CN109727599A - The children amusement facility and control method of interactive voice based on internet communication - Google Patents
The children amusement facility and control method of interactive voice based on internet communication Download PDFInfo
- Publication number
- CN109727599A CN109727599A CN201711039195.0A CN201711039195A CN109727599A CN 109727599 A CN109727599 A CN 109727599A CN 201711039195 A CN201711039195 A CN 201711039195A CN 109727599 A CN109727599 A CN 109727599A
- Authority
- CN
- China
- Prior art keywords
- voice
- network server
- amusement facility
- facility
- character string
- 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.)
- Withdrawn
Links
Abstract
The present invention discloses the children amusement facility and control method of a kind of interactive voice based on internet communication, comprising: input voice: acquiring voice command signal by the voice-input device that facility carries；It uploads voice: the voice messaging of input is uploaded into network server by internet；Speech recognition conversion: network server carries out identification conversion to received voice, converts voice signals into character string；Order passback: the character string after conversion is returned to the control unit of amusement facility by network server；Semantics recognition: character string is compared control unit with local dictionary is stored in advance in, and determines corresponding execution unit and executes movement；Execute command result: control unit judges whether according to setting strategy can be according to instruction execution order, and executes judging result；As a result feed back: local loudspeaker return implementing result according to predetermined policy.The application is travelled implementation by voice control, is increased interacting for facility and children, is promoted the interest of facility.
Description
Technical field
The present invention relates to amusement facility and control methods, more particularly to the interactive voice based on internet communication
Children amusement facility and control method.
Background technique
The playing method of existing children amusement facility is single, and interactive inadequate, after children have played a period of time, interest is gradually
It reduces, as people require the playability of children amusement facility higher and higher, children's facility is to interactive direction.It is existing
Children amusement facility is there is rich shortage is linked up with user speech, and data processing is inflexible, and intelligence degree is low.
Summary of the invention
In order to overcome the problems of the prior art, the present invention provides a kind of amusement of children of interactive voice Internet-based
Facility and control method.
To achieve the above object, the present invention is realized according to following technical scheme:
A kind of control method of the children amusement facility of interactive voice based on internet communication of the invention, including it is as follows
Step:
It inputs voice: voice command signal is acquired by the voice-input device that facility carries；
It uploads voice: the voice messaging of input is uploaded into the network server by internet；
Speech recognition conversion: the network server carries out identification conversion to received voice, converts voice signals into
Character string；
Order passback: the character string after conversion is returned to the control unit of amusement facility by the network server；
Semantics recognition: character string is compared described control unit with local dictionary is stored in advance in, and determines and corresponds to
Execution unit and execute movement；
Execute command result: control unit judges whether according to setting strategy can be according to instruction execution order, and executes
Judging result.
As a result feed back: local loudspeaker return implementing result according to predetermined policy.
In above-mentioned technical proposal, speech recognition conversion specifically includes the network server and carries out voice to received voice
Feature information extraction and voice characteristics information analysis, voice characteristics information obtains two dimensional character matrix after extracting, by feature square
Battle array vector is converted into feature vector, carries out feature selecting after feature vector statistics, finally carries out tagsort, tested speech
Emotional category.
In above-mentioned technical proposal, it includes that speech characteristic parameter extracts that voice characteristics information, which extracts, special to the voice extracted
Sign carries out linear transformation dimensionality reduction, retains the characteristic with distinction, enhances characteristics of speech sounds later and reduces the interference of noise.
In above-mentioned technical proposal, voice characteristics information analysis includes time construction analysis, amplitude construction analysis, fundamental frequency construction
Analysis and formant structural analysis.
A kind of children amusement facility of interactive voice based on internet communication of the invention includes:
It inputs voice device: voice command signal is acquired by the voice-input device that facility carries；
It uploads voice device: the voice messaging of input is uploaded into network server by internet；
Speech recognition conversion module: the network server carries out identification conversion to received voice, and voice signal is turned
Change character string into；
Order passback module: the character string after conversion is returned to the control unit of amusement facility by the network server；
Semantic recognition device: character string is compared described control unit with local dictionary is stored in advance in, and determines
Corresponding execution unit and execute movement；
Execute command result device: control unit according to setting strategy judge whether can according to instruction execution order, and
Execute judging result.
As a result feedback device: local loudspeaker return implementing result according to predetermined policy.
