公司 | Text content matching method and apparatus, electronic device, and storage medium |
| CN114554031A (en) * | 2022-03-07 | 2022-05-27 | 云知声智能科技股份有限公司 | Method, device, terminal and storage medium for prompting |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104796584A (en) | Prompt device with voice recognition function | |
| US10013977B2 (en) | Smart home control method based on emotion recognition and the system thereof | |
| CN102723078B (en) | Emotion speech recognition method based on natural language comprehension | |
| KR100948600B1 (en) | System and method for integrating gesture and voice | |
| WO2015059976A1 (en) | Information processing device, information processing method, and program | |
| CN112040263A (en) | Video processing method, video playing method, video processing device, video playing device, storage medium and equipment | |
| CN102568478A (en) | Video play control method and system based on voice recognition | |
| CN105244026A (en) | Voice processing method and device | |
| CN111583907A (en) | Information processing method, device and storage medium | |
| CN112735417B (en) | Speech translation method, electronic device, and computer-readable storage medium | |
| CN110853615A (en) | Data processing method, device and storage medium | |
| CN111415537A (en) | Symbol-labeling-based word listening system for primary and secondary school students | |
| CN106558306A (en) | Method for voice recognition, device and equipment | |
| CN110781649A (en) | Subtitle editing method and device, computer storage medium and electronic equipment | |
| CN107909997A (en) | A kind of combination control method and system | |
| CN112102828A (en) | Voice control method and system for automatically broadcasting content on large screen | |
| CN111435595A (en) | Text normalization method and device | |
| CN204559707U (en) | There is the prompter device of speech identifying function | |
| CN111062221A (en) | Data processing method, data processing device, electronic equipment and storage medium | |
| CN113992972A (en) | Subtitle display method and device, electronic equipment and readable storage medium | |
| CN115104151A (en) | Offline voice recognition method and device, electronic equipment and readable storage medium | |
| CN112185357A (en) | Device and method for simultaneously recognizing human voice and non-human voice | |
| CN112584238A (en) | Movie and television resource matching method and device and smart television | |
| CN111048068A (en) | Voice wake-up method, device and system and electronic equipment | |
| CN204856534U (en) | System of looking that helps is read to low eyesight based on OCR and TTS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150722 |