CN105788599B - Method of speech processing, router and intelligent sound control system - Google Patents

Method of speech processing, router and intelligent sound control system Download PDF

Info

Publication number
CN105788599B
CN105788599B CN201610230741.8A CN201610230741A CN105788599B CN 105788599 B CN105788599 B CN 105788599B CN 201610230741 A CN201610230741 A CN 201610230741A CN 105788599 B CN105788599 B CN 105788599B
Authority
CN
China
Prior art keywords
router
controlled
control equipment
voice
voice signal
Prior art date
Application number
CN201610230741.8A
Other languages
Chinese (zh)
Other versions
CN105788599A (en
Inventor
周瑜
李敬
王林章
Original Assignee
北京小米移动软件有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京小米移动软件有限公司 filed Critical 北京小米移动软件有限公司
Priority to CN201610230741.8A priority Critical patent/CN105788599B/en
Publication of CN105788599A publication Critical patent/CN105788599A/en
Application granted granted Critical
Publication of CN105788599B publication Critical patent/CN105788599B/en

Links

Abstract

The disclosure is directed to a kind of method of speech processing, router and intelligent sound control systems, this method comprises: router receives multiple voice signals that multiple voice capture devices are sent, router determines maximum first voice signal of signal strength from the multiple voice signal, and dissection process is carried out to first voice signal, determine the corresponding control equipment to be controlled of first voice signal and operational order;The operational order is sent to the control equipment to be controlled by router, so that the control equipment to be controlled executes corresponding operation according to the operational order.Scheme provided by the disclosure enables to intelligent sound control no longer to be limited by distance, and no matter the distance between user and smart machine are remote or close, can realize the voice control to smart machine.

Description

Method of speech processing, router and intelligent sound control system

Technical field

This disclosure relates to field of intelligent control technology, in particular to a kind of method of speech processing, router and intelligent sound Control system.

Background technique

Current smart machine in use, mostly uses greatly voice to carry out operation control.User issues voice control After information, smart machine acquires voice signal and executes corresponding operation according to voice signal.

In the related technology, when smart machine carries out voice collecting, it is desirable that the distance between user and smart machine meet one Fixed condition, user necessarily are in from the closer position of smart machine and issue voice signal.If user and smart machine it Between distance it is excessive, smart machine can not then collect voice signal, so as to cause voice operating failure.

Summary of the invention

The embodiment of the present disclosure provides a kind of method of speech processing, router and intelligent sound control system.The technology Scheme is as follows:

According to the first aspect of the embodiments of the present disclosure, a kind of method of speech processing is provided, this method comprises:

Router receives multiple voice signals that multiple voice capture devices are sent, and the multiple voice signal corresponds to identical Speech source;

The router determines the first voice signal, first voice according to the signal strength of the multiple voice signal Signal is the maximum signal of signal strength in the multiple voice signal;

The router to first voice signal carry out dissection process, determine first voice signal it is corresponding to Control equipment and operational order;

The operational order is sent to the control equipment to be controlled by the router, so that the control equipment to be controlled is according to institute It states operational order and executes corresponding operation.

Further, the multiple voice capture device is uniformly distributed in the control equipment region to be controlled.

Further, the control equipment to be controlled is multiple;The operational order is sent to described to be controlled by the router Control equipment, so that the control equipment to be controlled executes corresponding operation according to the operational order, comprising:

The operational order is sent respectively to multiple control equipments to be controlled by the router, so that the multiple control equipment Corresponding operation is executed according to the operational order respectively.

Further, the method also includes:

The control equipment to be controlled is multiple;The operational order is sent to the control equipment to be controlled by the router, with The control equipment to be controlled is set to execute corresponding operation according to the operational order, comprising:

The operational order is sent respectively to multiple control equipments to be controlled by the router, so that the multiple control equipment Corresponding operation is executed according to the operational order respectively.

Further, the router determines the first voice signal according to the signal strength of the multiple voice signal, packet It includes:

The router carries out calculating analysis to the multiple voice signal, by signal energy in the multiple voice signal Maximum voice signal is determined as first voice signal.

Further, before the router receives multiple voice signals that multiple voice capture devices are sent, further includes:

The router receives the registration request that the multiple voice capture device is sent;

The registration request that the router is sent according to the multiple voice capture device is set with the multiple voice collecting It is standby to establish network connection.

It further, include the matchmaker of each voice capture device in the registration request that the multiple voice capture device is sent Body access control MAC addresses information;The registration request that the router is sent according to the multiple voice capture device with it is described Multiple voice capture devices establish network connection, comprising:

The MAC Address of each voice capture device of router records;

The router is carried out by the MAC Address of the multiple voice capture device and the multiple voice capture device Network connection.

Further, first voice signal is sent to before the control equipment to be controlled by the router, further includes:

The router receives the registration request that the control equipment to be controlled is sent;

The registration request and the control equipment to be controlled that the router is sent according to the control equipment to be controlled are established network and are connected It connects.

It further, include the MAC Address letter of the control equipment to be controlled in the registration request that the control equipment to be controlled is sent Breath;The registration request and the control equipment to be controlled that the router is sent according to the control equipment to be controlled are established and are connected to the network, packet It includes:

The MAC Address of control equipment to be controlled described in the router records;

The router is connected to the network by the MAC Address of the control equipment to be controlled with the control equipment to be controlled.