In above-mentioned technical proposal, the voice characteristics information extraction module obtains two dimension to characteristics of speech sounds information extraction later
Eigenmatrix vector is converted into feature vector, carries out feature selecting after feature vector statistics, finally carry out special by eigenmatrix
Sign classification, the emotional category of tested speech.
In above-mentioned technical proposal, the voice characteristics information extraction module is extracted for speech characteristic parameter, to extracting
Phonetic feature carry out linear transformation dimensionality reduction, retain have distinction characteristic, later enhance characteristics of speech sounds and reduce make an uproar
The interference of sound.
In above-mentioned technical proposal, the voice characteristics information analysis module includes time construction analysis module, amplitude construction
Analysis module, fundamental frequency construction analysis module and formant structural analysis module.
Compared with prior art, the present invention having the following beneficial effects:
The solution have the advantages that: it is travelled implementation by voice control, increases interacting for facility and children, promoted
The interest of facility.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of showing for the control method of the children amusement facility of interactive voice based on internet communication of the invention
It is intended to.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.
Fig. 1 is a kind of control method of the children amusement facility of interactive voice based on internet communication of the invention, such as
Shown in Fig. 1, a kind of control method of the children amusement facility of interactive voice based on internet communication of the invention, including it is as follows
Step:
It inputs voice: voice command signal is acquired by the voice-input device that facility carries；
It uploads voice: the voice messaging of input is uploaded into the network server by internet；
Speech recognition conversion: the network server carries out identification conversion to received voice, converts voice signals into
Character string；
Order passback: the character string after conversion is returned to the control unit of amusement facility by the network server；
Semantics recognition: character string is compared described control unit with local dictionary is stored in advance in, and determines and corresponds to
Execution unit and execute movement；
Execute command result: control unit judges whether according to setting strategy can be according to instruction execution order, and executes
Judging result.
As a result feed back: local loudspeaker return implementing result according to predetermined policy.
Wherein, speech recognition conversion specifically includes the network server and mentions to received voice progress voice characteristics information
It takes and is analyzed with voice characteristics information, voice characteristics information obtains two dimensional character matrix after extracting, and eigenmatrix vector is converted
At feature vector, feature selecting is carried out after feature vector statistics, finally carries out tagsort, the emotional category of tested speech.
It includes that speech characteristic parameter extracts that voice characteristics information, which extracts, carries out linear transformation drop to the phonetic feature extracted
Dimension retains the characteristic with distinction, enhances characteristics of speech sounds later and reduces the interference of noise.
Voice characteristics information analysis includes time construction analysis, amplitude construction analysis, fundamental frequency construction analysis and formant
Structural analysis.The time of analysis phonetic feature is mainly focused on the difference of the time of giving orders or instructions of different voices, and the present invention calculates
The duration of each voice from start to end, further includes mute time, then with regard to the time duration of giving orders or instructions of voice
Frequency of averagely giving orders or instructions is analyzed and is compared.Amplitude construction analysis has stronger correlation with various voice messagings, mainly
Analysis comparison is carried out for amplitude average energy and dynamic range.Fundamental frequency construction analysis constructs the smooth base of voice signal first
Then frequency geometric locus analyzes the situation of change of the pitch contour curve of different phonetic, finds out different voice signals and respectively have
Some fundamental frequency construction features.Formant structural analysis finds out the power spectral envelope of sound channel first, then detects method by peak value and calculate
The frequency of each formant.
Accordingly, the children amusement facility of a kind of interactive voice based on internet communication of the invention, comprising:
It inputs voice device: voice command signal is acquired by the voice-input device that facility carries；
It uploads voice device: the voice messaging of input is uploaded into network server by internet；
Speech recognition conversion module: the network server carries out identification conversion to received voice, and voice signal is turned
Change character string into；
Order passback module: the character string after conversion is returned to the control unit of amusement facility by the network server；
Semantic recognition device: character string is compared described control unit with local dictionary is stored in advance in, and determines
Corresponding execution unit and execute movement；
Execute command result device: control unit according to setting strategy judge whether can according to instruction execution order, and
Execute judging result.
As a result feedback device: local loudspeaker return implementing result according to predetermined policy.
The voice characteristics information extraction module is to two dimensional character matrix is obtained after characteristics of speech sounds information extraction, by feature
Matrix-vector is converted into feature vector, carries out feature selecting after feature vector statistics, finally carries out tagsort, tested speech
Emotional category.
The voice characteristics information extraction module is extracted for speech characteristic parameter, carries out line to the phonetic feature extracted
Property transformation dimensionality reduction, retain the characteristic with distinction, enhance characteristics of speech sounds later and reduce the interference of noise.
The voice characteristics information analysis module includes time construction analysis module, amplitude construction analysis module, fundamental frequency structure
Make analysis module and formant structural analysis module.
The time of time construction analysis module is mainly focused on the difference of the time of giving orders or instructions of different voices, and the present invention calculates
The duration of each voice from start to end out, further includes mute time, then long with regard to the duration of giving orders or instructions of voice
Degree and frequency of averagely giving orders or instructions are analyzed and are compared.Amplitude construction analysis module has stronger related to various voice messagings
Property, analysis comparison is carried out mainly for amplitude average energy and dynamic range.Fundamental frequency construction analysis module constructs voice first
Then the pitch contour curve of signal smoothing analyzes the situation of change of the pitch contour curve of different phonetic, finds out different languages
The fundamental frequency construction feature that sound signal respectively has.Formant structural analysis module finds out the power spectral envelope of sound channel first, then leads to
Cross the frequency that peak value detection method calculates each formant.
In order to be suitble to the normal pickup in noisy external environment, facility can be equipped with individually control to voice input module
Key, only when pressing key pressing, voice input module pickup.The key can be machinery, be also possible to touch-induction-type.
Embodiment 1: for example, by taking amusement of children horse as an example.
Children say voice input module, " shake fastly fastly shake "；
The voice messaging passes to network server by the Internet communication module；
Network server converts voice signals into character string " shake fastly fastly shake "；
Character string is sent back to control module by network server；
Control module compares character string " shake fastly fastly shake " and local dictionary, obtains " shake fastly fastly shake "；Corresponding enforcement division
Part is motor, and execution movement is raising revolving speed 5%.
For control system according to preset strategy, acceleration mode can be continued by judging that local motor is in, and rev up 5%.
Local loudspeaker play the voice prestored: " listening yours, quicker ".
Embodiment 2: children say voice input module, " shake fastly fastly shake "；
The voice messaging passes to network server by the Internet communication module；
Due to speaking with a lisp, network server converts voice signals into character string " sting fastly fastly shake "；
Character string is sent back to amusement facility by network server；
Control module compares character string " sting fastly fastly shake " and local dictionary, obtains " sting fastly fastly shake " corresponding execution unit
For motor, execution movement is raising revolving speed 5%.
For control system according to preset strategy, acceleration mode can be continued by judging that local motor is in, and rev up 5%.
Local loudspeaker play the voice prestored: " listening yours, quicker ".
Embodiment 3: children say voice input module for another example, " shake fastly fastly shake "；
The voice messaging passes to network server by the Internet communication module；
Due to speaking with a lisp, network server converts voice signals into character string " sting fastly fastly shake "；
Character string is sent back to amusement facility by network server；
Control module compares character string " sting fastly fastly shake " and local dictionary, obtains " sting fastly fastly shake "；Corresponding enforcement division
Part is motor, and execution movement is raising revolving speed 5%.
For control system according to preset strategy, acceleration mode can not be continued by judging that local motor is in, and no longer be revved up.
Local loudspeaker play the voice prestored: " being dead tired, cannot be fast again ".
Embodiment 4: facility is other than motor for another example, and there are also each color lights；
Children say voice input module, " red light is bright "；
The voice messaging passes to network server by the Internet communication module；
Network server converts voice signals into character string " red light is bright "；
Character string is sent back to amusement facility by network server；
Control module compares character string " red light is bright " and local dictionary, obtains " red light is bright "；Corresponding enforcement division
Part is red LED lamp bead, and execution movement is to light.
Control system according to preset strategy, judge local red LED lamp bead be in can illuminating state, light red LED lamp
Pearl；
Local loudspeaker play the voice prestored: " red light is bright, beautiful ".
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (8)
1. a kind of control method of the children amusement facility of the interactive voice based on internet communication, which is characterized in that including such as
Lower step:
It inputs voice: voice command signal is acquired by the voice-input device that facility carries；
It uploads voice: the voice messaging of input is uploaded into network server by internet；
Speech recognition conversion: the network server carries out identification conversion to received voice, converts voice signals into character
String；
Order passback: the character string after conversion is returned to the control unit of amusement facility by the network server；
Semantics recognition: character string is compared described control unit with local dictionary is stored in advance in, and determines corresponding hold
Row component and execute movement；
Execute command result: control unit judges whether according to setting strategy can be according to instruction execution order, and executes judgement
As a result；
As a result feed back: local loudspeaker return implementing result according to predetermined policy.
2. a kind of controlling party of the children amusement facility of interactive voice based on internet communication according to claim 1
Method, which is characterized in that speech recognition conversion specifically includes the network server and carries out voice characteristics information to received voice
It extracts and voice characteristics information analysis, voice characteristics information obtains two dimensional character matrix after extracting, eigenmatrix vector is turned
It changes feature vector into, carries out feature selecting after feature vector statistics, finally carry out tagsort, the emotion class of tested speech
Not.
3. a kind of controlling party of the children amusement facility of interactive voice based on internet communication according to claim 2
Method, which is characterized in that it includes that speech characteristic parameter extracts that voice characteristics information, which extracts, is carried out to the phonetic feature extracted linear
Dimensionality reduction is converted, the characteristic with distinction is retained, enhance characteristics of speech sounds later and reduces the interference of noise.
4. a kind of controlling party of the children amusement facility of interactive voice based on internet communication according to claim 2
Method, which is characterized in that voice characteristics information analysis include time construction analysis, amplitude construction analysis, fundamental frequency construction analysis and
Formant structural analysis.
5. a kind of children amusement facility of the interactive voice based on internet communication characterized by comprising
It inputs voice device: voice command signal is acquired by the voice-input device that facility carries；
It uploads voice device: the voice messaging of input is uploaded into network server by internet；
Speech recognition conversion module: the network server carries out identification conversion to received voice, converts voice signals into
Character string；
Order passback module: the character string after conversion is returned to the control unit of amusement facility by the network server；
Semantic recognition device: character string is compared described control unit with local dictionary is stored in advance in, and determines and corresponds to
Execution unit and execute movement；
Execute command result device: control unit judges whether according to setting strategy can be according to instruction execution order, and executes
Judging result.
As a result feedback device: local loudspeaker return implementing result according to predetermined policy.
6. a kind of children amusement facility of interactive voice based on internet communication according to claim 5, feature exist
In the speech recognition conversion module includes voice characteristics information extraction module and voice characteristics information analysis module, institute's predicate
Eigenmatrix vector is converted by sound characteristic information extracting module to two dimensional character matrix is obtained after characteristics of speech sounds information extraction
Feature vector, feature vector statistics carry out feature selecting later, finally carry out tagsort, the emotional category of tested speech.
7. a kind of children amusement facility of interactive voice based on internet communication according to claim 6, feature exist
In the voice characteristics information extraction module is extracted for speech characteristic parameter, is linearly become to the phonetic feature extracted
Dimensionality reduction is changed, the characteristic with distinction is retained, enhance characteristics of speech sounds later and reduces the interference of noise.
8. a kind of controlling party of the children amusement facility of interactive voice based on internet communication according to claim 6
Method, which is characterized in that the voice characteristics information analysis module include time construction analysis module, amplitude construction analysis module,
Fundamental frequency construction analysis module and formant structural analysis module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711039195.0A CN109727599A (en) | 2017-10-31 | 2017-10-31 | The children amusement facility and control method of interactive voice based on internet communication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711039195.0A CN109727599A (en) | 2017-10-31 | 2017-10-31 | The children amusement facility and control method of interactive voice based on internet communication |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109727599A true CN109727599A (en) | 2019-05-07 |
Family
ID=66292668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711039195.0A Withdrawn CN109727599A (en) | 2017-10-31 | 2017-10-31 | The children amusement facility and control method of interactive voice based on internet communication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109727599A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113368507A (en) * | 2021-01-19 | 2021-09-10 | 福建技术师范学院 | Intelligent amusement system based on renewable energy and lithium battery power supply |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6341264B1 (en) * | 1999-02-25 | 2002-01-22 | Matsushita Electric Industrial Co., Ltd. | Adaptation system and method for E-commerce and V-commerce applications |
| CN102142253A (en) * | 2010-01-29 | 2011-08-03 | 富士通株式会社 | Voice emotion identification equipment and method |
| CN102298694A (en) * | 2011-06-21 | 2011-12-28 | 广东爱科数字科技有限公司 | Man-machine interaction identification system applied to remote information service |
| CN102831892A (en) * | 2012-09-07 | 2012-12-19 | 深圳市信利康电子有限公司 | Toy control method and system based on internet voice interaction |
| CN102831891A (en) * | 2011-06-13 | 2012-12-19 | 富士通株式会社 | Processing method and system for voice data |
| US20140214419A1 (en) * | 2013-01-29 | 2014-07-31 | Tencent Technology (Shenzhen) Company Limited | Method and system for automatic speech recognition |
| CN106683662A (en) * | 2015-11-10 | 2017-05-17 | 中国电信股份有限公司 | Speech recognition method and device |
| CN107123420A (en) * | 2016-11-10 | 2017-09-01 | 厦门创材健康科技有限公司 | Voice recognition system and interaction method thereof |
-
2017
- 2017-10-31 CN CN201711039195.0A patent/CN109727599A/en not_active Withdrawn
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6341264B1 (en) * | 1999-02-25 | 2002-01-22 | Matsushita Electric Industrial Co., Ltd. | Adaptation system and method for E-commerce and V-commerce applications |
| CN102142253A (en) * | 2010-01-29 | 2011-08-03 | 富士通株式会社 | Voice emotion identification equipment and method |
| CN102831891A (en) * | 2011-06-13 | 2012-12-19 | 富士通株式会社 | Processing method and system for voice data |
| CN102298694A (en) * | 2011-06-21 | 2011-12-28 | 广东爱科数字科技有限公司 | Man-machine interaction identification system applied to remote information service |
| CN102831892A (en) * | 2012-09-07 | 2012-12-19 | 深圳市信利康电子有限公司 | Toy control method and system based on internet voice interaction |
| US20140214419A1 (en) * | 2013-01-29 | 2014-07-31 | Tencent Technology (Shenzhen) Company Limited | Method and system for automatic speech recognition |
| CN106683662A (en) * | 2015-11-10 | 2017-05-17 | 中国电信股份有限公司 | Speech recognition method and device |
| CN107123420A (en) * | 2016-11-10 | 2017-09-01 | 厦门创材健康科技有限公司 | Voice recognition system and interaction method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 宋凌: "基于主成分分析的说话人特征变换研究", 《电子技术与软件工程》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113368507A (en) * | 2021-01-19 | 2021-09-10 | 福建技术师范学院 | Intelligent amusement system based on renewable energy and lithium battery power supply |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11908472B1 (en) | Connected accessory for a voice-controlled device | |
| Lech et al. | Real-time speech emotion recognition using a pre-trained image classification network: Effects of bandwidth reduction and companding | |
| US11551685B2 (en) | Device-directed utterance detection | |
| CN110827821B (en) | Voice interaction device and method and computer readable storage medium | |
| US11594224B2 (en) | Voice user interface for intervening in conversation of at least one user by adjusting two different thresholds | |
| CN109189980A (en) | The method and electronic equipment of interactive voice are carried out with user | |
| Kandali et al. | Emotion recognition from Assamese speeches using MFCC features and GMM classifier | |
| US10789948B1 (en) | Accessory for a voice controlled device for output of supplementary content | |
| CN106548775B (en) | Voice recognition method and system | |
| US10079021B1 (en) | Low latency audio interface | |
| CN104538043A (en) | Real-time emotion reminder for call | |
| US11393473B1 (en) | Device arbitration using audio characteristics | |
| US10148912B1 (en) | User interface for communications systems | |
| CN109887511A (en) | A kind of voice wake-up optimization method based on cascade DNN | |
| CN111192585A (en) | Music playing control system, control method and intelligent household appliance | |
| CN105788596A (en) | Speech recognition television control method and system | |
| CN111145763A (en) | GRU-based voice recognition method and system in audio | |
| CN109994106A (en) | A kind of method of speech processing and equipment | |
| US20240029743A1 (en) | Intermediate data for inter-device speech processing | |
| CN110232924A (en) | Vehicle-mounted voice management method, device, vehicle and storage medium | |
| CN110232928B (en) | Text-independent speaker verification method and device | |
| CN114283820A (en) | Multi-character voice interaction method, electronic equipment and storage medium | |
| KR20190032557A (en) | Voice-based communication | |
| CN109727599A (en) | The children amusement facility and control method of interactive voice based on internet communication | |
| US11769491B1 (en) | Performing utterance detection using convolution |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190507 |