CN107274891A - A kind of AR interface alternation method and system based on speech recognition engine - Google Patents
A kind of AR interface alternation method and system based on speech recognition engine Download PDFInfo
- Publication number
- CN107274891A CN107274891A CN201710368669.XA CN201710368669A CN107274891A CN 107274891 A CN107274891 A CN 107274891A CN 201710368669 A CN201710368669 A CN 201710368669A CN 107274891 A CN107274891 A CN 107274891A
- Authority
- CN
- China
- Prior art keywords
- speech recognition
- recognition engine
- library
- interface alternation
- engine
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/38—Creation or generation of source code for implementing user interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
Abstract
The present invention relates to a kind of AR interface alternation method and system based on speech recognition engine, its method comprises the following steps, S1, and phonetic order is generated using speech recognition engine;The coordinate position of dummy object in S2, identification AR interface, and the dummy object in the AR interfaces is performed corresponding interbehavior according to the phonetic order at the coordinate position.A kind of AR interface alternation methods based on speech recognition engine of the present invention solve the problem of voice of player can not be identified existing augmented reality, enrich people and the interactivity of game in AR applications, it can not only be interacted by picture with dummy object, the control function to the certain behavior of dummy object can also be reached by voice, the interest and playability of AR game is enhanced.
Description
Technical field
The present invention relates to AR technical fields, be specifically related to a kind of AR interface alternations method based on speech recognition engine and
System.
Background technology
The playing method of game in terms of existing (Augmented Reality, abbreviation AR) on augmented reality is to play
Family performs the behavior operation to virtual role by the button on operation equipment interface, and this playing method can not be rapidly achieved finger
Wave the purpose of dummy object on AR interfaces;Meanwhile, identification of the existing speech recognition technology to large vocabulary is unable to reach very high
Accuracy of identification, and be that can not allow the higher false drop rate of appearance of phonetic order in AR game, if there is higher
False drop rate can reduce the playability of game.
The content of the invention
The technical problems to be solved by the invention be to provide a kind of AR interface alternations method based on speech recognition engine and
System, solves the problem of voice of player can not be identified existing augmented reality, and can not only improve AR game should
Playability, also enriches the interaction between people and virtual reality, enhances the interest of AR technical products.
The technical scheme that the present invention solves above-mentioned technical problem is as follows:A kind of AR interface alternations based on speech recognition engine
Method, comprises the following steps,
S1, phonetic order is generated using speech recognition engine;
The coordinate position of dummy object in S2, identification AR interface, and the dummy object in the AR interfaces is sat described
Corresponding interbehavior is performed according to the phonetic order at cursor position.
The beneficial effects of the invention are as follows:A kind of AR interface alternation methods based on speech recognition engine of the present invention utilize voice
Recognize engine generation phonetic order;The coordinate position of dummy object in AR interfaces is recognized, and makes the virtual object in the AR interfaces
Body performs corresponding interbehavior at the coordinate position according to the phonetic order;It this method solve existing augmented reality
The problem of voice of player can not be identified technology, enriches people and the interactivity of game in AR applications, can not only lead to
Cross picture to interact with dummy object, moreover it is possible to reach the control function to the certain behavior of dummy object by voice, enhance
The interest and playability of AR game.
On the basis of above-mentioned technical proposal, the present invention can also do following improvement.
Further, the S1 specifically,
S11, carries out off-line learning to the vocabulary for needing speech recognition, obtains speech recognition library;
S12, the speech recognition library is imported into speech recognition engine,
S13, voice signal is inputted into the speech recognition engine, and by the voice signal and the speech recognition
Data in storehouse are matched, and the speech recognition engine generates corresponding phonetic order according to matching result.
Further, the S11 specifically,
S111, RP, generation instruction audio file are carried out to the vocabulary for needing speech recognition;
S112, is trained, and extract institute by speech recognition engine off-line learning instrument to the instruction audio file
The characteristic information in instruction audio file is stated, instruction text file is generated;
S113, is counted to the instruction text file, and extracts what is successively occurred between different instruction text
Statistical relationship;
S114, builds speech recognition modeling, and export the initial precision ginseng of speech recognition modeling according to the statistical relationship
Number,
S115, is tested the speech recognition modeling, and adjusted according to test result repeatedly using parameters precision parameter
The initial precision parameter is saved, final precision parameter is drawn;
S116, generation speech recognition library is combined with the speech recognition modeling by the final precision parameter.
