CN100501834C - Toy sound-control device and its language interaction and control method - Google Patents
Toy sound-control device and its language interaction and control method Download PDFInfo
- Publication number
- CN100501834C CN100501834C CNB2005100326670A CN200510032667A CN100501834C CN 100501834 C CN100501834 C CN 100501834C CN B2005100326670 A CNB2005100326670 A CN B2005100326670A CN 200510032667 A CN200510032667 A CN 200510032667A CN 100501834 C CN100501834 C CN 100501834C
- Authority
- CN
- China
- Prior art keywords
- module
- sound
- control
- toy
- phonetic synthesis
- 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
Images
Landscapes
- Toys (AREA)
Abstract
The present invention provides a voice-operated device for toy. It comprises pick-up module and playback module which are respectively connected with main control circuit board, and said main control circuit board includes control module, speech identification module, speech synthesizing module, model and rule base module, A/D converter module, A/D converter module, preamplifier module and power amplifier module, the control module is respectively connected with computer and excution module by means of input interface module and output interface module. Said device also can implement speech interacting and control method and program updation method.
Description
Technical field
The present invention relates to the voice-control toy technical field, specifically be meant a kind of toy sound-control device and interactive voice thereof and control method.
Background technology
Along with improving constantly of living standard, the kind of toy is more and more abundanter, and people are also more and more higher to the requirement of toy.Traditional toy mainly attracts children by aspects such as profile, color, sound, intelligence exercises, and the overwhelming majority needs " to take " and object for appreciation with hand, for example building blocks, rag baby, toy car or the like, and need be operated by hand.These toys can't " listen " understand and " answers " user in a minute, children are when using them, can only carry out self the one-side operation and the imagination by children, be difficult to obtain the sensation of carrying out " interchange " with own loved toy (toy that particularly personalizes, as rag baby etc.).In recent years, the function of all having added acoustic control or sounding in many toys, make them can be to some reactions of sound generating of people, if can walk towards the direction of sound, or after certain operation, we can say some words or send some sound etc., but the shortcoming of this type toy is at present: (1) function is simple, and existing sounding or voice-control toy still can't be distinguished the content of speaking, sensation from " interchange " also has very big distance, and is interesting low; (2) toy service regeulations and programme content can't upgrade, existing toy is after completing, just can't change the rule of its use, toy as some meeting sounding can only iterate same a few words after completing, grown service time and allowed the people feel dull easily, be difficult to satisfy children's curiosity, anti-object for appreciation is low.
Summary of the invention
The shortcoming that the objective of the invention is to overcome above-mentioned prior art provides a kind of interest, anti-object for appreciation height with not enough, can carry out toy sound-control device and the interactive voice and the control method of interactive voice and control and program updating.
Purpose of the present invention is achieved through the following technical solutions: this toy sound-control device comprises main control board, pickup module, playback module, described pickup module, playback module is connected with main control board respectively, it is characterized in that: described main control board comprises control module, sound identification module, the phonetic synthesis module, model and rule base module, the A/D modular converter, the D/A modular converter, pre-amplifying module, power amplifier module, described control module respectively with sound identification module, the phonetic synthesis module, model is connected with the rule base module, described sound identification module, the phonetic synthesis module is respectively by A/D modular converter and pre-amplifying module, D/A modular converter and power amplifier module and pickup module, playback module connects, and sound identification module, the phonetic synthesis module is connected with the rule base module with model simultaneously, and described control module is also passed through input interface module respectively, output interface module and computing machine, execution module connects.
For realizing the present invention better, described control module, sound identification module, phonetic synthesis module are integrated by a microprocessor.
Described pickup module can be a microphone.
Described playback module can be a loudspeaker.
Described execution module can be light, display screen or the gearing of toy.
Described control module, sound identification module, phonetic synthesis module also can be independently control chip, voice recognition chip, chipspeech separately, described model and rule base module can be storeies, described input interface module, output interface module can be conventional IO interfaces, described A/D modular converter and D/A modular converter can be A/D converter and D/A converter, described pre-amplifying module can be a pre-amplification circuit, and described power amplifier module can be a power amplifier.
The software section of described model and rule base module, promptly model and rule base comprise speech recognition modeling storehouse, phonetic synthesis model bank, output control signal storehouse, rule base.Described speech recognition modeling storehouse comprises all makes the model of cognition that this device can aitiogenic vocabulary, described phonetic synthesis model bank comprises all synthetic models that make the voice that this device can produce, described output control signal storehouse comprises the control signal that all can produce this device, and described rule base comprises all speech recognition modelings and phonetic synthesis model, exports the mapping ruler between the control signal.
Toy sound-control device of the present invention realizes that the method for interactive voice and control comprises:
(1) by described pickup module sound wave is converted to the sound electric signal of simulation, after pre-amplifying module amplifies, is sent to described A/D modular converter;
(2) described A/D modular converter is sampled to the sound electric signal of simulation and is quantized, and is converted to digital signal and sends into described sound identification module;
(3) described sound identification module carries out detection and Identification to input signal in real time, as the vocabulary in the speech recognition modeling storehouse as described in comprising in the input signal, then recognition result is delivered to described control module, otherwise continues input signal is detected;
(4) after described control module is received the recognition result that sound identification module provides, according to response rule predetermined in the rule base, to described output interface module output control signal required, that pre-define in the described output control signal storehouse, and notify described phonetic synthesis module to synthesize required voice;
(5) described phonetic synthesis module is utilized the synthetic required voice signal of speech recognition modeling in the described speech recognition modeling storehouse, and is delivered to described D/A modular converter according to the requirement of described control module;
(6) utilize described D/A modular converter that the audio digital signals of phonetic synthesis module output is converted to the voice telecommunication number of simulation, and play the voice signal of this simulation by described power amplifier module and playback module.
Toy sound-control device of the present invention realizes that the method for program updating comprises:
(1) whether the continuous input interface module that detects of this device is connected with computing machine, is connected with computing machine if detect input interface module, then stops all operations, enters the program updating state;
(2) this device is when the program updating state, by downloaded more new model and rule base;
(3) download when finishing model and rule base, and when computing machine disconnected with input interface module, this device recovery normal operating conditions was utilized new model and rule base realization interactive voice and control.
The present invention compared with prior art has following advantage and beneficial effect:
(1) interesting strong, this device can allow to be played the prodigiosin resolution and responds speaking of user, creates the sensation of more real personification, makes toy operation more convenient, has more interest.
(2) can repeat to upgrade, this device can pass through downloaded more new model and rule base, allows same toy have different speak content and reactive mode, has increased the anti-object for appreciation of toy.
(3) portability, this device can be transplanted to it in dissimilar voice-control toys easily by suitable vocabulary and rule base are set.
(4) adjustable, this device can be by adjusting the phonetic synthesis module some parameter (as fundamental frequency etc.), the synthetic easily sound (as male voice, female voice, child's voice etc.) with different characteristics is convenient to be applied in the different toys, or realizes the different effects of speaking in same toy.
Description of drawings
Fig. 1 is the circuit block diagram of toy sound-control device of the present invention.
Fig. 2 and 3 is circuit theory diagrams of toy sound-control device of the present invention.
Fig. 4 is the mounting structure figure of toy sound-control device of the present invention.
Fig. 5 is the workflow diagram of toy sound-control device of the present invention.
Embodiment
Below in conjunction with embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are not limited thereto.
As shown in Figure 1, this toy sound-control device comprises main control board 1, pickup module 2, playback module 3, pickup module 2, playback module 3 is connected with main control board 1 respectively, main control board 1 comprises control module 4, sound identification module 5, phonetic synthesis module 6, model and rule base module 7, A/D modular converter 8, D/A modular converter 9, input interface module 10, output interface module 11, pre-amplifying module 12, power amplifier module 13, control module 4 respectively with sound identification module 5, phonetic synthesis module 6, model is connected with rule base module 7, sound identification module 5, phonetic synthesis module 6 is respectively by A/D modular converter 8 and pre-amplifying module 12, D/A modular converter 9 and power amplifier module 13 and pickup module 2, playback module 3 connects, and sound identification module 5, phonetic synthesis module 6 is connected with rule base module 7 with model simultaneously, and control module 4 is also respectively by input interface module 10, output interface module 11 and computing machine 14, execution module 15 connects.Wherein the pickup module 2 of this toy sound-control device is selected microphone for use, and playback module 3 is selected loudspeaker for use, and execution module 15 can be light, display screen or the gearing of toy.
Shown in Fig. 2 and 3, the control module 4 of this toy sound-control device, sound identification module 5, phonetic synthesis module 6 is the microprocessors that three are combined into one, be dsp chip TMS320F2812, model and rule base module 7 are made of the FLASH storer that carries in the TMS320F2812 sheet, A/D modular converter 8 is made of jointly ADC that carries in the TMS320F2812 sheet and the outer low-pass filter circuit of sheet, D/A modular converter 9 is made of jointly the low-pass filter circuit outside pwm circuit in the TMS320F2812 sheet and the sheet, input interface module 10, output interface module 11 adopts the IO mouth that provides in the TMS320F2812 sheet to realize, pre-amplifying module 12 is made of pre-amplification circuit, power amplifier 13 is made of power amplifier, pickup module 2 adopts microphone, and playback module adopts loudspeaker.
As shown in Figure 4, when on a toy dog, this toy sound-control device being installed, the main control board 1 that will comprise dsp chip TMS320F2812, pre-amplification circuit, power amplifier, low-pass filter circuit places in the toy dog shell, microphone and loudspeaker are placed on respectively on the head and trunk of toy dog, and link to each other with power amplifier by pre-amplification circuit on signal wire and the main control board 1; One computer interface is set on the toy dog shell, and the IO mouth by TMS320F2812 on signal wire and the main control board 1 links to each other; Enclosure includes the gearing of parts such as toy dog four limbs, head, tail, and another IO mouth of TMS320F2812 provides control signal for this gearing on the main control board 1.
This toy sound-control device is realized the purpose of interactive voice and control and program updating by software control, and Fig. 5 has provided the workflow of this toy sound-control device, as shown in Figure 5:
After start powers on, at first carry out initial work, enter the master routine circulation then.
In the master routine circulation, whether at first detect input interface module is connected with computing machine, when detecting input interface module and link to each other with computing machine, promptly enter the program updating state, stop all normal operations this moment, model and rule base upgraded by computing machine by the user, after renewal finishes, the user disconnects computing machine and input interface module, and the system recovery normal operating conditions utilizes new model and rule base to carry out interactive voice and control with the user.Do not link to each other with computing machine if do not detect input interface module, wait for that then the input block is full after, enter in the sound identification module of soft realization.
In sound identification module, adopt following steps to come input signal is carried out detection and Identification:
(1) the end-point detection technology in the employing speech recognition detects in the input signal whether comprise voice.Comprise voice if detect input signal, then find out and note the starting point and the terminal point of this section voice; If not voice, then get back to the master routine round-robin and begin, wait for new data input.
(2) adopt speech recognition and refuse the knowledge technology, the voice segments that step (1) is noted is compared with the speech model in the speech recognition modeling storehouse, if this section voice are complementary with certain model wherein, then this section voice are that system can discern vocabulary, write down the sequence number of this model this moment, and recognition result is delivered to control module; If this section voice and all models all do not match, then this section voice are not that system can discern vocabulary, get back to the master routine round-robin and begin to continue to carry out, and wait for new data input.In the speech recognition modeling storehouse, speech recognition modeling adopts
Form store.
The control module of soft realization adopts following steps to determine output control signal and required synthetic voice after receiving the speech recognition modeling sequence number that sound identification module provides:
(1) in rule base, searches corresponding response rule according to the recognition result of sound identification module.Rule base is a record speech recognition modeling sequence number and phonetic synthesis model sequence number, exports the table that shines upon between the control signal sequence number, and its form is:
The speech recognition modeling sequence number of for example representing the toy name is 1, and the phonetic synthesis model sequence number of its reaction voice " tearful " is 3, and the output control signal sequence number of its reaction action " crust of wagging the tail " is 7, and then the form of rule list is
When being the toy name, be 1 but sound identification module obtains the speech recognition modeling sequence number, find corresponding phonetic synthesis model sequence number by rule list and be respectively 3 and 7 with output control signal sequence number.
(2) according to the output control signal sequence number of gained, in output control signal storehouse, find corresponding output control signal, and this signal is outputed to output interface module.In the output control signal storehouse, the output control signal adopts following form to store:
(3) the synthetic speech sequence number that obtains is delivered to the phonetic synthesis module of soft realization.
In the phonetic synthesis module, adopt the synthetic required voice of following steps:
(1) the phonetic synthesis model sequence number that provides according to control module is searched corresponding phonetic synthesis model in the phonetic synthesis model bank.In the phonetic synthesis model bank, the phonetic synthesis model adopts
Form store.
(2) utilize speech synthesis technique, synthetic required voice, and export D/A converter to.
After finishing these work, get back to the master routine circulation and begin to re-execute.
As mentioned above, can realize the present invention preferably.
Claims (6)
1, a kind of toy sound-control device comprises main control board, pickup module, playback module, described pickup module, playback module is connected with main control board respectively, it is characterized in that: described main control board comprises control module, sound identification module, the phonetic synthesis module, model and rule base module, the A/D modular converter, the D/A modular converter, pre-amplifying module, power amplifier module, described control module respectively with sound identification module, the phonetic synthesis module, model is connected with the rule base module, described sound identification module, the phonetic synthesis module is respectively by A/D modular converter and pre-amplifying module, D/A modular converter and power amplifier module and pickup module, playback module connects, and sound identification module, the phonetic synthesis module is connected with the rule base module with model simultaneously, and described control module is also passed through input interface module respectively, output interface module and computing machine, execution module connects.
2, by the described a kind of toy sound-control device of claim 1, it is characterized in that: described control module, sound identification module, phonetic synthesis module are integrated by a microprocessor.
3, by the described a kind of toy sound-control device of claim 1, it is characterized in that: described pickup module comprises microphone.
4, by the described a kind of toy sound-control device of claim 1, it is characterized in that: described playback module comprises loudspeaker.
5, by the described a kind of toy sound-control device of claim 1, it is characterized in that: described execution module comprises light, display screen or the gearing of toy.
6, a kind of interactive voice and control method of toy sound-control device realization as claimed in claim 1, it is characterized in that: whether device constantly detects input interface module and is connected with computing machine, if detecting input interface module is connected with computing machine, then stop all operations, enter the program updating state; Device is when the program updating state, by downloaded more new model and rule base; Download when finishing model and rule base, and when computing machine disconnected with input interface module, device recovered normal operating conditions, utilizes new model and rule base realization interactive voice and control:
(1) by described pickup module sound wave is converted to the sound electric signal of simulation, after pre-amplifying module amplifies, is sent to described A/D modular converter;
(2) described A/D modular converter is sampled to the sound electric signal of simulation and is quantized, and is converted to digital signal and sends into described sound identification module;
(3) described sound identification module carries out detection and Identification to input signal in real time, as the vocabulary in the speech recognition modeling storehouse as described in comprising in the input signal, then recognition result is delivered to described control module, otherwise continues input signal is detected;
(4) after described control module is received the recognition result that sound identification module provides, according to response rule predetermined in the rule base, to described output interface module output control signal required, that pre-define in the described output control signal storehouse, and notify described phonetic synthesis module to synthesize required voice;
(5) described phonetic synthesis module is utilized the synthetic required voice signal of speech recognition modeling in the described speech recognition modeling storehouse, and is delivered to described D/A modular converter according to the requirement of described control module;
(6) utilize described D/A modular converter that the audio digital signals of phonetic synthesis module output is converted to the voice telecommunication number of simulation, and play the voice signal of this simulation by described power amplifier module and playback module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100326670A CN100501834C (en) | 2005-01-04 | 2005-01-04 | Toy sound-control device and its language interaction and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100326670A CN100501834C (en) | 2005-01-04 | 2005-01-04 | Toy sound-control device and its language interaction and control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1640522A CN1640522A (en) | 2005-07-20 |
| CN100501834C true CN100501834C (en) | 2009-06-17 |
Family
ID=34876051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2005100326670A Expired - Fee Related CN100501834C (en) | 2005-01-04 | 2005-01-04 | Toy sound-control device and its language interaction and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100501834C (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096382A (en) * | 2010-10-29 | 2011-06-15 | 佛山市顺德区瑞德电子实业有限公司 | Interactive sound-control coffee pot controller |
| JP4971520B1 (en) * | 2011-11-24 | 2012-07-11 | 株式会社バンダイ | Makeup toy and wearing body for makeup toy |
| CN103028265B (en) * | 2012-12-20 | 2015-04-22 | 浙江理工大学 | Color teaching light toy based on natural interaction |
| CN104835495B (en) * | 2015-05-30 | 2018-05-08 | 宁波摩米创新工场电子科技有限公司 | A kind of high definition speech recognition system based on low-pass filtering |
| CN108091336A (en) * | 2017-12-15 | 2018-05-29 | 长沙志唯电子科技有限公司 | The intelligent robot of auxiliary exercise mandarin |
-
2005
- 2005-01-04 CN CNB2005100326670A patent/CN100501834C/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN1640522A (en) | 2005-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104834642B (en) | Change the method, device and equipment of music deduction style | |
| US9558727B2 (en) | Performance method of electronic musical instrument and music | |
| CN106782591A (en) | A kind of devices and methods therefor that phonetic recognization rate is improved under background noise | |
| US8912419B2 (en) | Synchronized multiple device audio playback and interaction | |
| CN201586394U (en) | Interactive stage effect system | |
| CN101357269A (en) | Intelligent toy and use method thereof | |
| CN208691406U (en) | Far field speech collecting system for smart television | |
| CN110349582A (en) | Display device and far field speech processing circuit | |
| CN100501834C (en) | Toy sound-control device and its language interaction and control method | |
| CN106878840A (en) | Intelligent microphone | |
| CN2776505Y (en) | Sound control device of toy | |
| JP3621020B2 (en) | Music reaction robot and transmitter | |
| CN202044780U (en) | Electric toy controlled by ultrasonic wave | |
| CN103177715B (en) | It digital piano | |
| CN202018824U (en) | Intelligent dialogue sounding | |
| CN201754335U (en) | Intelligent voice interaction device | |
| CN108847067A (en) | A kind of Aural-comprehension Training system | |
| CN202078739U (en) | Intelligent toy with click reading function | |
| CN101393738A (en) | Biology-like device capable of talking, and talking method thereof | |
| JP4531916B2 (en) | Information providing system and voice doll | |
| CN202773065U (en) | Sound box with karaoke singing function | |
| CN102339604A (en) | Speech intelligent interaction system | |
| CN101393429B (en) | Automatic control system and automatic control device by utilizing tone | |
| CN205754816U (en) | Cloud audio sound card | |
| CN212934141U (en) | Electric piano with karaoke function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| 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: 20090617 Termination date: 20130104 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |