CN204134197U - Intelligent toy system - Google Patents
Intelligent toy system Download PDFInfo
- Publication number
- CN204134197U CN204134197U CN201420442729.XU CN201420442729U CN204134197U CN 204134197 U CN204134197 U CN 204134197U CN 201420442729 U CN201420442729 U CN 201420442729U CN 204134197 U CN204134197 U CN 204134197U
- Authority
- CN
- China
- Prior art keywords
- voice
- control device
- toy system
- intelligent toy
- speech recognition
- 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.)
- Expired - Fee Related
Links
- 238000004891 communication Methods 0.000 claims abstract description 15
- 230000013011 mating Effects 0.000 claims abstract description 5
- 230000004044 response Effects 0.000 claims description 11
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000000034 method Methods 0.000 description 2
- 238000000465 moulding Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
Landscapes
- Toys (AREA)
Abstract
A kind of intelligent toy system, comprise: the toy being configured with sound pick-up, loudspeaker and communication interface, for voice signal being converted to the speech recognition device of word, voice server, controller, voice server comprises index and the keyword match device of sound bank, key word library, association voice and keyword; Controller is connected with speech recognition device and voice server respectively by wireless network, and be connected with the communication interface of described toy, controller comprises: the voice transfer for being gathered by described sound pick-up carries out the first control device identified to speech recognition device, for voice identification result being transferred to the second control device that voice server carries out mating, and the 3rd control device for will the voice transfer that finds to described loudspeaker mated carry out playing.The Intelligent dialogue that this intelligent toy system can carry out not limiting by content with people is chatted.
Description
Technical field
The utility model relates to toy, particularly a kind of intelligent toy system.
Background technology
The existing toy with phonetic function stores music or voice by built-in chip, can send voice or play music, add attraction to a certain extent when toy is used.But these toys existing all can only play fixing music and voice by fixed mode, and intelligence degree is lower.
Utility model content
The purpose of this utility model is to provide a kind of intelligent toy system, and the Intelligent dialogue that this intelligent toy system can carry out not limiting by content with people is chatted.
For reaching above-mentioned purpose, a kind of intelligent toy system that the utility model provides comprises:
Toy, is configured with sound pick-up, loudspeaker and communication interface;
For voice signal being converted to the speech recognition device of word;
Voice server, it comprises index and the keyword match device of sound bank, key word library, association voice and keyword; And
Controller, it is connected with speech recognition device and voice server respectively by wireless network, and be connected with the communication interface of described toy, and comprise: the voice transfer for being gathered by described sound pick-up carries out the first control device identified to speech recognition device, for voice identification result being transferred to the second control device that voice server carries out mating, and the 3rd control device for will the voice transfer that finds to described loudspeaker mated carry out playing.
In above-mentioned intelligent toy system, preferably, this intelligent toy system also comprises for the VODER according to word synthesis response voice, described controller is connected with this VODER by wireless network, and described controller also comprises the 4th control device obtaining response voice for voice identification result being transferred to when receiving the matching error signal that voice server returns this VODER.
In above-mentioned intelligent toy system, preferably, described VODER comprises search engine and text-to-speech device, and described search engine is used in corresponding database, searching out the text the highest with the input text degree of correlation and being transferred to described text-to-speech device.
In above-mentioned intelligent toy system, preferably, the communication interface of described toy is bluetooth or wireline interface.
In above-mentioned intelligent toy system, preferably, institute's speech recognizer is the speech recognition device based on cloud platform.
In above-mentioned intelligent toy system, preferably, described controller is smart mobile phone, and first to fourth control device in controller is by software simulating.
This intelligent toy system gathers voice by the sound pick-up in toy, and then pass through the pronunciation of voice recognizing machine identification people, and recognition result is carried out keyword match and find out the response voice corresponding to this pronunciation from speech database, play finally by the loudspeaker in toy, thus toy can be achieved and people's Intelligent dialogue is chatted.Visible, compared to existing voice toy, the utility model intelligent toy can be simulated true man and be engaged in the dialogue, and has more hommization and intellectuality.
Accompanying drawing explanation
Fig. 1 is the structured flowchart of some embodiment intelligent toy systems;
Fig. 2 is the theory diagram of some embodiment intelligent toy systems.
Detailed description of the invention
The utility model is further illustrated below in conjunction with drawings and Examples.
With reference to Fig. 1, this intelligent toy system comprises: toy 10, speech recognition device 20, voice server 30, controller 40, VODER 60.