Beneficial effect using above-mentioned further scheme is:A kind of AR interface alternations based on speech recognition engine of the present invention
Method is based on speech recognition engine, and first the audio file of the phonetic order to needing off-line learning carries out training repeatedly and to knowing
The debugging repeatedly of other parameter, to get the speech recognition library of high-accuracy, improves the precision of speech recognition.
Further, the speech recognition engine is based on the exploitation of PocketSphinx speech recognition systems.
Beneficial effect using above-mentioned further scheme is:The voice developed based on PocketSphinx speech recognition systems
Identification engine is the speech recognition engine of an amount of calculation and volume all very littles, and its accuracy of identification to small vocabulary is very high
, and to the destruction very little of performance, reaction quickly, can further solve existing augmented reality to the voice of player without
The problem of method is identified.
Further, in the S13, before the voice signal is matched with the data in the speech recognition library also
Including:Filtration treatment is carried out to the voice signal.
Beneficial effect using above-mentioned further scheme is:To voice signal carry out filtration treatment after again with speech recognition library
In data matched, the noise in voice signal can be removed, it is to avoid interference, improve matching accuracy rate.
Based on a kind of above-mentioned AR interface alternation methods based on speech recognition engine, the present invention also provides a kind of based on voice
Recognize the AR interface alternation systems of engine.
A kind of AR interface alternation systems based on speech recognition engine, including speech recognition engine and AR engines,
The speech recognition engine, it is used to generate phonetic order;
The AR engines, it is used for the coordinate position for recognizing dummy object in AR interfaces, and makes the void in the AR interfaces
Intend object and corresponding interbehavior is performed according to the phonetic order at the coordinate position.
The beneficial effects of the invention are as follows:A kind of AR interface alternation systems based on speech recognition engine of the present invention believe voice
Phonetic order is generated number in speech recognition engine and is sent in AR engines, recognizes that tracking obtains AR circle by combining AR engines
The coordinate position of dummy object in face, corresponding behavior control is carried out to dummy object in AR interfaces;It this method solve existing increasing
The problem of voice of player can not be identified strong reality technology, enriches people and the interactivity of game in AR applications, not only
It can be interacted by picture with dummy object, moreover it is possible to which the control function to the certain behavior of dummy object is reached by voice,
Enhance the interest and playability of AR game.
On the basis of above-mentioned technical proposal, the present invention can also do following improvement.
Further, the speech recognition engine specifically for,
Off-line learning is carried out to the vocabulary for needing speech recognition, speech recognition library is obtained;
The speech recognition library is imported into speech recognition engine,
Voice signal is inputted into the speech recognition engine, and by the voice signal and the speech recognition library
Data matched, the speech recognition engine generates corresponding phonetic order according to matching result.
Further, the speech recognition engine specifically for,
RP, generation instruction audio file are carried out to the vocabulary for needing speech recognition;
The instruction audio file is trained by speech recognition engine off-line learning instrument, and extracts the instruction
Characteristic information in audio file, generates instruction text file;
The instruction text file is counted, and extracts the statistics successively occurred between different instruction text and is closed
System;
Speech recognition modeling is built according to the statistical relationship, and exports the initial precision parameter of speech recognition modeling,
The speech recognition modeling is tested repeatedly using parameters precision parameter, and according to test result regulation
Initial precision parameter, draws final precision parameter;
The final precision parameter is combined into generation speech recognition library with the speech recognition modeling.
Beneficial effect using above-mentioned further scheme is:A kind of AR interface alternations based on speech recognition engine of the present invention
System is based on speech recognition engine, and first the audio file of the phonetic order to needing off-line learning carries out training repeatedly and to knowing
The debugging repeatedly of other parameter, to get the speech recognition library of high-accuracy, improves the precision of speech recognition.
Further, the speech recognition engine is based on the exploitation of PocketSphinx speech recognition systems.
Beneficial effect using above-mentioned further scheme is:The voice developed based on PocketSphinx speech recognition systems
Identification engine is the speech recognition engine of an amount of calculation and volume all very littles, and its accuracy of identification to small vocabulary is very high
, and to the destruction very little of performance, reaction quickly, can further solve existing augmented reality to the voice of player without
The problem of method is identified.
Further, in the speech recognition engine, the voice signal is entered with the data in the speech recognition library
Also include before row matching:Filtration treatment is carried out to the voice signal.
Beneficial effect using above-mentioned further scheme is:To voice signal carry out filtration treatment after again with speech recognition library
In data matched, the noise in voice signal can be removed, it is to avoid interference, improve matching accuracy rate.
Brief description of the drawings
Fig. 1 is a kind of overall flow figure of the AR interface alternation methods based on speech recognition engine of the present invention;
Fig. 2 is the flow of generation phonetic order in a kind of AR interface alternation methods based on speech recognition engine of the present invention
Figure;
Fig. 3 in a kind of AR interface alternation methods based on speech recognition engine of the present invention to needing the vocabulary of speech recognition
Carry out the flow chart that off-line learning obtains speech recognition library;
Fig. 4 is a kind of structured flowchart of the AR interface alternation systems based on speech recognition engine of the present invention.
Embodiment
The principle and feature of the present invention are described below in conjunction with accompanying drawing, the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
As shown in figure 1, a kind of AR interface alternation methods based on speech recognition engine, comprise the following steps,
S1, phonetic order is generated using speech recognition engine;
The coordinate position of dummy object in S2, identification AR interface, and the dummy object in the AR interfaces is sat described
Corresponding interbehavior is performed according to the phonetic order at cursor position.
In this specific embodiment, the S1 specifically, as shown in Fig. 2
S11, carries out off-line learning to the vocabulary for needing speech recognition, obtains speech recognition library;
S12, the speech recognition library is imported into speech recognition engine,
S13, voice signal is inputted into the speech recognition engine, and by the voice signal and the speech recognition
Data in storehouse are matched, and the speech recognition engine generates corresponding phonetic order according to matching result.
In this specific embodiment, in the S11, off-line learning is carried out to the vocabulary for needing speech recognition and obtains voice knowledge
Other storehouse is concretely comprised the following steps, as shown in figure 3,
S111, RP, generation instruction audio file are carried out to the vocabulary for needing speech recognition;
S112, is trained, and extract institute by speech recognition engine off-line learning instrument to the instruction audio file
The characteristic information in instruction audio file is stated, instruction text file is generated;
S113, is counted to the instruction text file, and extracts what is successively occurred between different instruction text
Statistical relationship;
S114, builds speech recognition modeling, and export the initial precision ginseng of speech recognition modeling according to the statistical relationship
Number,
S115, is tested the speech recognition modeling, and adjusted according to test result repeatedly using parameters precision parameter
The initial precision parameter is saved, final precision parameter is drawn;
S116, generation speech recognition library is combined with the speech recognition modeling by the final precision parameter.
In this specific embodiment, the speech recognition engine is based on the exploitation of PocketSphinx speech recognition systems.
In this specific embodiment, in the S13, the voice signal is entered with the data in the speech recognition library
Also include carrying out filtration treatment to the voice signal before row matching.
A kind of AR interface alternations method based on speech recognition engine of the present invention is illustrated so that AR plays as an example below.
Specifically for example:
In a AR game applications using the method exploitation of the present invention, it is possible to achieve the soldier of player is simply referred to
The function of operation is waved, the enemy that order soldier preferentially attacks front, the enemy on the preferential attack left side, preferential attack the right is followed successively by
Enemy, defend backward this 4 instruction, and hold AR stage properties (as exploitation peashooter) experience AR game player can not be quick
The corresponding button by manual operation mobile terminal reach soldier's function of commander.Utilize the language of the method exploitation of the present invention
Sound identification engine, which quickly can be responded accurately, to be attacked forward, is attacked, is attacked to the right to the left, this 4 simple languages are defendd backward
Sound is instructed, and accomplishes that this point is accomplished by, and first passes through carry out RP of the tester to the vocabulary of phonetic order, generation instruction
Audio file;The instruction audio file is trained by speech recognition engine off-line learning instrument, and extracts the finger
The characteristic information in audio file is made, instruction text file is generated;The instruction text file is counted, and extracts difference
The statistical relationship successively occurred between instruction text file;Speech recognition modeling is built according to the statistical relationship, and exports language
The initial precision parameter of sound identification model, is tested the speech recognition modeling repeatedly using parameters precision parameter, and root
The initial precision parameter is adjusted according to test result, final precision parameter is drawn;By the final precision parameter and the voice
Identification model combines generation speech recognition library.
Study is obtained speech recognition library to imported into speech recognition engine, the phonetic order that people sends entered so as to realize
The function of row identification;Its specific method is that the corresponding phonetic order of saying of player's standard is such as attacked forward, and mobile device is obtained
To corresponding voice data, it is input in speech recognition engine, progress is gone after the dry corresponding filtration treatment of grade, voice data
Matched with the data in speech recognition library, obtain being sent to after matching result in AR engines, it is responded by AR engines.
AR systems are followed the trail of by the identification to designated pictures stably to get dummy object into real world
Positional information, the incoming voice identification result of speech recognition engine carries out being converted into the commander behaviour to the soldier that plays after analysis judgement
Instruct.
The method of the present invention make it that augmented reality obtains speech identifying function system, enhancing people and virtual reality it
Between interaction, enhance AR game interest and playability;If player is when holding peashooter experience AR game, it is no longer necessary to
As traditional game, it is necessary to the behavior operation to virtual role is performed by operating the button on the interface of mobile terminal, but
The behavior that virtual role in being played to AR is performed by the movement of itself and phonetic order is operated.
Based on a kind of above-mentioned AR interface alternation methods based on speech recognition engine, the present invention also provides a kind of based on voice
Recognize the AR interface alternation systems of engine.
As shown in figure 4, a kind of AR interface alternation systems based on speech recognition engine, including speech recognition engine and AR draw
Hold up,
The speech recognition engine, it is used to generate phonetic order;
The AR engines, it is used for the coordinate position for recognizing dummy object in AR interfaces, and makes the void in the AR interfaces
Intend object and corresponding interbehavior is performed according to the phonetic order at the coordinate position.
In this specific embodiment, the speech recognition engine specifically for,
Off-line learning is carried out to the vocabulary for needing speech recognition, speech recognition library is obtained;
The speech recognition library is imported into speech recognition engine,
Voice signal is inputted into the speech recognition engine, and by the voice signal and the speech recognition library
Data matched, the speech recognition engine generates corresponding phonetic order according to matching result.
In this specific embodiment, the speech recognition engine specifically for,
RP, generation instruction audio file are carried out to the vocabulary for needing speech recognition;
The instruction audio file is trained by speech recognition engine off-line learning instrument, and extracts the instruction
Characteristic information in audio file, generates instruction text file;
The instruction text file is counted, and extracts the statistics successively occurred between different instruction text and is closed
System;
Speech recognition modeling is built according to the statistical relationship, and exports the initial precision parameter of speech recognition modeling,
The speech recognition modeling is tested repeatedly using parameters precision parameter, and according to test result regulation
Initial precision parameter, draws final precision parameter;
The final precision parameter is combined into generation speech recognition library with the speech recognition modeling.
In this specific embodiment, the speech recognition engine is based on the exploitation of PocketSphinx speech recognition systems.
In this specific embodiment, in the speech recognition engine, by the voice signal and the speech recognition library
In data matched before also include:Filtration treatment is carried out to the voice signal.
A kind of AR interface alternation systems based on speech recognition engine of the present invention are by voice signal in speech recognition engine
Generation phonetic order is simultaneously sent in AR engines, recognizes that tracking obtains the coordinate of dummy object in AR interfaces by combining AR engines
Position, corresponding behavior control is carried out to dummy object in AR interfaces;Existing augmented reality be this method solve to player's
The problem of voice can not be identified, enriches people and the interactivity of game in AR applications, not only can by picture with it is virtual
Object is interacted, moreover it is possible to reach the control function to the certain behavior of dummy object by voice, enhances the entertaining of AR game
Property and playability.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc. should be included in the scope of the protection.
Claims (10)
1. a kind of AR interface alternation methods based on speech recognition engine, it is characterised in that:Comprise the following steps,
S1, phonetic order is generated using speech recognition engine;
The coordinate position of dummy object in S2, identification AR interface, and make the dummy object in the AR interfaces in the coordinate bit
Put place and corresponding interbehavior is performed according to the phonetic order.
2. a kind of AR interface alternation methods based on speech recognition engine according to claim 1, it is characterised in that:It is described
S1 specifically,
S11, carries out off-line learning to the vocabulary for needing speech recognition, obtains speech recognition library;
S12, the speech recognition library is imported into speech recognition engine,
S13, voice signal is inputted into the speech recognition engine, and by the voice signal and the speech recognition library
Data matched, the speech recognition engine generates corresponding phonetic order according to matching result.
3. a kind of AR interface alternation methods based on speech recognition engine according to claim 2, it is characterised in that:It is described
S11 specifically,
S111, RP, generation instruction audio file are carried out to the vocabulary for needing speech recognition;
S112, is trained, and extract the finger by speech recognition engine off-line learning instrument to the instruction audio file
The characteristic information in audio file is made, instruction text file is generated;
S113, is counted, and extract the statistics successively occurred between different instruction text to the instruction text file
Relation;
S114, speech recognition modeling is built according to the statistical relationship, and exports the initial precision parameter of speech recognition modeling,
S115, is tested the speech recognition modeling repeatedly using parameters precision parameter, and adjusts institute according to test result
Initial precision parameter is stated, final precision parameter is drawn;
S116, generation speech recognition library is combined with the speech recognition modeling by the final precision parameter.
4. a kind of AR interface alternation methods based on speech recognition engine according to any one of claims 1 to 3, its feature
It is:The speech recognition engine is based on the exploitation of PocketSphinx speech recognition systems.
5. a kind of AR interface alternation methods based on speech recognition engine according to Claims 2 or 3, it is characterised in that:
In the S13, also include before the voice signal is matched with the data in the speech recognition library:To the voice
Signal carries out filtration treatment.
6. a kind of AR interface alternation systems based on speech recognition engine, it is characterised in that:Draw including speech recognition engine and AR
Hold up,
The speech recognition engine, it is used to generate phonetic order;
The AR engines, it is used for the coordinate position for recognizing dummy object in AR interfaces, and makes the virtual object in the AR interfaces
Body performs corresponding interbehavior at the coordinate position according to the phonetic order.
7. a kind of AR interface alternation systems based on speech recognition engine according to claim 6, it is characterised in that:It is described
Speech recognition engine specifically for,
Off-line learning is carried out to the vocabulary for needing speech recognition, speech recognition library is obtained;
The speech recognition library is imported into speech recognition engine,
Voice signal is inputted into the speech recognition engine, and by the number in the voice signal and the speech recognition library
According to being matched, the speech recognition engine generates corresponding phonetic order according to matching result.
8. a kind of AR interface alternation systems based on speech recognition engine according to claim 7, it is characterised in that:It is described
Speech recognition engine specifically for,
RP, generation instruction audio file are carried out to the vocabulary for needing speech recognition;
The instruction audio file is trained by speech recognition engine off-line learning instrument, and extracts the instruction audio
Characteristic information in file, generates instruction text file;
The instruction text file is counted, and extracts the statistical relationship successively occurred between different instruction text;
Speech recognition modeling is built according to the statistical relationship, and exports the initial precision parameter of speech recognition modeling,
The speech recognition modeling is tested repeatedly using parameters precision parameter, and it is described initial according to test result regulation
Precision parameter, draws final precision parameter;
The final precision parameter is combined into generation speech recognition library with the speech recognition modeling.
9. a kind of AR interface alternation systems based on speech recognition engine according to any one of claim 6 to 8, its feature
It is:The speech recognition engine is based on the exploitation of PocketSphinx speech recognition systems.
10. a kind of AR interface alternation systems based on speech recognition engine according to claim 7 or 8, it is characterised in that:
In the speech recognition engine, also include before the voice signal is matched with the data in the speech recognition library:
Filtration treatment is carried out to the voice signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710368669.XA CN107274891A (en) | 2017-05-23 | 2017-05-23 | A kind of AR interface alternation method and system based on speech recognition engine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710368669.XA CN107274891A (en) | 2017-05-23 | 2017-05-23 | A kind of AR interface alternation method and system based on speech recognition engine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107274891A true CN107274891A (en) | 2017-10-20 |
Family
ID=60064711
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710368669.XA Pending CN107274891A (en) | 2017-05-23 | 2017-05-23 | A kind of AR interface alternation method and system based on speech recognition engine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107274891A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110597395A (en) * | 2019-09-19 | 2019-12-20 | 腾讯科技(深圳)有限公司 | Object interaction control method and device, storage medium and electronic device |
CN110941416A (en) * | 2019-11-15 | 2020-03-31 | 北京奇境天成网络技术有限公司 | Interaction method and device for human and virtual object in augmented reality |
WO2022088840A1 (en) * | 2020-10-29 | 2022-05-05 | 北京字节跳动网络技术有限公司 | Ar game control method and apparatus, electronic device, and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104008752A (en) * | 2013-02-25 | 2014-08-27 | 精工爱普生株式会社 | Speech recognition device and method, and semiconductor integrated circuit device |
CN105608934A (en) * | 2015-12-21 | 2016-05-25 | 大连新锐天地传媒有限公司 | AR children's story early education stage play system |
CN106408480A (en) * | 2016-11-25 | 2017-02-15 | 山东孔子文化产业发展有限公司 | Sinology three-dimensional interactive learning system and method based on augmented reality and speech recognition |
CN106444023A (en) * | 2016-08-29 | 2017-02-22 | 北京知境科技有限公司 | Super-large field angle binocular stereoscopic display transmission type augmented reality system |
CN106512393A (en) * | 2016-10-14 | 2017-03-22 | 上海异界信息科技有限公司 | Application voice control method and system suitable for virtual reality environment |
-
2017
- 2017-05-23 CN CN201710368669.XA patent/CN107274891A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104008752A (en) * | 2013-02-25 | 2014-08-27 | 精工爱普生株式会社 | Speech recognition device and method, and semiconductor integrated circuit device |
CN105608934A (en) * | 2015-12-21 | 2016-05-25 | 大连新锐天地传媒有限公司 | AR children's story early education stage play system |
CN106444023A (en) * | 2016-08-29 | 2017-02-22 | 北京知境科技有限公司 | Super-large field angle binocular stereoscopic display transmission type augmented reality system |
CN106512393A (en) * | 2016-10-14 | 2017-03-22 | 上海异界信息科技有限公司 | Application voice control method and system suitable for virtual reality environment |
CN106408480A (en) * | 2016-11-25 | 2017-02-15 | 山东孔子文化产业发展有限公司 | Sinology three-dimensional interactive learning system and method based on augmented reality and speech recognition |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110597395A (en) * | 2019-09-19 | 2019-12-20 | 腾讯科技(深圳)有限公司 | Object interaction control method and device, storage medium and electronic device |
CN110941416A (en) * | 2019-11-15 | 2020-03-31 | 北京奇境天成网络技术有限公司 | Interaction method and device for human and virtual object in augmented reality |
WO2022088840A1 (en) * | 2020-10-29 | 2022-05-05 | 北京字节跳动网络技术有限公司 | Ar game control method and apparatus, electronic device, and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11550998B2 (en) | Method and apparatus for generating a competition commentary based on artificial intelligence, and storage medium | |
CN106710590B (en) | Voice interaction system and method with emotion function based on virtual reality environment | |
CN110971964B (en) | Intelligent comment generation and playing method, device, equipment and storage medium | |
JP7253570B2 (en) | Contextual in-game element recognition, annotation and interaction based on remote user input | |
Chai et al. | Sign language recognition and translation with kinect | |
Lang et al. | Sign language recognition using kinect | |
CN106182006B (en) | Chess and card interaction data processing method towards intelligent robot and device | |
CN102110399B (en) | A kind of assist the method for explanation, device and system thereof | |
CN107274891A (en) | A kind of AR interface alternation method and system based on speech recognition engine | |
CN108986835A (en) | Based on speech de-noising method, apparatus, equipment and the medium for improving GAN network | |
TW201117110A (en) | Behavior recognition system and recognition method by combining image and speech, and the computer | |
WO2021196646A1 (en) | Interactive object driving method and apparatus, device, and storage medium | |
CN108109613A (en) | For the audio training of Intelligent dialogue voice platform and recognition methods and electronic equipment | |
CN108711436A (en) | Speaker verification's system Replay Attack detection method based on high frequency and bottleneck characteristic | |
CN103035135A (en) | Children cognitive system based on augment reality technology and cognitive method | |
WO2017166651A1 (en) | Voice recognition model training method, speaker type recognition method and device | |
CN111672098A (en) | Virtual object marking method and device, electronic equipment and storage medium | |
CN206711600U (en) | The voice interactive system with emotive function based on reality environment | |
CN110223678A (en) | Audio recognition method and system | |
CN111191787B (en) | Training method and device of neural network for extracting speaker embedded features | |
CN108815845B (en) | The information processing method and device of human-computer interaction, computer equipment and readable medium | |
US20120149449A1 (en) | Apparatus and method for analyzing player's behavior pattern | |
Hamidia et al. | Voice interaction using Gaussian mixture models for augmented reality applications | |
Pavlakos et al. | Kinect-based multimodal gesture recognition using a two-pass fusion scheme | |
Magerko et al. | Digital improvisational theatre: party quirks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171020 |
|
RJ01 | Rejection of invention patent application after publication |