Further, language is transmitted by Wireless Fidelity WI-FI between the multiple voice capture device and the router Sound signal passes through WI-FI transmission of speech signals between the router and the control equipment to be controlled.

According to the second aspect of an embodiment of the present disclosure, a kind of router is provided, which includes:

First receiving module is configured as receiving multiple voice signals that multiple voice capture devices are sent, the multiple Voice signal corresponds to identical speech source;

First determining module is configured as determining the first voice signal according to the signal strength of the multiple voice signal, First voice signal is the maximum signal of signal strength in the multiple voice signal;

Second determining module is configured as carrying out dissection process to first voice signal, determines first voice The corresponding control equipment to be controlled of signal and operational order;

First sending module is configured as the operational order being sent to the control equipment to be controlled, so that described to be controlled Control equipment executes corresponding operation according to the operational order.

According to the third aspect of an embodiment of the present disclosure, a kind of router is provided, which includes:

Processor;

For storing the memory of the executable instruction of the processor;

Wherein, the processor is configured to:

Multiple voice signals that multiple voice capture devices are sent are received, the multiple voice signal corresponds to identical voice Source;

The first voice signal is determined according to the signal strength of the multiple voice signal, and first voice signal is described The maximum signal of signal strength in multiple voice signals;

To first voice signal carry out dissection process, determine the corresponding control equipment to be controlled of first voice signal with And operational order;

The operational order is sent to the control equipment to be controlled, so that the control equipment to be controlled is according to the operational order Execute corresponding operation.

According to a fourth aspect of embodiments of the present disclosure, a kind of intelligent sound control system is provided, which includes aforementioned Router, multiple voice capture devices and at least one control equipment to be controlled, wherein the control equipment to be controlled be with calculating The smart machine of processing capacity.

The technical solution that the embodiment of the present disclosure provides can include the following benefits: by by multiple voice capture devices Connect with router with smart machine, when user issue voice when, no matter which kind of position user is in, can by with its away from From the signal that nearest voice capture device collects maximum intensity, which can be by router after router dissection process It is sent to corresponding smart machine, smart machine executes corresponding operation further according to operational order included in the signal.From And the voice control for smart machine of user is not limited by distance.

It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not The disclosure can be limited.

Detailed description of the invention

The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure Example, and together with specification for explaining the principles of this disclosure.

Fig. 1 be this disclosure relates to intelligent sound control system architecture diagram;

Fig. 2 is a kind of flow chart of method of speech processing shown according to an exemplary embodiment;

Fig. 3 is a kind of flow chart of the method for speech processing shown according to another exemplary embodiment;

Fig. 4 is a kind of flow chart of the method for speech processing shown according to a further exemplary embodiment;

Fig. 5 is a kind of flow chart of the method for speech processing shown according to a further exemplary embodiment;

Fig. 6 is a kind of block diagram of router shown according to an exemplary embodiment;

Fig. 7 is a kind of block diagram of router shown according to an exemplary embodiment;

Fig. 8 is a kind of block diagram of router shown according to an exemplary embodiment;

Fig. 9 is a kind of block diagram of router shown according to an exemplary embodiment;

Figure 10 is a kind of block diagram of router shown according to an exemplary embodiment;

Figure 11 is a kind of block diagram of router shown according to an exemplary embodiment;

Figure 12 is a kind of block diagram of router shown according to an exemplary embodiment;

Figure 13 is a kind of block diagram of router shown according to an exemplary embodiment;

Figure 14 is a kind of block diagram of the entity of router shown according to an exemplary embodiment;

Figure 15 is the block diagram of router 1900 shown according to an exemplary embodiment.

Through the above attached drawings, it has been shown that the specific embodiment of the disclosure will be hereinafter described in more detail.These attached drawings It is not intended to limit the scope of this disclosure concept by any means with verbal description, but is by referring to specific embodiments Those skilled in the art illustrate the concept of the disclosure.

Specific embodiment

Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.

Smart machine refers to the equipment with calculation processing ability, such as smart phone, intelligent robot, intelligent sound box Deng.Smart machine provides multiple control modes for user, such as by pressing key control, by smart machine on smart machine Touch manner control, by voice control etc..Wherein, voice control mode is since convenient and efficient advantage is as many users First choice.

As previously mentioned, in the existing technology by voice control smart machine, to the distance between user and smart machine It is required that stringenter.It, will be due to apart from too far and language can not be passed through when user is located at bedroom for example, in one family Sound closes the intelligent sound box in parlor.

The disclosure is based on this, proposes that one kind can not be by the method for the voice control smart machine that distance is limited, this method Applied in the intelligent sound control system as composed by multiple voice capture devices, router and smart machine.By means of Multiple voice capture devices and router in the system, no matter user is how far at a distance from smart machine, as long as user Sound can be collected by one of voice capture device, user can easily complete the control of smart machine.

Fig. 1 be this disclosure relates to intelligent sound control system architecture diagram, as shown in Figure 1, the intelligent sound control system In system include multiple voice capture devices, router and smart machine, wherein smart machine specifically can be smart phone, Intelligent robot, intelligent sound box etc..Voice capture device and smart machine all have a network access facility, voice capture device with The forwarding and processing of voice signal are carried out between smart machine by router.

As long as the speech-controlled information that user is issued can be collected by any one voice capture device, so that it may logical It crosses voice capture device and is sent to router, then be forwarded on corresponding smart machine by router.And if user distance Smart machine is closer, and smart machine oneself can receive and identify the speech-controlled information of user, then does not need to adopt by voice Collection equipment and router are acquired and forward.

Fig. 2 is a kind of flow chart of method of speech processing shown according to an exemplary embodiment, and this method is applied to upper It states in intelligent sound control system.As shown in Fig. 2, the method for speech processing may include the following steps:

In a step 101, router receives multiple voice signals that multiple voice capture devices are sent, multiple voice letter Number corresponding identical speech source.

Multiple voice capture devices are located at the different location of intelligent sound control system region, it is assumed for example that the intelligence Speech control system is arranged in one family, then multiple voice capture devices can be located at the different location in family.

After user issues voice, voice signal can be all received positioned at multiple voice capture devices of different location, and The voice signal is sent to router.

Wherein, voice capture device can have any equipment of voice input and playing function for microphone, loudspeaker etc., The disclosure is without limitation.

In a step 102, router determines the first voice signal according to the signal strength of multiple voice signals.

Wherein, the first voice signal is the maximum signal of signal strength in above-mentioned multiple voice signals.

Since multiple voice capture devices are located at the different location of intelligent sound control system region, when user issues After voice, each voice capture device the quality of collected voice signal may be different.The language closer from user The quality that sound acquires the collected voice signal of equipment institute is higher, on the contrary lower.When multiple voice capture devices will be adopted The voice signal collected is all sent to after router, and router needs to screen these voice signals, therefrom selects language The voice signal of sound signal maximum intensity, to more accurately extract effective control information therein.

In step 103, router carries out dissection process to above-mentioned first voice signal, determines that the first voice signal is corresponding Control equipment and operational order to be controlled.

After router identifies signal strength maximum voice signal, this voice signal can further be solved Analysis, therefrom parses control object corresponding to this voice signal.For example, when the voice that user is sent out is " to close parlor When speaker ", router can parse the voice, so that it is determined that the object of this voice control is " speaker in parlor ", with And this operation is " closing ".

Wherein, above-mentioned control equipment to be controlled is the object of this secondary control, and control equipment to be controlled can be intelligent sound control system Any smart machine in system.

At step 104, aforesaid operations instruction is sent to above-mentioned control equipment to be controlled by router, to be controlled is set up so that above-mentioned For according to the corresponding operation of aforesaid operations instruction execution.

Assuming that the voice that user initially issues is " speaker for closing parlor ", after processing above-mentioned, router is Know that the voice is to be directed to " speaker in parlor ", and the operation executed is " closing ", therefore, router " will directly can close Closing " this operational order is sent to " speaker in parlor " this control equipment to be controlled.

In the present embodiment, by connecting multiple voice capture devices and router with smart machine, when user issues language When sound, no matter which kind of position user is in, can be by collecting maximum intensity apart from nearest voice capture device with it Signal, which can be sent to corresponding smart machine by router after router dissection process, smart machine root again Corresponding operation is executed according to operational order included in the signal.So that the voice control for smart machine of user It is not limited by distance.

In another embodiment, above-mentioned multiple voice capture devices are uniformly distributed in above-mentioned control equipment region to be controlled.

For example, above-mentioned control equipment to be controlled is located in one family, i.e., the intelligent sound within the scope of one family controls system In system, above-mentioned multiple voice capture devices can be evenly distributed on two of parlor in the different zones of this family, such as the family Side, each bedroom, toilet, can one voice capture device of each distribution in kitchen.Such distribution can guarantee no matter user Any position in the family nearby has the voice collecting that can collect larger intensity voice signal to set It is standby, to guarantee that the instruction that user is issued can correctly be executed by control equipment to be controlled.

On the basis of the above embodiments, the present embodiment is related to processing method when control equipment to be controlled is multiple.That is, if When 103 control equipments to be controlled determined are multiple control equipments to be controlled through the above steps, then the specific execution of above-mentioned steps 104 Process are as follows:

Aforesaid operations instruction is sent respectively to multiple control equipments to be controlled by router, so that multiple control equipment distinguishes root Corresponding operation is executed according to the operational order.

For example, it is assumed that the voice that user issues is " to close visitor in intelligent sound control system within the scope of one family The speaker and lamp in the Room ", then router will recognise that " speaker " and " lamp " the two control equipments to be controlled when identifying the voice, this When, router can send respectively " closing " this operational order to " speaker in parlor " and " lamp in parlor "." speaker in parlor " " lamp in parlor " can all execute shutoff operation after receiving this operational order.

In the present embodiment, router can be parsed out multiple control equipments to be controlled in user speech, and make to be controlled set up It is standby to be performed simultaneously corresponding operation, to improve the efficiency of voice control and execution.

Fig. 3 is a kind of flow chart of the method for speech processing shown according to another exemplary embodiment, as shown in figure 3, After above-mentioned steps 104, further includes:

In step 105, router receives the second voice signal that control equipment to be controlled is sent.

Wherein, the second voice signal is control equipment to be controlled in executing operating process or execution operation terminates rear line and returns The feedback signal returned.For example, if user has issued the voice of " lamp for closing parlor ", when " lamp in parlor " has executed closing behaviour After work, the feedback information of " being turned off completion " can be returned to user.Control equipment to be controlled can send that information to router.

In step 106, router determines corresponding first voice capture device of the first voice signal.

In step 107, above-mentioned second voice signal is sent to the first voice capture device by router.

After router receives this feedback signal of the second voice signal, judge which source language this signal is for The feedback of sound signal, and then the sending device of source voice signal, i.e. the first voice capture device can be determined according to source voice signal, Voice capture device namely nearest from user.Second voice signal this feedback signal can be sent to source in turn by router The sending device of voice signal is simultaneously played out by the sending device.

In the present embodiment, router is made by the way that feedback signal to be returned to the voice capture device of sending source voice signal It obtains feedback signal only to play in a voice capture device nearest from user, to both can guarantee that user heard instead in time Feedforward information, while extra noise will not be generated again.

On the basis of the above embodiments, the present embodiment is related to router determining first voice letter from multiple voice signals Number specific method.That is above-mentioned steps 102 specifically:

Router carries out calculating analysis to multiple voice signals, and the maximum voice of signal energy in multiple voice signals is believed Number be used as the first voice signal.I.e. router determines the intensity of signal by calculating the signal energy of each voice signal, this The computational efficiency of kind method is high and more accurate for the judgement of signal strength.

On the basis of the above embodiments, the present embodiment is related to the process that voice capture device is registered on the router, that is, Fig. 4 is a kind of flow chart of the method for speech processing shown according to a further exemplary embodiment, as shown in figure 4, in above-mentioned steps Before 101, further includes:

In step 201, router receives the registration request that multiple voice capture devices are sent.

In step 202, the registration request that router is sent according to multiple voice capture devices is set with multiple voice collectings It is standby to establish network connection.

Before voice capture device transmits data between router, need to register in the router first, Cai Nengyu Network connection is set up between router.After establishment of the network connection, the ability of voice signal transmitted by voice capture device It is received and processed by router.

In a kind of possible embodiment, multiple voice capture devices are respectively by the media access control (Media of oneself Access Control, abbreviation MAC) address carrying is in the registration request.Then in above-mentioned steps 202, routing implement body can be first The MAC Address for first recording each voice capture device is established network further according to the MAC Address and each voice capture device and is connected It connects.

Router can also in other way, such as the mark of voice capture device is established with voice capture device Network connection.Voice capture device can carry the device identification of oneself in the registration request, and router is subsequent can basis The device identification carries out data transmission between voice capture device.For following control equipments to be controlled, this can also be passed through Kind mode is transmitted to carry out registration and data.

On the basis of the above embodiments, the present embodiment is related to the process that control equipment to be controlled is registered on the router, that is, figure 5 be a kind of flow chart of the method for speech processing shown according to a further exemplary embodiment, as shown in figure 5, in above-mentioned steps 104 Before, further includes:

In step 301, router receives the registration request that control equipment to be controlled is sent.

In step 302, the registration request and control equipment to be controlled that router is sent according to control equipment to be controlled establish network company It connects.

It before control equipment to be controlled transmits data between router, needs to register in the router first, ability and road By setting up network connection between device.After establishment of the network connection, control equipment to be controlled could receive the control of router transmission Information simultaneously sends feedback information to router.

In a kind of possible embodiment, control equipment to be controlled carries the MAC Address of oneself in the registration request.On then State in step 302, routing implement body can record the MAC Address of control equipment to be controlled first, further according to the MAC Address with it is to be controlled Equipment establishes network connection.

It should be noted that the control equipment to be controlled in the above method can be any intelligence in intelligent sound control system Equipment, therefore, above-mentioned control equipment to be controlled can also have multiple, and upon logging, each control equipment to be controlled can send respectively request and disappear It ceases to router, network connection is established between router.

Further, after establishing network connection between voice capture device and router, Wireless Fidelity can be passed through (Wireless Fidelity, abbreviation WI-FI) transmission of speech signals.Wherein, voice capture device can built-in WI-FI processing Module, for supporting WI-FI connection and data to transmit.In addition, when establishing network connection between control equipment to be controlled and router Afterwards, WI-FI transmission of speech signals can be passed through.Wherein, in control equipment to be controlled can also built-in WI-FI processing module, be used to branch Hold WI-FI connection and data transmission.

In the present embodiment, passed between voice capture device and router and router and control equipment to be controlled by WI-FI Defeated voice signal.WI-FI has in transmission speed and has great advantage as the transmission technology being applied in WLAN, Therefore, data are transmitted using WI-FI in the present embodiment, the transmission speed of voice signal can be made to be increased dramatically, from And smart machine is enabled quickly to receive and process the speech-controlled information of user.

Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.It is real for disclosure device Undisclosed details in example is applied, embodiments of the present disclosure is please referred to.

Fig. 6 is a kind of block diagram of router shown according to an exemplary embodiment, as shown in fig. 6, the router can be with Include:

First receiving module 601 is configured as receiving multiple voice signals that multiple voice capture devices are sent, multiple Voice signal corresponds to identical speech source.

First determining module 602 is configured as determining that the first voice is believed according to the signal strength of above-mentioned multiple voice signals Number, which is the maximum signal of signal strength in above-mentioned multiple voice signals.

Second determining module 603 is configured as carrying out dissection process to the first voice signal, determines the first voice signal pair The control equipment and operational order to be controlled answered.

First sending module 604, be configured as by aforesaid operations instruct be sent to above-mentioned control equipment to be controlled so that it is above-mentioned to Equipment is controlled according to the corresponding operation of aforesaid operations instruction execution.

Further, above-mentioned multiple voice capture devices are uniformly distributed in above-mentioned control equipment region to be controlled.

Fig. 7 is a kind of block diagram of router shown according to an exemplary embodiment, to be controlled is set up as shown in fig. 7, above-mentioned It is standby be it is multiple, the first sending module 604 includes:

First sending submodule 6041 is configured as aforesaid operations instruction being sent respectively to multiple control equipments to be controlled, with Make multiple control equipment respectively according to the corresponding operation of aforesaid operations instruction execution.

Fig. 8 is a kind of block diagram of router shown according to an exemplary embodiment, as shown in figure 8, the router also wraps It includes:

Second receiving module 605 is configured as receiving the second voice signal that control equipment to be controlled is sent.

Third determining module 606 is configured to determine that corresponding first voice capture device of the first voice signal.

Second sending module 607 is configured as the second voice signal being sent to the first voice capture device.

Fig. 9 is a kind of block diagram of router shown according to an exemplary embodiment, as shown in figure 9, the first determining module 602 include:

First determines submodule 6021, is configured as carrying out calculating analysis to multiple voice signals, by multiple voice signals The middle maximum voice signal of signal energy is determined as the first voice signal.

Figure 10 is a kind of block diagram of router shown according to an exemplary embodiment, and as shown in Figure 10, the router is also Include:

Third receiving module 608 is configured as receiving the more of multiple voice capture devices transmissions in the first receiving module 601 Before a voice signal, the registration request that multiple voice capture devices are sent is received.

First establishes module 609, is configured as the registration request and multiple voices sent according to multiple voice capture devices It acquires equipment and establishes network connection.

Figure 11 is a kind of block diagram of router shown according to an exemplary embodiment, and as shown in figure 11, multiple voices are adopted Collect the mac address information in the registration request that equipment is sent including each voice capture device, first, which establishes module 609, includes:

First record sub module 6091 is configured as recording the MAC Address of multiple voice capture devices.

First connection submodule 6092, is configured as adopting by the MAC Address of multiple voice capture devices with multiple voices Collection equipment is connected to the network.

Figure 12 is a kind of block diagram of router shown according to an exemplary embodiment, and as shown in figure 12, the router is also Include:

4th receiving module 610, be configured as sending module 604 by the first voice signal be sent to control equipment to be controlled it Before, receive the registration request that control equipment to be controlled is sent.

Second establishes module 611, and the registration request and control equipment to be controlled for being configured as being sent according to control equipment to be controlled are established Network connection.

Figure 13 is a kind of block diagram of router shown according to an exemplary embodiment, and as shown in figure 13, second establishes mould Block 611 includes:

Second record sub module 6111 is configured as recording the MAC Address of control equipment to be controlled.

Second connection submodule 6112, is configured as the MAC Address and control equipment to be controlled by multiple voice capture devices It is connected to the network.

Further, pass through WI-FI transmission of speech signals between multiple voice capture devices and router.

Further, pass through WI-FI transmission of speech signals between router and control equipment to be controlled.

In conclusion the router that the disclosure provides, is believed by receiving the voice that multiple voice capture devices are sent respectively Number, top-quality voice signal is therefrom selected, and dissection process is carried out to the voice signal, identifies that the voice signal is corresponding Control equipment to be controlled and the equipment is controlled so that no matter user is how far from smart machine, can realize pair The control of smart machine.

About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method Embodiment in be described in detail, no detailed explanation will be given here.

Figure 14 is a kind of block diagram of the entity of router shown according to an exemplary embodiment, as shown in figure 14, the road It include: memory 91 and processor 92 by device.

Memory 91 is used for the executable instruction of storage processor 92.

Processor 92 is configured as:

Multiple voice signals that multiple voice capture devices are sent are received, the multiple voice signal corresponds to identical voice Source;

The first voice signal is determined according to the signal strength of the multiple voice signal, and first voice signal is described The maximum signal of signal strength in multiple voice signals;

To first voice signal carry out dissection process, determine the corresponding control equipment to be controlled of first voice signal with And operational order;

The operational order is sent to the control equipment to be controlled, so that the control equipment to be controlled is according to the operational order Execute corresponding operation.

In the embodiment of above-mentioned router, it should be appreciated that processor 92 can be central processing submodule (English: Central Processing Unit, referred to as: CPU), can also be other general processors, digital signal processor (English: Digital Signal Processor, referred to as: DSP), specific integrated circuit (English: Application Specific Integrated Circuit, referred to as: ASIC) etc..General processor can be microprocessor or the processor is also possible to Any conventional processor etc., and memory above-mentioned can be read-only memory (English: read-only memory, abbreviation: ROM), random access memory (English: random access memory, abbreviation: RAM), flash memory, hard disk or solid State hard disk.SIM card is also referred to as subscriber identification card, smart card, and digital mobile telephone must load onto this card and can use.I.e. Store the information of digital mobile phone client on computer chip, the contents such as telephone directory of the key of encryption and user.Knot The step of closing method disclosed in the embodiment of the present disclosure can be embodied directly in hardware processor and execute completion, or use processor In hardware and software module combination execute completion.

Figure 15 is the block diagram of router 1900 shown according to an exemplary embodiment.Referring to Fig.1 5, router 1900 wraps Processing component 1922 is included, further comprises one or more processors and memory represented by a memory 1932 money Source, can be by the instruction of the execution of processing component 1922, such as application program for storing.The application journey stored in memory 1932 Sequence may include it is one or more each correspond to one group of instruction module.In addition, processing component 1922 is configured To execute instruction, to execute the above method.

Router 1900 can also include that a power supply module 1926 is configured as executing the power management of router 1900, One wired or wireless network interface 1950 is configured as router 1900 being connected to network and an input and output (I/O) Interface 1958.

In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided It such as include the memory 1932 of instruction, above-metioned instruction can be executed by the processing component 1922 of router 1900 to complete above-mentioned side Method.For example, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, magnetic Band, floppy disk and optical data storage devices etc..

A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by router 1900 When managing device execution, so that router 1900 is able to carry out a kind of method of speech processing.The described method includes:

Router receives multiple voice signals that multiple voice capture devices are sent, and the multiple voice signal corresponds to identical Speech source;

The router determines the first voice signal, first voice according to the signal strength of the multiple voice signal Signal is the maximum signal of signal strength in the multiple voice signal;

The router to first voice signal carry out dissection process, determine first voice signal it is corresponding to Control equipment and operational order;

The operational order is sent to the control equipment to be controlled by the router, so that the control equipment to be controlled is according to institute It states operational order and executes corresponding operation.

The embodiment of the present disclosure also provides a kind of intelligent sound control system, which includes road above-mentioned By device, multiple voice capture devices and at least one control equipment to be controlled, wherein the control equipment to be controlled is with calculation processing The smart machine of ability.

Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following Claim is pointed out.

It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.

Claims (20)

1. a kind of method of speech processing characterized by comprising
Router receives multiple voice signals that multiple voice capture devices are sent, and the multiple voice signal corresponds to identical language Source of sound;
The router determines the first voice signal, first voice signal according to the signal strength of the multiple voice signal For the maximum signal of signal strength in the multiple voice signal, wherein the voice capture device is closer from institute's speech source, Collected voice signal quality it is higher, the signal strength of the voice signal is bigger;
The router carries out dissection process to first voice signal, determines that first voice signal is corresponding to be controlled Equipment and operational order;
The operational order is sent to the control equipment to be controlled by the router, so that the control equipment to be controlled is according to the behaviour Make the corresponding operation of instruction execution;
The method also includes:
The router receives the second voice signal that the control equipment to be controlled is sent;
The router determines corresponding first voice capture device of first voice signal;
Second voice signal is sent to first voice capture device by the router.
2. the method according to claim 1, wherein the multiple voice capture device is in the control equipment to be controlled It is uniformly distributed in region.
3. the method according to claim 1, wherein the control equipment to be controlled is multiple;The router is by institute It states operational order and is sent to the control equipment to be controlled, so that the control equipment to be controlled executes corresponding behaviour according to the operational order Make, comprising:
The operational order is sent respectively to multiple control equipments to be controlled by the router, so that the multiple control equipment is distinguished Corresponding operation is executed according to the operational order.
4. the method according to claim 1, wherein signal of the router according to the multiple voice signal Intensity determines the first voice signal, comprising:
The router carries out calculating analysis to the multiple voice signal, and signal energy in the multiple voice signal is maximum Voice signal be determined as first voice signal.
5. the method according to claim 1, wherein the router receives what multiple voice capture devices were sent Before multiple voice signals, further includes:
The router receives the registration request that the multiple voice capture device is sent;
The registration request that the router is sent according to the multiple voice capture device is built with the multiple voice capture device Vertical network connection.
6. according to the method described in claim 5, it is characterized in that, in the registration request that the multiple voice capture device is sent MAC address information including each voice capture device;The router is according to the multiple voice collecting The registration request and the multiple voice capture device that equipment is sent, which are established, to be connected to the network, comprising:
The MAC Address of each voice capture device of router records;
The router carries out network by the MAC Address of the multiple voice capture device and the multiple voice capture device Connection.
7. the method according to claim 1, wherein first voice signal is sent to institute by the router Before stating control equipment to be controlled, further includes:
The router receives the registration request that the control equipment to be controlled is sent;
The registration request and the control equipment to be controlled that the router is sent according to the control equipment to be controlled are established and are connected to the network.
8. the method according to the description of claim 7 is characterized in that including institute in the registration request that the control equipment to be controlled is sent State the mac address information of control equipment to be controlled;Registration request that the router is sent according to the control equipment to be controlled and it is described to It controls equipment and establishes network connection, comprising:
The MAC Address of control equipment to be controlled described in the router records;
The router is connected to the network by the MAC Address of the control equipment to be controlled with the control equipment to be controlled.
9. method according to claim 1-8, which is characterized in that the multiple voice capture device and the road By, by Wireless Fidelity WI-FI transmission of speech signals, passing through WI-FI between the router and the control equipment to be controlled between device Transmission of speech signals.
10. a kind of router, which is characterized in that the router includes:
First receiving module is configured as receiving multiple voice signals that multiple voice capture devices are sent, the multiple voice Signal corresponds to identical speech source;
First determining module is configured as determining the first voice signal according to the signal strength of the multiple voice signal, described First voice signal is the maximum signal of signal strength in the multiple voice signal, wherein the voice capture device is from institute Speech source is closer, collected voice signal quality it is higher, the signal strength of the voice signal is bigger;
Second determining module is configured as carrying out dissection process to first voice signal, determines first voice signal Corresponding control equipment to be controlled and operational order;
First sending module is configured as the operational order being sent to the control equipment to be controlled, to be controlled sets up so that described It is standby that corresponding operation is executed according to the operational order;
Second receiving module is configured as receiving the second voice signal that the control equipment to be controlled is sent;
Third determining module is configured to determine that corresponding first voice capture device of first voice signal;
Second sending module is configured as second voice signal being sent to first voice capture device.
11. router according to claim 10, which is characterized in that the multiple voice capture device is described to be controlled Equipment is uniformly distributed in region.
12. router according to claim 10, which is characterized in that the control equipment to be controlled is multiple;First hair The module is sent to include:
First sending submodule is configured as the operational order being sent respectively to the multiple control equipment to be controlled, so that institute It states multiple control equipment and corresponding operation is executed according to the operational order respectively.
13. router according to claim 10, which is characterized in that first determining module includes:
First determines submodule, is configured as carrying out calculating analysis to the multiple voice signal, by the multiple voice signal The middle maximum voice signal of signal energy is determined as first voice signal.
14. router according to claim 10, which is characterized in that further include:
Third receiving module is configured as receiving multiple voices that multiple voice capture devices are sent in first receiving module Before signal, the registration request that the multiple voice capture device is sent is received;
First establishes module, is configured as the registration request and the multiple voice sent according to the multiple voice capture device It acquires equipment and establishes network connection.
15. router according to claim 14, which is characterized in that the registration that the multiple voice capture device is sent is asked It include the mac address information of each voice capture device in asking;Described first, which establishes module, includes:
First record sub module is configured as recording the MAC Address of the multiple voice capture device;
First connection submodule, is configured as adopting by the MAC Address of the multiple voice capture device with the multiple voice Collection equipment is connected to the network.
16. router according to claim 10, which is characterized in that further include:
4th receiving module is configured as being sent to first voice signal in first sending module described to be controlled Before equipment, the registration request that the control equipment to be controlled is sent is received;
Second establishes module, is configured as the registration request sent according to the control equipment to be controlled and the control equipment to be controlled is established Network connection.
17. router according to claim 16, which is characterized in that wrapped in the registration request that the control equipment to be controlled is sent Include the mac address information of the control equipment to be controlled;Described second, which establishes module, includes:
Second record sub module is configured as recording the MAC Address of the control equipment to be controlled;
Second connection submodule, is configured as the MAC Address and the control equipment to be controlled by the multiple voice capture device It is connected to the network.
18. the described in any item routers of 1-17 according to claim 1, which is characterized in that the multiple voice capture device with By WI-FI transmission of speech signals between the router, passed between the router and the control equipment to be controlled by WI-FI Defeated voice signal.
19. a kind of router, which is characterized in that the router includes:
Processor;
For storing the memory of the executable instruction of the processor;
Wherein, the processor is configured to:
Multiple voice signals that multiple voice capture devices are sent are received, the multiple voice signal corresponds to identical speech source;
Determine that the first voice signal, first voice signal are the multiple according to the signal strength of the multiple voice signal The maximum signal of signal strength in voice signal, wherein the voice capture device is closer from institute's speech source, and institute is collected The quality of voice signal is higher, and the signal strength of the voice signal is bigger;
Dissection process is carried out to first voice signal, determines the corresponding control equipment to be controlled of first voice signal and behaviour It instructs;
The operational order is sent to the control equipment to be controlled, so that the control equipment to be controlled is executed according to the operational order Corresponding operation;
The processor is also configured to
The router receives the second voice signal that the control equipment to be controlled is sent;
The router determines corresponding first voice capture device of first voice signal;
Second voice signal is sent to first voice capture device by the router.
20. a kind of intelligent sound control system, which is characterized in that including described in any item routers of claim 10-18, more A voice capture device and at least one control equipment to be controlled, wherein the control equipment to be controlled is with calculation processing ability Smart machine.
CN201610230741.8A 2016-04-14 2016-04-14 Method of speech processing, router and intelligent sound control system CN105788599B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610230741.8A CN105788599B (en) 2016-04-14 2016-04-14 Method of speech processing, router and intelligent sound control system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610230741.8A CN105788599B (en) 2016-04-14 2016-04-14 Method of speech processing, router and intelligent sound control system

Publications (2)

Publication Number Publication Date
CN105788599A CN105788599A (en) 2016-07-20
CN105788599B true CN105788599B (en) 2019-08-06

Family

ID=56396515

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610230741.8A CN105788599B (en) 2016-04-14 2016-04-14 Method of speech processing, router and intelligent sound control system

Country Status (1)

Country Link
CN (1) CN105788599B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106251590A (en) * 2016-08-09 2016-12-21 深圳市金立通信设备有限公司 A kind of method finding the network equipment and router
WO2018107389A1 (en) * 2016-12-14 2018-06-21 深圳前海达闼云端智能科技有限公司 Method and apparatus for joint assistance by means of voice, and robot
CN107195305A (en) * 2017-07-21 2017-09-22 合肥联宝信息技术有限公司 A kind of information processing method and electronic equipment
CN107452386A (en) * 2017-08-16 2017-12-08 联想(北京)有限公司 A kind of voice data processing method and system
CN109377987A (en) * 2018-08-31 2019-02-22 百度在线网络技术(北京)有限公司 Exchange method, device, equipment and the storage medium of intelligent sound equipment room

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007295085A (en) * 2006-04-21 2007-11-08 Kobe Steel Ltd Sound source separation apparatus, and sound source separation method
CN102483918A (en) * 2009-11-06 2012-05-30 株式会社东芝 Voice recognition means
CN102538143A (en) * 2012-02-06 2012-07-04 广东美的电器股份有限公司 Intelligent phonic search engine air-conditioning system and control method thereof
CN103745722A (en) * 2014-02-10 2014-04-23 上海金牌软件开发有限公司 Voice interaction smart home system and voice interaction method
CN105242556A (en) * 2015-10-28 2016-01-13 小米科技有限责任公司 A speech control method and device of intelligent devices, a control device and the intelligent device
CN105355205A (en) * 2015-11-27 2016-02-24 江门市征极光兆科技有限公司 Intelligent voice control box
CN105389099A (en) * 2014-08-29 2016-03-09 三星电子株式会社 method and apparatus for voice recording and playback

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9177557B2 (en) * 2009-07-07 2015-11-03 General Motors Llc. Singular value decomposition for improved voice recognition in presence of multi-talker background noise
JP2013243503A (en) * 2012-05-18 2013-12-05 Tamura Seisakusho Co Ltd Voice transmission system
CN204231404U (en) * 2014-12-09 2015-03-25 西安邮电大学 A kind of multi-function router
CN104883299B (en) * 2015-06-24 2018-02-13 上海斐讯数据通信技术有限公司 Method for configuring routers, system and router
CN105388772B (en) * 2015-12-04 2019-02-15 重庆财信合同能源管理有限公司 A kind of indoor intelligent control system and method based on speech recognition

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007295085A (en) * 2006-04-21 2007-11-08 Kobe Steel Ltd Sound source separation apparatus, and sound source separation method
CN102483918A (en) * 2009-11-06 2012-05-30 株式会社东芝 Voice recognition means
CN102538143A (en) * 2012-02-06 2012-07-04 广东美的电器股份有限公司 Intelligent phonic search engine air-conditioning system and control method thereof
CN103745722A (en) * 2014-02-10 2014-04-23 上海金牌软件开发有限公司 Voice interaction smart home system and voice interaction method
CN105389099A (en) * 2014-08-29 2016-03-09 三星电子株式会社 method and apparatus for voice recording and playback
CN105242556A (en) * 2015-10-28 2016-01-13 小米科技有限责任公司 A speech control method and device of intelligent devices, a control device and the intelligent device
CN105355205A (en) * 2015-11-27 2016-02-24 江门市征极光兆科技有限公司 Intelligent voice control box

Also Published As

Publication number Publication date
CN105788599A (en) 2016-07-20

Similar Documents

Publication Publication Date Title
US10219062B2 (en) Wireless audio output devices
CN101252376B (en) System and method for connecting blue tooth equipment and mobile communication terminal thereof
CN101673544B (en) Cross monitoring method and system based on voiceprint recognition and location tracking
US20080167072A1 (en) System and method for providing telephone service access via a gateway telephone
US10374952B2 (en) Method for increasing layer-3 longest prefix match scale
CN108351872A (en) Equipment selection for providing response
CA2901603A1 (en) Mobile device speaker control
KR20140104215A (en) Wireless network audio system having auto pairing function and method of auto pairing using the same
CN104159226B (en) Method for connecting network and device
CN103281752A (en) WIFI (wireless fidelity) network access method and device, electronic equipment and communication system
JP2016502355A (en) Voice-controlled configuration of an automation system
CN101416476A (en) Remote user interface for bluetoothtm device
CN106462383A (en) Hands free device with directional interface
CN100405803C (en) System to provide sounds
CN103270738B (en) For processing voice and/or the communication system of video call and method when multiple audio or video sensors can get
CN103281759A (en) WIFI (wireless fidelity) network access method and device, electronic equipment and communication system
CN104080194A (en) Method for wirelessly configuring WIFI access parameters of zero-input terminal equipment through mobile phone
US8103315B2 (en) Portable terminal device
GB2377136A (en) Mobile telephone inter-connecting apparatus
CN102572891A (en) System and method for configuring network parameters fast
WO2007104212A1 (en) Network terminal door bell device, system and method
US20160352567A1 (en) Intelligent agent features for wearable personal communication nodes
CN105120122A (en) Alarm method and device
CN105359560B (en) Pass through the service provision of intelligent personal gateway
US9615173B2 (en) Information processing system and storage medium

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
GR01 Patent grant