Toy 10 is configured with sound pick-up 11, loudspeaker 12 and communication interface 13.Voice collecting can be carried out by sound pick-up 11.Voice can be play by loudspeaker 12.Communication interface 13 is then for sending and received speech signal, and communication interface 13 can adopt wireline interface, also can adopt wave point.In preferred embodiment, communication interface 13 adopts bluetooth.Moulding, size etc. as toy 10 then do not limit, and can adopt various moulding.
Speech recognition device 20 is for being converted to word by voice signal.In the preferred embodiment, speech recognition device 20 adopts the speech recognition device based on cloud platform, such as University of Science and Technology news scud platform.To speech recognition itself, belong to common practise, do not belong to summary of the invention of the present utility model, therefore repeat no more.
Voice server 30 comprises index 33 and the keyword match device 34 of sound bank 31, key word library 32, association voice and keyword.A large amount of voice are stored in sound bank 31.Key word library 32 stores a large amount of keywords.Keyword in voice in sound bank 31 and key word library 32 is mapped by index 33.Keyword match device 34, for being mated with the keyword in key word library 32 by the word received, finds out the keyword that the word of this input is corresponding, and then finds out corresponding voice by index 33.
VODER 60 is for replying voice according to word synthesis.In some preferred embodiment, VODER 60 comprises search engine and text-to-speech device (TextToSpeech, TTS), described search engine is used in corresponding database, searching out the File Transfer the highest with the input text degree of correlation to described text-to-speech device.The text-converted the highest with the input text degree of correlation that search engine finds by text-to-speech device becomes received pronunciation, as response voice.Here the corresponding database said can be the self-contained database of VODER, also can be the database connected by network.VODER 60 can adopt the VODER based on cloud platform, such as University of Science and Technology news scud platform.
Controller 40 is connected with speech recognition device 20, voice server 30 and VODER 60 respectively by wireless network 50, is also connected with the communication interface 13 of toy 10 with Time Controller 40.Controller 40 comprises: first control device 41, second control device 42, the 3rd control device 43 and the 4th control device 44.First control device 41 identifies to speech recognition device 20 for the voice transfer gathered by the sound pick-up 11 in toy 10.Second control device 42 mates for voice identification result (word) is transferred to voice server 30, finds corresponding voice (namely replying voice) and the corresponding text of voice.3rd control device 43 is for playing mating the voice transfer found to the loudspeaker 12 in toy 10.4th control device 44 obtains response voice for voice identification result (word) being transferred to when receiving the matching error signal that voice server returns this VODER 60.First to fourth above-mentioned control device 41,42,43,44 respectively by realizations such as a microprocessor (CPU) or circuit, also can realize with same microprocessor, can also pass through software simulating.In certain embodiments, controller 40 adopts smart mobile phone, first to fourth control device in controller 40 by software, as realizations such as APP (i.e. the abbreviation of Application).
This intelligent toy system can be simulated true man and be engaged in the dialogue, and has more hommization and intellectuality.Adopt smart mobile phone for controller 40 below, the course of work of this intelligent toy system is described.With reference to Fig. 1,2, this course of work comprises the following steps:
Sound pick-up 11 in toy 10 gathers voice, and passes through communication interface 13 by the voice transfer of collection to the APP (namely realizing the application software of above-mentioned first to fourth control device 41,42,43,44) in smart mobile phone;
This voice transfer is identified to speech recognition device 20 by wireless network 50 by this APP in smart mobile phone, and recognition result (word) is returned to this APP in smart mobile phone by wireless network 50;
Recognition result (word) is transferred to voice server 30 by wireless network 50 and mates by this APP in smart mobile phone.Matching process comprises: first by voice identification result (word) and the keyword match in key word library 32, find out the keyword matched with this voice identification result, then the voice with this keyword association are found by index 33 from sound bank 31, as the voice (namely reply voice) corresponding with this voice identification result, such as: voice identification result is word " fail to see what Lushan Mountain really looks like ", the keyword mated in the key word library obtained is word " fail to see what Lushan Mountain really looks like ", the corresponding voice (namely replying voice) found from sound bank are the pronunciation on " edge is in this mountain ".Due to the polytropy of the restriction of sound bank and the voice of people, possibly cannot find the keyword matched with voice identification result sometimes, namely occur the situation of matching error;
When the match is successful, the response voice found are transferred to this APP in smart mobile phone by voice server 30 by wireless network 50, this response voice transfer is play to the loudspeaker 12 in toy 10 by this APP in smart mobile phone, thus realize dialogue chat;
When mating unsuccessful, matching error is returned to this APP in smart mobile phone by voice server 30, voice identification result (word) is transferred to VODER 60 by this APP in smart mobile phone, standard response voice are obtained (such as by VODER 60, when pronunciation recognition result is word " fail to see what Lushan Mountain really looks like ", the response voice obtained by VODER 60 may be " describing due to still not comprehensive to the understanding of objective things ... "), the loudspeaker 12 be then transferred in toy 10 are play.
In certain embodiments, unsuccessful situation can also be mated to voice server 30 and disregard, namely not reply.
This intelligent toy system at least has the following advantages:
1, utilize the communication interface such as bluetooth, line traffic control, traditional sounding toy is become to network and carries out the intelligent toy of voice-enabled chat;
2, increasing the special voice server of toy based on cloud platform speech recognition device basis, by the controller based on mobile terminal, install the chat APP software that toy is special, networking realizes this process of voice-enabled chat.
Below in conjunction with specific embodiments the utility model has been done and compared detailed description; but these specific descriptions should not be construed as the restriction to the utility model protection domain, those skilled in the art can also make other modification according to explanation of the present utility model or be equal to replacement etc.Protection domain of the present utility model is as the criterion with claims.
Claims (6)
1. an intelligent toy system, is characterized in that, this intelligent toy system comprises:
Toy (10), is configured with sound pick-up (11), loudspeaker (12) and communication interface (13);
For voice signal being converted to the speech recognition device (20) of word;
Voice server (30), it comprises index (33) and the keyword match device (34) of sound bank (31), key word library (32), association voice and keyword; And
Controller (40), it is connected with speech recognition device and voice server respectively by wireless network (50), and be connected with the communication interface of described toy, and comprise: voice transfer to the speech recognition device for being gathered by described sound pick-up carries out the first control device (41) identified, for voice identification result being transferred to the second control device (42) that voice server carries out mating, and the 3rd control device (43) for will the voice transfer that finds to described loudspeaker mated carry out playing.
2. intelligent toy system as claimed in claim 1, it is characterized in that, this intelligent toy system also comprises for the VODER (60) according to word synthesis response voice, described controller (40) is connected with this VODER by wireless network, and described controller also comprises the 4th control device (44) obtaining response voice for voice identification result being transferred to when receiving the matching error signal that voice server (30) returns this VODER.
3. intelligent toy system as claimed in claim 2, it is characterized in that, described VODER (60) comprises search engine and text-to-speech device, and described search engine is used in corresponding database, searching out the File Transfer the highest with the input text degree of correlation to described text-to-speech device.
4. intelligent toy system as claimed in claim 1, it is characterized in that, the communication interface of described toy is bluetooth.
5. intelligent toy system as claimed in claim 1, it is characterized in that, institute's speech recognizer (20) is the speech recognition device based on cloud platform.
6. intelligent toy system as claimed in claim 2, it is characterized in that, described controller (40) is smart mobile phone, and first to fourth control device in controller is by software simulating.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420442729.XU CN204134197U (en) | 2014-08-07 | 2014-08-07 | Intelligent toy system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420442729.XU CN204134197U (en) | 2014-08-07 | 2014-08-07 | Intelligent toy system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN204134197U true CN204134197U (en) | 2015-02-04 |
Family
ID=52410916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201420442729.XU Expired - Fee Related CN204134197U (en) | 2014-08-07 | 2014-08-07 | Intelligent toy system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN204134197U (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104867363A (en) * | 2015-05-19 | 2015-08-26 | 苏州鱼骨头电子科技有限公司 | Voice on demand system for children |
| CN105355204A (en) * | 2015-11-24 | 2016-02-24 | 广州市海葱科技有限公司 | System and method for voice recognition based on cloud computation |
| CN105597337A (en) * | 2016-03-14 | 2016-05-25 | 深圳市艾塔文化科技有限公司 | Method and system of data interaction between toys |
| CN105895134A (en) * | 2016-05-10 | 2016-08-24 | 安徽声讯信息技术有限公司 | Recording device with remote recording and cloud transliteration control functions and implementation method thereof |
| CN106128457A (en) * | 2016-08-29 | 2016-11-16 | 昆山邦泰汽车零部件制造有限公司 | A kind of control method talking with robot |
| CN106297804A (en) * | 2016-09-06 | 2017-01-04 | 成都市极米科技有限公司 | The voice interactive method of projector and system |
| CN109036402A (en) * | 2018-07-18 | 2018-12-18 | 深圳市本牛科技有限责任公司 | Digital speech VOD system and its operating method and the device for using the system |
| CN109587664A (en) * | 2018-11-14 | 2019-04-05 | 深圳市芯中芯科技有限公司 | A kind of voice dialing system of edge calculations in conjunction with cloud computing |
| CN110152314A (en) * | 2018-02-13 | 2019-08-23 | 卡西欧计算机株式会社 | Session output system, session output server, session output method, and storage medium |
| CN111145602A (en) * | 2020-01-20 | 2020-05-12 | 浙江酷哥创客教育科技有限公司 | Programmable voice intelligent teaching aid |
| TWI778023B (en) * | 2017-02-24 | 2022-09-21 | 日商葳葳維爾股份有限公司 | Control device, control method, information processing device, information processing method and program |
-
2014
- 2014-08-07 CN CN201420442729.XU patent/CN204134197U/en not_active Expired - Fee Related
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104867363A (en) * | 2015-05-19 | 2015-08-26 | 苏州鱼骨头电子科技有限公司 | Voice on demand system for children |
| CN105355204A (en) * | 2015-11-24 | 2016-02-24 | 广州市海葱科技有限公司 | System and method for voice recognition based on cloud computation |
| CN105597337B (en) * | 2016-03-14 | 2018-08-14 | 深圳市艾塔文化科技有限公司 | The method and system of data interaction between a kind of toy |
| CN105597337A (en) * | 2016-03-14 | 2016-05-25 | 深圳市艾塔文化科技有限公司 | Method and system of data interaction between toys |
| CN105895134A (en) * | 2016-05-10 | 2016-08-24 | 安徽声讯信息技术有限公司 | Recording device with remote recording and cloud transliteration control functions and implementation method thereof |
| CN106128457A (en) * | 2016-08-29 | 2016-11-16 | 昆山邦泰汽车零部件制造有限公司 | A kind of control method talking with robot |
| CN106297804A (en) * | 2016-09-06 | 2017-01-04 | 成都市极米科技有限公司 | The voice interactive method of projector and system |
| CN106297804B (en) * | 2016-09-06 | 2020-10-20 | 成都极米科技股份有限公司 | Voice interaction method and system of projector |
| TWI778023B (en) * | 2017-02-24 | 2022-09-21 | 日商葳葳維爾股份有限公司 | Control device, control method, information processing device, information processing method and program |
| CN110152314A (en) * | 2018-02-13 | 2019-08-23 | 卡西欧计算机株式会社 | Session output system, session output server, session output method, and storage medium |
| CN109036402A (en) * | 2018-07-18 | 2018-12-18 | 深圳市本牛科技有限责任公司 | Digital speech VOD system and its operating method and the device for using the system |
| CN109587664A (en) * | 2018-11-14 | 2019-04-05 | 深圳市芯中芯科技有限公司 | A kind of voice dialing system of edge calculations in conjunction with cloud computing |
| CN111145602A (en) * | 2020-01-20 | 2020-05-12 | 浙江酷哥创客教育科技有限公司 | Programmable voice intelligent teaching aid |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN204134197U (en) | Intelligent toy system | |
| KR102205371B1 (en) | Individualized hotword detection models | |
| CN108694940B (en) | Voice recognition method and device and electronic equipment | |
| KR102281178B1 (en) | Method and apparatus for recognizing multi-level speech | |
| US20190088262A1 (en) | Method and apparatus for pushing information | |
| CN110111775A (en) | A kind of Streaming voice recognition methods, device, equipment and storage medium | |
| US9626962B2 (en) | Method and apparatus for recognizing speech, and method and apparatus for generating noise-speech recognition model | |
| CN101599270A (en) | Voice server and voice control method | |
| CN107644638A (en) | Audio recognition method, device, terminal and computer-readable recording medium | |
| KR20190021338A (en) | Subsequent voice query prediction | |
| WO2008083175A3 (en) | On a mobile device tracking use of search results delivered to the mobile device | |
| WO2018022085A1 (en) | Identification of preferred communication devices | |
| KR20170030387A (en) | User-based language model generating apparatus, method and voice recognition apparatus | |
| CN103514882B (en) | A kind of audio recognition method and system | |
| CN110349575A (en) | Method, apparatus, electronic equipment and the storage medium of speech recognition | |
| CN108877809A (en) | A kind of speaker's audio recognition method and device | |
| CN111261151A (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN104601202A (en) | Method and terminal for realizing file search based on Bluetooth technology as well as Bluetooth device | |
| WO2014173325A1 (en) | Gutturophony recognition method and device | |
| KR20240115216A (en) | Method and apparatus for speech signal processing | |
| CN103281446A (en) | Voice short message sending system and voice short message sending method | |
| CN112735381B (en) | Model updating method and device | |
| KR20230075386A (en) | Method and apparatus for speech signal processing | |
| WO2016027909A1 (en) | Data structure, interactive voice response device, and electronic device | |
| KR101326262B1 (en) | Speech recognition device and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150204 Termination date: 20160807 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |