CN109123927A - A kind of Intelligent bracelet based on speech recognition - Google Patents
A kind of Intelligent bracelet based on speech recognition Download PDFInfo
- Publication number
- CN109123927A CN109123927A CN201810958249.1A CN201810958249A CN109123927A CN 109123927 A CN109123927 A CN 109123927A CN 201810958249 A CN201810958249 A CN 201810958249A CN 109123927 A CN109123927 A CN 109123927A
- Authority
- CN
- China
- Prior art keywords
- module
- voice
- intelligent bracelet
- information
- voice messaging
- 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
- 238000001514 detection method Methods 0.000 claims abstract description 68
- 238000004891 communication Methods 0.000 claims abstract description 27
- 230000005540 biological transmission Effects 0.000 claims abstract description 22
- 238000001228 spectrum Methods 0.000 claims description 44
- 230000006870 function Effects 0.000 claims description 41
- 230000033001 locomotion Effects 0.000 claims description 28
- 230000010354 integration Effects 0.000 claims description 19
- 230000005611 electricity Effects 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims 1
- 238000000034 method Methods 0.000 description 24
- 230000008569 process Effects 0.000 description 17
- 230000015654 memory Effects 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000005457 optimization Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A44—HABERDASHERY; JEWELLERY
- A44C—PERSONAL ADORNMENTS, e.g. JEWELLERY; COINS
- A44C5/00—Bracelets; Wrist-watch straps; Fastenings for bracelets or wrist-watch straps
- A44C5/0007—Bracelets specially adapted for other functions or with means for attaching other articles
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/38—Transceivers, i.e. devices in which transmitter and receiver form a structural unit and in which at least one part is used for functions of transmitting and receiving
- H04B1/3827—Portable transceivers
- H04B1/385—Transceivers carried on the body, e.g. in helmets
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/38—Transceivers, i.e. devices in which transmitter and receiver form a structural unit and in which at least one part is used for functions of transmitting and receiving
- H04B1/3827—Portable transceivers
- H04B1/385—Transceivers carried on the body, e.g. in helmets
- H04B2001/3861—Transceivers carried on the body, e.g. in helmets carried in a hand or on fingers
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computer Networks & Wireless Communication (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
A kind of Intelligent bracelet based on speech recognition, including microphone module, detection module, central processing module and communication module;Microphone module, the first object voice messaging that the user for obtaining Intelligent bracelet inputs, and first object voice messaging is sent to detection module;Detection module for receiving the first object voice messaging of microphone module transmission, and detects whether first object voice messaging matches with default voice messaging;Central processing module, the second target voice information and the corresponding target device of default voice messaging of user's input for when detection module detects first object voice messaging and default voice messaging matches, obtaining Intelligent bracelet;Communication module, the second target voice information for obtaining central processing module are sent to target device.Implement the embodiment of the present invention, is capable of providing a kind of small volume and function is simple, can directly carry out the Intelligent bracelet suitable for underage child of information transmission by voice.
Description
Technical field
The present invention relates to wearable device technical field more particularly to a kind of Intelligent bracelets based on speech recognition.
Background technique
Currently, children wear wearable device the phenomenon that it is more and more common, for example, children usually wear phone wrist-watch come with
The types of applications etc. installed in phone wrist-watch is made friends and used between parent's video calling, children.For the ease of children in electricity
It talks about triggering on the display screen of wrist-watch and executes aforesaid operations, the display screen of phone wrist-watch is often arranged bigger, so that whole
A phone wrist-watch volume is larger.In practice, it has been found that the phone wrist-watch that volume is excessive and function is complicated is not particularly suited for low age youngster
Virgin (such as 2 to 3 years old children).Therefore, developing a wearable device for being specially suitable for underage child becomes a urgent need to resolve
The problem of.
Summary of the invention
The embodiment of the present invention discloses a kind of Intelligent bracelet based on speech recognition, since Intelligent bracelet can directly pass through language
Sound carries out information transmission, because miscellaneous for carrying out information transmission without being arranged on the display screen of Intelligent bracelet
Virtual menu and virtual key, thus reduce Intelligent bracelet display screen size, thereby reduce Intelligent bracelet
Volume is more suitable for underage child.
The embodiment of the present invention discloses a kind of Intelligent bracelet based on speech recognition, and the Intelligent bracelet includes microphone mould
Block, detection module, central processing module and communication module;
The microphone module, the first object voice messaging that the user for obtaining the Intelligent bracelet inputs, and will
The first object voice messaging is sent to the detection module;
The detection module, the first object voice messaging sent for receiving the microphone module, and detect
Whether the first object voice messaging matches with default voice messaging;
The central processing module, for when the detection module detect the first object voice messaging with it is described pre-
If voice messaging matches, the second target voice information and the default language that the user of the Intelligent bracelet inputs are obtained
Message ceases corresponding target device;
The communication module, the second target voice information for obtaining the central processing module are sent to institute
State target device.
As an alternative embodiment, in embodiments of the present invention, the microphone module is for obtaining the intelligence
The mode of the first object voice messaging of user's input of energy bracelet specifically:
The microphone module, the initial speech information that the user for obtaining the Intelligent bracelet inputs, and judge institute
State whether the corresponding voice amplitudes value of initial speech information is greater than default voice amplitudes value;When judging the initial speech information
When the corresponding voice amplitudes value is greater than the default voice amplitudes value, corresponding first language of the initial speech information is judged
Sound spectrum the second voice spectrum whether corresponding with noise matches;When judging first voice spectrum and second language
When sound spectrum does not match that, judge whether the corresponding voice signal-to-noise ratio of the initial speech information is greater than default voice signal-to-noise ratio;
It, will be described first when judging that the corresponding voice signal-to-noise ratio of the initial speech information is greater than the default voice signal-to-noise ratio
Beginning voice messaging is determined as first object voice messaging.
As an alternative embodiment, in embodiments of the present invention,
The detection module is also used in the first object voice messaging for receiving the microphone module and sending
Later, pretreatment and speech parameter generation are carried out to the first object voice messaging, obtains the first object voice letter
Cease corresponding target mel-frequency cepstrum coefficient;
The detection module is for detecting the side whether the first object voice messaging matches with default voice messaging
Formula specifically:
The detection module, for utilizing dynamic time warping algorithm using the phonetic feature for presetting voice messaging as foundation
Detect the corresponding target mel-frequency cepstrum coefficient of the first object voice messaging whether with the default voice messaging
Phonetic feature match.
As an alternative embodiment, in embodiments of the present invention,
The detection module is also used to work as and judges the target mel-frequency cepstrum coefficient and the default voice messaging
Phonetic feature the default voice messaging is updated to the first object voice messaging when matching, and will be described default
The phonetic feature of voice messaging is updated to the corresponding feature of the target mel-frequency cepstrum coefficient;And the triggering centre
It manages device and executes the second target voice information and the default voice letter that the user of the acquisition Intelligent bracelet inputs
Cease corresponding target device.
As an alternative embodiment, in embodiments of the present invention, the detection module is used for first mesh
Mark voice messaging carries out pretreatment and speech parameter generation, obtains the corresponding target Meier frequency of the first object voice messaging
The mode of rate cepstrum coefficient specifically:
The detection module, the voice time domain signal for including to the first object voice messaging carry out Fourier's change
It changes, obtains voice frequency domain signal;And calculate the voice frequency domain frequency spectrum of the voice frequency domain signal;And utilize triangle bandpass filtering
Device is filtered the voice frequency domain frequency spectrum, obtains filtered target frequency-domain spectrum;And calculate the target frequency domain frequency
The log spectrum of spectrum carries out long-lost cosine code to the log spectrum, obtains target mel-frequency cepstrum coefficient.
As an alternative embodiment, in embodiments of the present invention, the Intelligent bracelet further includes inertia integral mould
Block, in which:
The inertia integration module, for obtaining the motion information of the Intelligent bracelet, the motion information is included at least
Direction of motion information and motion velocity information;And the motion velocity information is integrated in conjunction with preset time, obtain with
The travel information that the preset time, the motion velocity information match;And in conjunction with the direction of motion information and
The location information of Intelligent bracelet subsequent time described in the travel information prediction.
As an alternative embodiment, in embodiments of the present invention, the Intelligent bracelet further includes locating module,
In:
The locating module, for obtaining working as the Intelligent bracelet when the unlatching of the positioning function of the locating module
Front position information;
The inertia integral unit is also used to when the positioning function of the locating module is closed, and detects the intelligent hand
Whether the location information of ring subsequent time is located at default relocate in range;When detecting the Intelligent bracelet subsequent time
When location information is located in the default repositioning range, to the locating module transmission be used to indicate reopen it is described fixed
The enabled instruction of the positioning function of position module;
The locating module is also used to receive the enabled instruction, and reopened according to the enabled instruction it is described fixed
The positioning function of position module.
As an alternative embodiment, in embodiments of the present invention, the Intelligent bracelet further includes Electromagnetic generation mould
Block and power module, the Electromagnetic generation module includes magnet and coil, in which:
The Electromagnetic generation module, the current signal generated for obtaining the coil according to the swing of the magnet, will
The current signal is sent to power module;
The power module for receiving the current signal, and the current signal is converted to and is believed with the electric current
Number matched electricity.
As an alternative embodiment, in embodiments of the present invention, the communication module is logical using narrowband Internet of Things
Letter technology realizes communication function.
As an alternative embodiment, in embodiments of the present invention, the Intelligent bracelet further includes that sound plays mould
Block and indicating lamp module, in which:
The sound broadcasting module is returned for that ought receive the target device according to the second target voice information
Third target voice information when, voice plays the third target voice information, and sends and flash to the indicating lamp module
Instruction;
The indicating lamp module, for being flashed according to the indicated flashing mode of the flashing instruction.
Compared with prior art, the embodiment of the present invention has the advantages that
In the embodiment of the present invention, the first object voice letter of the available user's input of the microphone module of Intelligent bracelet
Breath, when the detection module of Intelligent bracelet detects that the first object voice messaging matches with default voice messaging (such as " father ")
When, detection module obtains the second target voice information of user's input, and utilizes communication module by the second target voice information
It is sent to the corresponding target device of default voice messaging (such as the mobile phone of the father of the children using Intelligent bracelet).This process benefit
It is realized with the voice recognition mode of dialogue scene in fitting real life and carries out information transmission automatically by voice, it is not necessary in intelligence
The miscellaneous virtual menu and virtual key for being used to carry out information transmission can be set on the display screen of bracelet, to reduce
The size of the display screen of Intelligent bracelet, thereby reduces the volume of Intelligent bracelet, is more suitable for underage child.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of structural schematic diagram of Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention;
Fig. 2 is the structural schematic diagram of another Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention;
Fig. 3 is the structural schematic diagram of another Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention;
Fig. 4 is the structural schematic diagram of another Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention;
Fig. 5 is the structural schematic diagram of another Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention;
Fig. 6 is a kind of information exchange process signal of Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention
Figure.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
It should be noted that term " includes " and " having " and their any changes in the embodiment of the present invention and attached drawing
Shape, it is intended that cover and non-exclusive include.Such as contain the process, method of a series of steps or units, system, product or
Equipment is not limited to listed step or unit, but optionally further comprising the step of not listing or unit or optional
Ground further includes the other step or units intrinsic for these process, methods, product or equipment.
The embodiment of the present invention discloses a kind of Intelligent bracelet based on speech recognition, is capable of providing a kind of small volume and function
Simply, the Intelligent bracelet suitable for underage child of information transmission can be directly carried out by voice.It carries out individually below detailed
It describes in detail bright.
Embodiment one
Referring to Fig. 1, Fig. 1 is a kind of structural representation of Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention
Figure, as shown in Figure 1, should Intelligent bracelet 100 based on speech recognition may include microphone module 101, detection module 102, in
Entreat processing module 103 and communication module 104;
Microphone module 101, the first object voice messaging that the user for obtaining Intelligent bracelet inputs, and by the first mesh
Mark voice messaging is sent to detection module 102.
As an alternative embodiment, microphone module 101 obtains the first object of user's input of Intelligent bracelet
Voice messaging may include:
Microphone module 101 obtains the initial speech information of user's input of Intelligent bracelet;
Microphone module 101 judges whether the corresponding voice amplitudes value of initial speech information is greater than default voice amplitudes value;
When judging that the corresponding voice amplitudes value of initial speech information is greater than default voice amplitudes value, microphone module
101 judge that corresponding first voice spectrum of initial speech information the second voice spectrum whether corresponding with noise matches;
When judging that the first voice spectrum and the second voice spectrum do not match that, microphone module 101 judges initial language
Message ceases whether corresponding voice signal-to-noise ratio is greater than default voice signal-to-noise ratio;
When judging that the corresponding voice signal-to-noise ratio of initial speech information is greater than default voice signal-to-noise ratio, microphone module
Initial speech information is determined as first object voice messaging by 101.
By implementing this optional embodiment, when the initial speech information got is not the legal use of Intelligent bracelet
(the initial speech information such as got is the passerby positioned at Intelligent bracelet present position nearby to the initial speech information of family input
Talk sound) when, when the corresponding voice amplitudes value of initial speech information is less than or equal to default voice amplitudes value, at this point, not
The initial speech information is determined as first object voice messaging;When the initial speech information got is noise (voice amplitudes
Value is greater than the noise of default voice amplitudes value) when, corresponding first voice spectrum corresponding with noise second of initial speech information
Voice spectrum matches, at this point, the initial speech information is not determined as first object voice messaging;When the initial language got
Message breath had not only included noise but also when including non-noise, judge the corresponding voice signal-to-noise ratio of initial speech information whether greatly with default language
Sound signal-to-noise ratio illustrates initial speech information when the corresponding voice signal-to-noise ratio of initial voice messaging is greater than default voice signal-to-noise ratio
In noise proportional it is smaller negligible, initial speech information is determined as first object voice messaging at this time;When initial language
When message ceases corresponding voice signal-to-noise ratio less than or equal to default voice signal-to-noise ratio, illustrate the noise ratio in initial speech information
Example is excessively high, which is not determined as first object voice messaging.It, can by implementing this optional embodiment
To filter invalid voice to a certain extent, to improve the reliability of the first object voice messaging finally obtained.
Detection module 102 for receiving the first object voice messaging of the transmission of microphone module 101, and detects the first mesh
Whether mark voice messaging matches with default voice messaging.
In the embodiment of the present invention, several predetermined keyword information are previously stored in Intelligent bracelet, for example, " father ",
" mother ", " grandfather " and " grandmother " etc., default voice messaging can be for one in several predetermined keyword information or more
It is a.
As an alternative embodiment, receiving the first object language that microphone module 101 is sent in detection module 102
After message breath, detection module 102 be can be also used for:
Pretreatment and speech parameter generation are carried out to first object voice messaging, it is corresponding to obtain first object voice messaging
Target mel-frequency cepstrum coefficient.
As another optional embodiment, detection module 102 to first object voice messaging carry out pretreatment and
Speech parameter generation, obtaining the corresponding target mel-frequency cepstrum coefficient of first object voice messaging may include:
Detection module 102 carries out Fourier transformation to the voice time domain signal that first object voice messaging includes, and obtains language
Audio domain signal;
The voice frequency domain frequency spectrum of the calculating voice frequency domain signal of detection module 102;
Detection module 102 is filtered voice frequency domain frequency spectrum using triangle bandpass filter, obtains filtered target
Frequency-domain spectrum;
Detection module 102 calculates the log spectrum of target frequency-domain spectrum, carries out long-lost cosine code to log spectrum, obtains
Target mel-frequency cepstrum coefficient.
As another optional embodiment, detection module 102 detect first object voice messaging whether with default language
Message manner of breathing matches
Detection module 102 utilizes dynamic time warping algorithm detection the using the phonetic feature for presetting voice messaging as foundation
Whether the corresponding target mel-frequency cepstrum coefficient of one target voice information matches with the phonetic feature of default voice messaging.
By implementing this optional embodiment, since dynamic time warping algorithm is known suitable for alone word voice
Not, thus using dynamic time warping algorithm whether the corresponding target mel-frequency cepstrum coefficient of first object voice messaging is detected
Match with the phonetic feature of default voice messaging and be accustomed to suitable for the speech expression of underage child, Detection accuracy is higher.
Central processing module 103, for detecting first object voice messaging and default voice messaging when detection module 102
When matching, the second target voice information and the corresponding target of default voice messaging for obtaining user's input of Intelligent bracelet are set
It is standby.
As another optional embodiment, when detection module 102 judges target mel-frequency cepstrum coefficient and pre-
If the phonetic feature of voice messaging matches, detection module 102 be can be also used for:
Default voice messaging is updated to first object voice messaging, and the phonetic feature of default voice messaging is updated to
The corresponding feature of target mel-frequency cepstrum coefficient;And triggering central processing unit 103 executes above-mentioned acquisition Intelligent bracelet
The the second target voice information and the corresponding target device of default voice messaging of user's input.
By implementing this optional embodiment, it can judge every time target mel-frequency cepstrum coefficient and preset
When the phonetic feature of voice messaging matches, default voice messaging and the corresponding phonetic feature of default voice messaging are updated, this
One process can constantly train the default corresponding phonetic feature of voice messaging, to obtain relatively reliable default voice messaging pair
The phonetic feature answered.
As another optional embodiment, default voice messaging is updated to first object voice by detection module 102
Information, and the phonetic feature of default voice messaging is updated to the corresponding feature of target mel-frequency cepstrum coefficient and may include:
Detection module 102 obtains first object voice to be updated according to default voice messaging and first object voice messaging
Information, and obtained according to the phonetic feature of default voice messaging and the corresponding feature of target mel-frequency cepstrum coefficient to be updated
Target mel-frequency cepstrum coefficient;
Default voice messaging is updated to above-mentioned first object voice messaging to be updated by detection module 102, and will be preset
The phonetic feature of voice messaging is updated to the above-mentioned corresponding feature of target mel-frequency cepstrum coefficient to be updated.
By implementing this optional embodiment, target mel-frequency cepstrum coefficient and default language can be being judged every time
When the phonetic feature of message breath matches, default voice messaging is updated in conjunction with default voice messaging and first object voice messaging
For first object voice messaging to be updated, the phonetic feature of default voice messaging is updated to above-mentioned target Meier to be updated
The corresponding feature of frequency cepstral coefficient.This process can constantly train the default corresponding phonetic feature of voice messaging, thus
To the relatively reliable corresponding phonetic feature of default voice messaging.
Communication module 104, the second target voice information for obtaining central processing module 103 are sent to target and set
It is standby.
In the embodiment of the present invention, communication module 104 realizes communication function using protenchyma connected network communication technology.
As an alternative embodiment, when default voice messaging can be more in several predetermined keyword information
When the corresponding voice of a predetermined keyword information, central processing module 103 obtains the second target of user's input of Intelligent bracelet
Voice messaging and the corresponding target device of default voice messaging may include:
Central processing module 103 obtains the second target voice information and each default language that the user of Intelligent bracelet inputs
Message ceases corresponding target device;
The second target voice information that communication module 104 obtains central processing module, which is sent to target device, can wrap
It includes:
The second target voice information that the user of Intelligent bracelet inputs is sent to each default voice and believed by communication module 104
Cease corresponding target device.
It for example, will be intelligent when default voice messaging is " father " corresponding voice and " mother " corresponding voice
The equipment that the second target voice information (such as " I, which stays out, has a meal ") of user's input of bracelet is sent to the father of the user
And the equipment of the mother of the user further enriches the functional diversity of Intelligent bracelet to realize the function of mass-sending.
As another optional embodiment, which can also include bluetooth module, which can be with
Using the MESH technology of bluetooth 5.0, wherein bluetooth module can be used for:
It searches in the signal cover of the bluetooth module with the presence or absence of at least one target device;
When judging to receive the matching instruction of user's input there are when at least one target device, matching instruction is used for
Indicating intelligent bracelet is matched with several target devices at least one target device;
Intelligent bracelet is matched with several target devices according to the matching instruction, and obtains several targets
The contact details of each target device in equipment, contact details can include but is not limited to telephone number and social account etc.;
The contact details of the contact details of Intelligent bracelet and each target device are uploaded to background server, so that after
The Intelligent bracelet and each target device are established friend relation by platform server.
By implementing this optional embodiment, quickly added using the many-to-many equipment communication technology realization of bluetooth module
Plusing good friend carries out social activity convenient for the user of Intelligent bracelet, improves the social experience of the user of Intelligent bracelet, in addition, using blue
The MESH technology of tooth 5.0 can also save the power consumption of bluetooth module.
As it can be seen that being talked with by implementing the Intelligent bracelet based on speech recognition described in Fig. 1 using being bonded in real life
The voice recognition mode of situation, which is realized, carries out information transmission automatically by voice, it is not necessary to set on the display screen of Intelligent bracelet
The miscellaneous virtual menu and virtual key for being used to carry out information transmission is set, to reduce the display screen of Intelligent bracelet
Size, thereby reduce the volume of Intelligent bracelet, be more suitable for underage child.
Embodiment two
Referring to Fig. 2, the structure that Fig. 2 is another Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention is shown
It is intended to.Wherein, the Intelligent bracelet 100 shown in Fig. 2 based on speech recognition is the intelligent hand based on speech recognition as shown in Figure 1
The optimization of ring 100 obtains, shown in Fig. 2 to be known based on voice compared with the Intelligent bracelet 100 shown in FIG. 1 based on speech recognition
Other Intelligent bracelet 100 further includes inertia integration module 105, in which:
Inertia integration module 105, for obtaining the motion information of Intelligent bracelet, motion information is believed including at least the direction of motion
Breath and motion velocity information;And motion velocity information is integrated in conjunction with preset time, it obtains and preset time, movement speed
The travel information that degree information matches;And it combines one under direction of motion information and travel information prediction Intelligent bracelet
The location information at moment.
As it can be seen that being talked with by implementing the Intelligent bracelet based on speech recognition described in Fig. 2 using being bonded in real life
The voice recognition mode of situation, which is realized, carries out information transmission automatically by voice, it is not necessary to set on the display screen of Intelligent bracelet
The miscellaneous virtual menu and virtual key for being used to carry out information transmission is set, to reduce the display screen of Intelligent bracelet
Size, thereby reduce the volume of Intelligent bracelet, be more suitable for underage child.
In addition, GPS signal is weak indoors extremely can not by implementing the Intelligent bracelet based on speech recognition described in Fig. 2
When knowing the position of Intelligent bracelet, it can use the location information of inertia integration module prediction Intelligent bracelet subsequent time, improve
To the reliability of the Intelligent bracelet positioning under different scenes.For example, as the children market and the parent indoors that wear Intelligent bracelet
When wandering away, even if the GPS signal of indoor mall is weak, it also can use inertia integration module and carry out auxiliary positioning, to improve positioning
Reliability.
Embodiment three
Referring to Fig. 3, the structure that Fig. 3 is another Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention is shown
It is intended to.Wherein, the Intelligent bracelet 100 shown in Fig. 3 based on speech recognition is the intelligent hand based on speech recognition as shown in Figure 2
The optimization of ring 100 obtains, shown in Fig. 3 to be known based on voice compared with the Intelligent bracelet 100 shown in Fig. 2 based on speech recognition
Other Intelligent bracelet 100 further includes locating module 106, in which:
Locating module 106, for obtaining the present bit confidence of Intelligent bracelet when the unlatching of the positioning function of locating module
Breath.
Inertia integral unit 105 is also used to detect one under Intelligent bracelet when the positioning function of locating module 106 is closed
Whether the location information at moment is located at default relocate in range;When the location information position for detecting Intelligent bracelet subsequent time
When default relocate in range, is sent to locating module 106 and be used to indicate the positioning function for reopening locating module
Enabled instruction.
Locating module 106 is also used to receive enabled instruction, and reopens positioning function according to enabled instruction.
As it can be seen that being talked with by the Intelligent bracelet based on speech recognition described in implementing Fig. 3 using being bonded in real life
The voice recognition mode of situation, which is realized, carries out information transmission automatically by voice, it is not necessary to set on the display screen of Intelligent bracelet
The miscellaneous virtual menu and virtual key for being used to carry out information transmission is set, to reduce the display screen of Intelligent bracelet
Size, thereby reduce the volume of Intelligent bracelet, be more suitable for underage child.
In addition, GPS signal is weak indoors extremely can not by the Intelligent bracelet based on speech recognition described in implementing Fig. 3
When knowing the position of Intelligent bracelet, it can use the location information of inertia integration module prediction Intelligent bracelet subsequent time, improve
To the reliability of the Intelligent bracelet positioning under different scenes.For example, as the children market and the parent indoors that wear Intelligent bracelet
When wandering away, even if the GPS signal of indoor mall is weak, it also can use inertia integration module and carry out auxiliary positioning, to improve positioning
Reliability.
In addition, the positioning of locating module can also be worked as by the Intelligent bracelet based on speech recognition described in implementing Fig. 3
Function is closed and inertia integral unit detects that the location information of Intelligent bracelet subsequent time is located at default relocate in range
When, reopen the positioning function of locating module.For example, being closed when the children for wearing Intelligent bracelet are in safety zone activity
The positioning function for closing locating module saves power consumption with this, and the location information of children's subsequent time is predicted using inertia integral unit,
When the location information of subsequent time is located at default relocate in range, the positioning function of locating module is reopened, thus
The power consumption of Intelligent bracelet can be saved but also effectively Intelligent bracelet is positioned.
Example IV
Referring to Fig. 4, the structure that Fig. 4 is another Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention is shown
It is intended to.Wherein, the Intelligent bracelet 100 shown in Fig. 4 based on speech recognition is the intelligent hand based on speech recognition as shown in Figure 3
The optimization of ring 100 obtains, shown in Fig. 4 to be known based on voice compared with the Intelligent bracelet 100 shown in Fig. 3 based on speech recognition
Other Intelligent bracelet 100 further includes Electromagnetic generation module 107 and power module 108, in which:
Electromagnetic generation module 107, the current signal generated for obtaining coil according to the swing of magnet, current signal is sent out
Give power module 108.
In the embodiment of the present invention, Electromagnetic generation module includes magnet and coil.
Power module 108 is converted to and the matched electricity of current signal for receiving current signal, and by current signal.
As it can be seen that being talked with by implementing the Intelligent bracelet based on speech recognition described in Fig. 4 using being bonded in real life
The voice recognition mode of situation, which is realized, carries out information transmission automatically by voice, it is not necessary to set on the display screen of Intelligent bracelet
The miscellaneous virtual menu and virtual key for being used to carry out information transmission is set, to reduce the display screen of Intelligent bracelet
Size, thereby reduce the volume of Intelligent bracelet, be more suitable for underage child.
In addition, GPS signal is weak indoors extremely can not by implementing the Intelligent bracelet based on speech recognition described in Fig. 4
When knowing the position of Intelligent bracelet, it can use the location information of inertia integration module prediction Intelligent bracelet subsequent time, improve
To the reliability of the Intelligent bracelet positioning under different scenes.For example, as the children market and the parent indoors that wear Intelligent bracelet
When wandering away, even if the GPS signal of indoor mall is weak, it also can use inertia integration module and carry out auxiliary positioning, to improve positioning
Reliability.
In addition, the positioning of locating module can also be worked as by implementing the Intelligent bracelet based on speech recognition described in Fig. 4
Function is closed and inertia integral unit detects that the location information of Intelligent bracelet subsequent time is located at default relocate in range
When, reopen the positioning function of locating module.For example, being closed when the children for wearing Intelligent bracelet are in safety zone activity
The positioning function for closing locating module saves power consumption with this, and the location information of children's subsequent time is predicted using inertia integral unit,
When the location information of subsequent time is located at default relocate in range, the positioning function of locating module is reopened, thus
The power consumption of Intelligent bracelet can be saved but also effectively Intelligent bracelet is positioned.
In addition, Electromagnetic generation module can also be utilized by implementing the Intelligent bracelet based on speech recognition described in Fig. 4
In coil current signal is generated according to the swing of magnet, and current signal is issued into power module, so that power module is in intelligence
When the electricity of energy bracelet exhausts, using the corresponding electricity emergency of the current signal, to improve the user experience.
Embodiment five
Referring to Fig. 5, the structure that Fig. 5 is another Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention is shown
It is intended to.Wherein, the Intelligent bracelet 100 shown in fig. 5 based on speech recognition is the intelligent hand based on speech recognition as shown in Figure 4
The optimization of ring 100 obtains, shown in fig. 5 to be known based on voice compared with the Intelligent bracelet 100 shown in Fig. 4 based on speech recognition
Other Intelligent bracelet 100 further includes sound broadcasting module 109 and indicating lamp module 110, in which:
Sound broadcasting module 109, for working as the third mesh for receiving target device and returning according to the second target voice information
When marking voice messaging, voice plays third target voice information, and sends flashing instruction to indicating lamp module 110.
Indicating lamp module 110, for being flashed according to the indicated flashing mode of flashing instruction.
As it can be seen that being talked with by implementing the Intelligent bracelet based on speech recognition described in Fig. 5 using being bonded in real life
The voice recognition mode of situation, which is realized, carries out information transmission automatically by voice, it is not necessary to set on the display screen of Intelligent bracelet
The miscellaneous virtual menu and virtual key for being used to carry out information transmission is set, to reduce the display screen of Intelligent bracelet
Size, thereby reduce the volume of Intelligent bracelet, be more suitable for underage child.
In addition, GPS signal is weak indoors extremely can not by implementing the Intelligent bracelet based on speech recognition described in Fig. 5
When knowing the position of Intelligent bracelet, it can use the location information of inertia integration module prediction Intelligent bracelet subsequent time, improve
To the reliability of the Intelligent bracelet positioning under different scenes.For example, as the children market and the parent indoors that wear Intelligent bracelet
When wandering away, even if the GPS signal of indoor mall is weak, it also can use inertia integration module and carry out auxiliary positioning, to improve positioning
Reliability.
In addition, the positioning of locating module can also be worked as by implementing the Intelligent bracelet based on speech recognition described in Fig. 5
Function is closed and inertia integral unit detects that the location information of Intelligent bracelet subsequent time is located at default relocate in range
When, reopen the positioning function of locating module.For example, being closed when the children for wearing Intelligent bracelet are in safety zone activity
The positioning function for closing locating module saves power consumption with this, and the location information of children's subsequent time is predicted using inertia integral unit,
When the location information of subsequent time is located at default relocate in range, the positioning function of locating module is reopened, thus
The power consumption of Intelligent bracelet can be saved but also effectively Intelligent bracelet is positioned.
In addition, Electromagnetic generation module can also be utilized by implementing the Intelligent bracelet based on speech recognition described in Fig. 5
In coil current signal is generated according to the swing of magnet, and current signal is issued into power module, so that power module is in intelligence
When the electricity of energy bracelet exhausts, using the corresponding electricity emergency of the current signal, to improve the user experience.
In addition, sound broadcasting module can also be utilized by implementing the Intelligent bracelet based on speech recognition described in Fig. 5
Voice plays the third target voice information that target device is returned according to the second target voice information, and is sent out using indicating lamp module
It is used to indicate the flashing for receiving third target voice information out, enriches the functional diversity of Intelligent bracelet.
Embodiment six
Referring to Fig. 6, Fig. 6 is a kind of information exchange flow diagram of Intelligent bracelet based on speech recognition, wherein figure
The information exchange flow diagram of the 6 described Intelligent bracelets based on speech recognition can be applied to described in embodiment one
In Intelligent bracelet based on speech recognition, the information exchange process for being somebody's turn to do the Intelligent bracelet based on speech recognition may include following step
It is rapid:
601, microphone module obtains the first object voice messaging of user's input of Intelligent bracelet.
As an alternative embodiment, microphone module obtains the first object voice of user's input of Intelligent bracelet
Information may include:
Microphone module obtains the initial speech information of user's input of Intelligent bracelet, and judges that initial speech information is corresponding
Voice amplitudes value whether be greater than default voice amplitudes value;
When judging that the corresponding voice amplitudes value of initial speech information is greater than default voice amplitudes value, microphone module is sentenced
Disconnected corresponding first voice spectrum of initial speech information the second voice spectrum whether corresponding with noise matches;
When judging that the first voice spectrum and the second voice spectrum do not match that, microphone module judges that initial speech is believed
Cease whether corresponding voice signal-to-noise ratio is greater than default voice signal-to-noise ratio;
When judging that the corresponding voice signal-to-noise ratio of initial speech information is greater than default voice signal-to-noise ratio, microphone module will
Initial speech information is determined as first object voice messaging.
By implementing this optional embodiment, when the initial speech information got is not the legal use of Intelligent bracelet
(the initial speech information such as got is the passerby positioned at Intelligent bracelet present position nearby to the initial speech information of family input
Talk sound) when, when the corresponding voice amplitudes value of initial speech information is less than or equal to default voice amplitudes value, at this point, not
The initial speech information is determined as first object voice messaging;When the initial speech information got is noise (voice amplitudes
Value is greater than the noise of default voice amplitudes value) when, corresponding first voice spectrum corresponding with noise second of initial speech information
Voice spectrum matches, at this point, the initial speech information is not determined as first object voice messaging;When the initial language got
Message breath had not only included noise but also when including non-noise, judge the corresponding voice signal-to-noise ratio of initial speech information whether greatly with default language
Sound signal-to-noise ratio illustrates initial speech information when the corresponding voice signal-to-noise ratio of initial voice messaging is greater than default voice signal-to-noise ratio
In noise proportional it is smaller negligible, initial speech information is determined as first object voice messaging at this time;When initial language
When message ceases corresponding voice signal-to-noise ratio less than or equal to default voice signal-to-noise ratio, illustrate the noise ratio in initial speech information
Example is excessively high, which is not determined as first object voice messaging.It, can by implementing this optional embodiment
To filter invalid voice to a certain extent, to improve the reliability of the first object voice messaging finally obtained.
602, first object voice messaging is sent to detection module by microphone module.
603, detection module receives the first object voice messaging that microphone module is sent.
As an alternative embodiment, receiving the first object voice that microphone module is sent in detection module believes it
Afterwards, following steps can also be performed:
Detection module carries out pretreatment and speech parameter generation to first object voice messaging, obtains first object voice
The corresponding target mel-frequency cepstrum coefficient of information.
As another optional embodiment, detection module carries out pretreatment and voice to first object voice messaging
Parameter extraction, obtaining the corresponding target mel-frequency cepstrum coefficient of first object voice messaging may include:
Detection module carries out Fourier transformation to the voice time domain signal that first object voice messaging includes, and obtains voice frequency
Domain signal;
The voice frequency domain frequency spectrum of detection module calculating voice frequency domain signal;
Detection module is filtered voice frequency domain frequency spectrum using triangle bandpass filter, obtains filtered target frequency domain
Frequency spectrum;
Detection module calculates the log spectrum of target frequency-domain spectrum, carries out long-lost cosine code to log spectrum, obtains mesh
Mark mel-frequency cepstrum coefficient.
604, whether detection module detection first object voice messaging matches with default voice messaging, if so, executing
Step 605 is to step 606, if not, terminating this process.
In the embodiment of the present invention, several predetermined keyword information are previously stored in Intelligent bracelet, for example, " father ",
" mother ", " grandfather " and " grandmother " etc., default voice messaging can be for one in several predetermined keyword information or more
It is a.
As an alternative embodiment, detection module detection first object voice messaging whether with default voice messaging
Match and may include:
Detection module detects the first mesh using dynamic time warping algorithm using the phonetic feature for presetting voice messaging as foundation
Whether the corresponding target mel-frequency cepstrum coefficient of mark voice messaging matches with the phonetic feature of default voice messaging.
By implementing this optional embodiment, by implementing this optional embodiment, since dynamic time is advised
Whole algorithm is suitable for alone word speech recognition, thus corresponding using dynamic time warping algorithm detection first object voice messaging
The voice that whether matches with the phonetic feature of default voice messaging suitable for underage child of target mel-frequency cepstrum coefficient
Statement habit, Detection accuracy are higher.
As another optional embodiment, when detection module judges target mel-frequency cepstrum coefficient and default language
When the phonetic feature of message breath matches, following steps can also be performed:
Default voice messaging is updated to first object voice messaging by detection module, and the voice of default voice messaging is special
Sign is updated to the corresponding feature of target mel-frequency cepstrum coefficient;And the acquisition Intelligent bracelet of triggering central processing unit execution
The the second target voice information and the corresponding target device of default voice messaging of user's input.
By implementing this optional embodiment, it can judge every time target mel-frequency cepstrum coefficient and preset
When the phonetic feature of voice messaging matches, default voice messaging and the corresponding phonetic feature of default voice messaging are updated, this
One process can constantly train the default corresponding phonetic feature of voice messaging, to obtain relatively reliable default voice messaging pair
The phonetic feature answered.
As another optional embodiment, default voice messaging is updated to first object voice letter by detection module
Breath, and the phonetic feature of default voice messaging is updated to the corresponding feature of target mel-frequency cepstrum coefficient and may include:
Detection module, which obtains first object voice to be updated according to default voice messaging and first object voice messaging, to be believed
Breath, and mesh to be updated is obtained according to the phonetic feature of default voice messaging and the corresponding feature of target mel-frequency cepstrum coefficient
Mark mel-frequency cepstrum coefficient;
Default voice messaging is updated to above-mentioned first object voice messaging to be updated by detection module, and by default voice
The phonetic feature of information is updated to the above-mentioned corresponding feature of target mel-frequency cepstrum coefficient to be updated.
By implementing this optional embodiment, target mel-frequency cepstrum coefficient and default language can be being judged every time
When the phonetic feature of message breath matches, default voice messaging is updated in conjunction with default voice messaging and first object voice messaging
For first object voice messaging to be updated, the phonetic feature of default voice messaging is updated to above-mentioned target Meier to be updated
The corresponding feature of frequency cepstral coefficient.This process can constantly train the default corresponding phonetic feature of voice messaging, thus
To the relatively reliable corresponding phonetic feature of default voice messaging.
605, central processing module obtains the second target voice information and default voice that the user of Intelligent bracelet inputs
The corresponding target device of information.
606, the second target voice information that communication module obtains central processing module is sent to target device.
As an alternative embodiment, when default voice messaging can be more in several predetermined keyword information
When the corresponding voice of a predetermined keyword information, central processing module obtains the second target voice of user's input of Intelligent bracelet
Information and the corresponding target device of default voice messaging may include:
Central processing module obtains the second target voice information and each default voice that the user of Intelligent bracelet inputs
The corresponding target device of information;
The second target voice information that communication module obtains central processing module is sent to target device and may include:
The second target voice information that the user of Intelligent bracelet inputs is sent to each default voice messaging by communication module
Corresponding target device.
It for example, will be intelligent when default voice messaging is " father " corresponding voice and " mother " corresponding voice
The equipment that the second target voice information (such as " I, which stays out, has a meal ") of user's input of bracelet is sent to the father of the user
And the equipment of the mother of the user further enriches the functional diversity of Intelligent bracelet to realize the function of mass-sending.
In the embodiment of the present invention, communication module realizes communication function using protenchyma connected network communication technology.
As an alternative embodiment, the Intelligent bracelet can also include inertia integration module and locating module,
In, following steps can also be performed in the information exchange process of the Intelligent bracelet based on speech recognition:
The motion information of inertia integration module acquisition Intelligent bracelet;
Motion information includes at least direction of motion information and motion velocity information in the embodiment of the present invention.
Inertia integration module combination preset time integrates motion velocity information, obtains and preset time, movement speed
The travel information that degree information matches;
The position of inertia integration module combination direction of motion information and travel information prediction Intelligent bracelet subsequent time
Information.
By implementing this optional embodiment, indoors when the weak position that can not extremely know Intelligent bracelet of GPS signal,
The location information that can use inertia integration module prediction Intelligent bracelet subsequent time, is improved to the Intelligent bracelet under different scenes
The reliability of positioning.For example, when market and parent's children of wearing Intelligent bracelet wander away indoors, even if indoor mall
GPS signal is weak, also can use inertia integration module and carrys out auxiliary positioning, to improve the reliability of positioning.
As another optional embodiment, following steps can also be performed:
When the positioning function of locating module is opened, locating module obtains the current location information of Intelligent bracelet;
When the positioning function of locating module is closed, inertia integral unit detects the location information of Intelligent bracelet subsequent time
Whether default relocate range in is located at;
When the location information for detecting Intelligent bracelet subsequent time is located at default relocate in range, inertia integral is single
Member sends the enabled instruction for being used to indicate the positioning function for reopening locating module to locating module;
Locating module receives enabled instruction, and the positioning function of locating module is reopened according to enabled instruction.
By implementing this optional embodiment, it can also be closed when the positioning function of locating module and inertia integral is single
When member detects that the location information of Intelligent bracelet subsequent time is located in default repositioning range, locating module is reopened
Positioning function.For example, when wear Intelligent bracelet children be in safety zone activity when, close the positioning function of locating module with
This saves power consumption, using the location information of inertia integral unit prediction children's subsequent time, when the location information position of subsequent time
When default relocate in range, the positioning function of locating module is reopened, so that the power consumption of Intelligent bracelet can be saved
Effectively Intelligent bracelet can be positioned again.
As another optional embodiment, the Intelligent bracelet can also include Electromagnetic generation module and power module,
Electromagnetic generation module includes magnet and coil, wherein the information exchange process of the Intelligent bracelet based on speech recognition can also be held
Row following steps:
Electromagnetic generation module obtains the current signal that coil is generated according to the swing of magnet, and current signal is sent to power supply
Module;
Power module receives current signal, and current signal is converted to and the matched electricity of current signal.
It, can also be using the coil in Electromagnetic generation module according to the pendulum of magnet by implementing this optional embodiment
Movable property gives birth to current signal, and current signal is issued power module, so that power module makes when the electricity of Intelligent bracelet exhausts
With the corresponding electricity emergency of the current signal, to improve the user experience.
As another optional embodiment, the Intelligent bracelet can also include Electromagnetic generation module and power module,
Electromagnetic generation module includes magnet and coil, wherein the information exchange process of the Intelligent bracelet based on speech recognition can also be held
Row following steps:
When receiving the third target voice information that target device is returned according to the second target voice information, sound is played
Modular voice plays third target voice information, and sends flashing instruction to indicating lamp module;
Indicating lamp module is flashed according to the indicated flashing mode of flashing instruction.
By implementing this optional embodiment, can also be played using sound broadcasting module voice target device according to
The third target voice information that second target voice information returns, and be used to indicate using indicating lamp module sending and receive third
The flashing of target voice information enriches the functional diversity of Intelligent bracelet.
As another optional embodiment, which can also include bluetooth module, which can be with
Using the MESH technology of bluetooth 5.0, wherein the information exchange process of the Intelligent bracelet based on speech recognition can also be performed following
Step:
Bluetooth module is searched in the signal cover of the bluetooth module with the presence or absence of at least one target device;
When judging that bluetooth module receives the matching instruction of user's input there are when at least one target device, match
Instruction is used to indicate Intelligent bracelet and is matched with several target devices at least one target device;
Bluetooth module matches Intelligent bracelet with several target devices according to the matching instruction, and if obtaining this
The contact details of each target device, contact details can include but is not limited to telephone number and social account in dry target device
Number etc.;
The contact details of the contact details of Intelligent bracelet and each target device are uploaded to background service by bluetooth module
Device, so that the Intelligent bracelet and each target device are established friend relation by background server.
By implementing this optional embodiment, quickly added using the many-to-many equipment communication technology realization of bluetooth module
Plusing good friend carries out social activity convenient for the user of Intelligent bracelet, improves the social experience of the user of Intelligent bracelet, in addition, using blue
The MESH technology of tooth 5.0 can also save the power consumption of bluetooth module.
As it can be seen that by the information exchange process for implementing the Intelligent bracelet based on speech recognition described by Fig. 6, it is real using fitting
The voice recognition mode of dialogue scene, which is realized, in the life of border carries out information transmission automatically by voice, it is not necessary in Intelligent bracelet
The miscellaneous virtual menu and virtual key for being used to carry out information transmission is set on display screen, to reduce intelligent hand
The size of the display screen of ring, thereby reduces the volume of Intelligent bracelet, is more suitable for underage child.
In various embodiments of the present invention, it should be appreciated that magnitude of the sequence numbers of the above procedures are not meant to execute suitable
Successively, the execution sequence of each process should be determined by its function and internal logic the certainty of sequence, without coping with the embodiment of the present invention
Implementation process constitutes any restriction.
In embodiment provided by the present invention, it should be appreciated that " B corresponding with A " indicates that B is associated with A, can be with according to A
Determine B.It is also to be understood that determine that B is not meant to determine B only according to A according to A, it can also be according to A and/or other information
Determine B.
In addition, each functional unit in various embodiments of the present invention can integrate in one processing unit, it is also possible to
Each unit physically exists alone, and can also be integrated in one unit with two or more units.Above-mentioned integrated unit
Both it can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in a retrievable memory of computer.Based on this understanding, technical solution of the present invention substantially or
Person says all or part of of the part that contributes to existing technology or the technical solution, can be in the form of software products
It embodies, which is stored in a memory, including several requests are with so that a computer is set
Standby (can be personal computer, server or network equipment etc., specifically can be the processor in computer equipment) executes
Some or all of each embodiment above method of the invention step.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of storing data.
A kind of Intelligent bracelet based on speech recognition disclosed by the embodiments of the present invention is described in detail above, herein
In apply that a specific example illustrates the principle and implementation of the invention, the explanation of above example is only intended to sides
Assistant solves method and its core concept of the invention;At the same time, for those skilled in the art, think of according to the present invention
Think, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as pair
Limitation of the invention.
Claims (10)
1. a kind of Intelligent bracelet based on speech recognition, which is characterized in that the Intelligent bracelet includes microphone module, detection mould
Block, central processing module and communication module;
The microphone module, the first object voice messaging that the user for obtaining the Intelligent bracelet inputs, and will be described
First object voice messaging is sent to the detection module;
The detection module, the first object voice messaging sent for receiving the microphone module, and described in detection
Whether first object voice messaging matches with default voice messaging;
The central processing module, for detecting the first object voice messaging and the default language when the detection module
When message manner of breathing matches, the second target voice information and the default voice for obtaining user's input of the Intelligent bracelet are believed
Cease corresponding target device;
The communication module, the second target voice information for obtaining the central processing module are sent to the mesh
Marking device.
2. Intelligent bracelet according to claim 1, which is characterized in that the microphone module is for obtaining the intelligent hand
The mode of the first object voice messaging of user's input of ring specifically:
The microphone module, the initial speech information that the user for obtaining the Intelligent bracelet inputs, and judge described first
Whether the corresponding voice amplitudes value of beginning voice messaging is greater than default voice amplitudes value;When judging that the initial speech information is corresponding
Voice amplitudes value when being greater than the default voice amplitudes value, judge the initial speech information corresponding first voice frequency
Whether the second voice spectrum corresponding with noise matches spectrum;When judging first voice spectrum and second voice frequency
When spectrum does not match that, judge whether the corresponding voice signal-to-noise ratio of the initial speech information is greater than default voice signal-to-noise ratio;When sentencing
It is disconnected go out the initial speech information corresponding voice signal-to-noise ratio when being greater than the default voice signal-to-noise ratio, by the initial language
Message breath is determined as first object voice messaging.
3. Intelligent bracelet according to claim 2, it is characterised in that:
The detection module, be also used to it is described receive the first object voice messaging that the microphone module is sent it
Afterwards, pretreatment and speech parameter generation are carried out to the first object voice messaging, obtains the first object voice messaging
Corresponding target mel-frequency cepstrum coefficient;
The detection module has for detecting the mode whether the first object voice messaging matches with default voice messaging
Body are as follows:
The detection module, for being detected using dynamic time warping algorithm using the phonetic feature for presetting voice messaging as foundation
The corresponding target mel-frequency cepstrum coefficient of the first object voice messaging whether the language with the default voice messaging
Sound feature matches.
4. Intelligent bracelet according to claim 3, it is characterised in that:
The detection module is also used to when the language for judging the target mel-frequency cepstrum coefficient Yu the default voice messaging
When sound feature matches, the default voice messaging is updated to the first object voice messaging, and by the default voice
The phonetic feature of information is updated to the corresponding feature of the target mel-frequency cepstrum coefficient;And the triggering central processing unit
Execute the second target voice information and the default voice messaging pair that the user of the acquisition Intelligent bracelet inputs
The target device answered.
5. Intelligent bracelet according to claim 4, which is characterized in that the detection module is used for the first object language
Message breath carries out pretreatment and speech parameter generation, obtains the corresponding target mel-frequency of the first object voice messaging and falls
The mode of spectral coefficient specifically:
The detection module, the voice time domain signal for including to the first object voice messaging carry out Fourier transformation,
Obtain voice frequency domain signal;And calculate the voice frequency domain frequency spectrum of the voice frequency domain signal;And utilize triangle bandpass filter
The voice frequency domain frequency spectrum is filtered, filtered target frequency-domain spectrum is obtained;And calculate the target frequency-domain spectrum
Log spectrum, to the log spectrum carry out long-lost cosine code, obtain target mel-frequency cepstrum coefficient.
6. Intelligent bracelet according to any one of claims 1 to 5, which is characterized in that the Intelligent bracelet further includes inertia
Integration module, in which:
The inertia integration module, for obtaining the motion information of the Intelligent bracelet, the motion information includes at least movement
Directional information and motion velocity information;And the motion velocity information is integrated in conjunction with preset time, obtain with it is described
The travel information that preset time, the motion velocity information match;And in conjunction with the direction of motion information and described
The location information of Intelligent bracelet subsequent time described in travel information prediction.
7. Intelligent bracelet according to claim 6, which is characterized in that the Intelligent bracelet further includes locating module, in which:
The locating module, for obtaining the present bit of the Intelligent bracelet when the unlatching of the positioning function of the locating module
Confidence breath;
The inertia integral unit is also used to detect under the Intelligent bracelet when the positioning function of the locating module is closed
Whether the location information at one moment is located at default relocate in range;When the position for detecting the Intelligent bracelet subsequent time
When information is located in the default repositioning range, it is used to indicate to locating module transmission and reopens the positioning mould
The enabled instruction of the positioning function of block;
The locating module is also used to receive the enabled instruction, and reopens the positioning mould according to the enabled instruction
The positioning function of block.
8. Intelligent bracelet according to claim 7, which is characterized in that the Intelligent bracelet further include Electromagnetic generation module and
Power module, the Electromagnetic generation module includes magnet and coil, in which:
The Electromagnetic generation module, the current signal generated for obtaining the coil according to the swing of the magnet, will be described
Current signal is sent to power module;
The power module is converted to and the current signal for receiving the current signal, and by the current signal
The electricity matched.
9. Intelligent bracelet according to claim 8, which is characterized in that the communication module utilizes protenchyma connected network communication skill
Art realizes communication function.
10. Intelligent bracelet according to claim 9, which is characterized in that the Intelligent bracelet further includes sound broadcasting module
And indicating lamp module, in which:
The sound broadcasting module, for when receive that the target device returns according to the second target voice information the
When three target voice information, voice plays the third target voice information, and sends flashing instruction to the indicating lamp module;
The indicating lamp module, for being flashed according to the indicated flashing mode of the flashing instruction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810958249.1A CN109123927A (en) | 2018-08-22 | 2018-08-22 | A kind of Intelligent bracelet based on speech recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810958249.1A CN109123927A (en) | 2018-08-22 | 2018-08-22 | A kind of Intelligent bracelet based on speech recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109123927A true CN109123927A (en) | 2019-01-04 |
Family
ID=64790589
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810958249.1A Pending CN109123927A (en) | 2018-08-22 | 2018-08-22 | A kind of Intelligent bracelet based on speech recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109123927A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110074519A (en) * | 2019-04-10 | 2019-08-02 | 南京启诺信息技术有限公司 | A kind of language identification bracelet |
CN113517901A (en) * | 2021-04-13 | 2021-10-19 | 深圳市太美亚电子科技有限公司 | Intelligent bracelet of solar intelligent household system and control method thereof |
CN114778648A (en) * | 2022-04-24 | 2022-07-22 | 深圳科瑞德健康科技有限公司 | Test system and measurement method for oxidation-reduction potential value of aqueous solution |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1764933A (en) * | 2003-02-26 | 2006-04-26 | 联邦科学和工业研究组织 | Tracking method and apparatus |
CN203366006U (en) * | 2013-04-22 | 2013-12-25 | 上海与德通讯技术有限公司 | Electronic wristwatch |
US9288301B2 (en) * | 2013-06-20 | 2016-03-15 | Electronics And Telecommunications Research Institute | Smart watch |
CN106128456A (en) * | 2016-06-16 | 2016-11-16 | 美的集团股份有限公司 | The sound control method of intelligent appliance, terminal and system |
CN107728184A (en) * | 2017-12-04 | 2018-02-23 | 紫光股份有限公司 | A kind of global location device with inertial sensor auxiliary positioning |
US20180103311A1 (en) * | 2016-10-12 | 2018-04-12 | FuelStation Inc. | Wearable system configured to receive audio signals through dock |
CN108134870A (en) * | 2017-12-12 | 2018-06-08 | 北京小米移动软件有限公司 | Method for sending voice message and device |
-
2018
- 2018-08-22 CN CN201810958249.1A patent/CN109123927A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1764933A (en) * | 2003-02-26 | 2006-04-26 | 联邦科学和工业研究组织 | Tracking method and apparatus |
CN203366006U (en) * | 2013-04-22 | 2013-12-25 | 上海与德通讯技术有限公司 | Electronic wristwatch |
US9288301B2 (en) * | 2013-06-20 | 2016-03-15 | Electronics And Telecommunications Research Institute | Smart watch |
CN106128456A (en) * | 2016-06-16 | 2016-11-16 | 美的集团股份有限公司 | The sound control method of intelligent appliance, terminal and system |
US20180103311A1 (en) * | 2016-10-12 | 2018-04-12 | FuelStation Inc. | Wearable system configured to receive audio signals through dock |
CN107728184A (en) * | 2017-12-04 | 2018-02-23 | 紫光股份有限公司 | A kind of global location device with inertial sensor auxiliary positioning |
CN108134870A (en) * | 2017-12-12 | 2018-06-08 | 北京小米移动软件有限公司 | Method for sending voice message and device |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110074519A (en) * | 2019-04-10 | 2019-08-02 | 南京启诺信息技术有限公司 | A kind of language identification bracelet |
CN113517901A (en) * | 2021-04-13 | 2021-10-19 | 深圳市太美亚电子科技有限公司 | Intelligent bracelet of solar intelligent household system and control method thereof |
CN114778648A (en) * | 2022-04-24 | 2022-07-22 | 深圳科瑞德健康科技有限公司 | Test system and measurement method for oxidation-reduction potential value of aqueous solution |
CN114778648B (en) * | 2022-04-24 | 2023-10-31 | 深圳科瑞德健康科技有限公司 | System and method for testing oxidation-reduction potential value of aqueous solution |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11974207B2 (en) | Modular emergency communication flow management system | |
CN107680597B (en) | Audio recognition method, device, equipment and computer readable storage medium | |
US11178275B2 (en) | Method and apparatus for detecting abnormality of caller | |
CN110534099A (en) | Voice wakes up processing method, device, storage medium and electronic equipment | |
US9462444B1 (en) | Cloud based collaborative mobile emergency call initiation and handling distribution system | |
JP4558074B2 (en) | Telephone communication terminal | |
CN109123927A (en) | A kind of Intelligent bracelet based on speech recognition | |
CN107613144A (en) | Automatic call method, device, storage medium and mobile terminal | |
CN104040480A (en) | Methods and systems for searching utilizing acoustical context | |
CN104969289A (en) | Voice trigger for a digital assistant | |
CN108597176A (en) | A kind of safe early warning method and wearable device based on wearable device | |
CN109646258A (en) | A kind of blind-guiding stick, blind guiding system and blind-guiding method | |
CN106128475A (en) | Wearable intelligent safety equipment based on abnormal emotion speech recognition and control method | |
CN103002425A (en) | Method and system for automatically triggering emergency calls and mobile terminal | |
JP2009061547A (en) | Robot control system, robot, program, and information storage medium | |
CN107506166A (en) | Information cuing method and device, computer installation and readable storage medium storing program for executing | |
US20190286480A1 (en) | Electronic device and server for processing data received from electronic device | |
US11521621B2 (en) | Gathering user's speech samples | |
KR20180113075A (en) | Method and device for generating natural language expression by using framework | |
KR20180109631A (en) | Electronic device and method for executing function of electronic device | |
CN107666536A (en) | A kind of method and apparatus for finding terminal, a kind of device for being used to find terminal | |
JP2018025855A (en) | Information processing server, information processing device, information processing system, information processing method, and program | |
CN109451385A (en) | A kind of based reminding method and device based on when using earphone | |
KR102419728B1 (en) | A system for determining an action based on a situation, a vehicle for performing the action, and a method thereof | |
CN107483724A (en) | The triggering method of mobile terminal and its contextual model, computer-readable recording medium |
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: 20190104 |
|
RJ01 | Rejection of invention patent application after publication |