CN108124043A - Auxiliary actuating apparatus, speech control system and its method - Google Patents

Auxiliary actuating apparatus, speech control system and its method Download PDF

Info

Publication number
CN108124043A
CN108124043A CN201711423107.7A CN201711423107A CN108124043A CN 108124043 A CN108124043 A CN 108124043A CN 201711423107 A CN201711423107 A CN 201711423107A CN 108124043 A CN108124043 A CN 108124043A
Authority
CN
China
Prior art keywords
mobile terminal
module
voice
wireless transport
transport module
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
Application number
CN201711423107.7A
Other languages
Chinese (zh)
Inventor
张国峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Via Technologies Inc
Original Assignee
Via Technologies Inc
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 Via Technologies Inc filed Critical Via Technologies Inc
Publication of CN108124043A publication Critical patent/CN108124043A/en
Pending legal-status Critical Current

Links

Landscapes

  • Mobile Radio Communication Systems (AREA)
  • Telephone Function (AREA)

Abstract

A kind of auxiliary actuating apparatus, speech control system and its method.The auxiliary actuating apparatus to aid in open a mobile terminal apparatus a voice system and cause a voice identification module of the mobile terminal receive the voice signal of the voice system with by the voice signal be converted into it is multiple segmentation semanteme, and cause a speech processing module of the mobile terminal is parsed according to the plurality of segmentation semanteme to mean representated by the plurality of segmentation semanteme, the mobile terminal apparatus includes one first wireless transport module, the voice system, the voice identification module, with the speech processing module, which includes:One second wireless transport module is matched with first wireless transport module;An and trigger module, couple second wireless transport module, wherein when the trigger module is triggered, which is linked by first wireless transport module of a wireless communication protocol and the mobile terminal apparatus, to start the voice system of the mobile terminal apparatus.

Description

Auxiliary actuating apparatus, speech control system and its method
This case is the applying date on May 17th, 2013, Application No. 201310183217.6, entitled " auxiliary opens The divisional application of the application for a patent for invention of dynamic device, speech control system and its method ".
Technical field
The present invention relates to a kind of technology for opening phonetic function, and more particularly to a kind of auxiliary actuating apparatus, speech controls System and method.
Background technology
With the development of science and technology, the mobile terminal apparatus with voice system is increasingly popularized.Above-mentioned voice system is By speech understanding technology, user is allowed to be linked up with mobile terminal apparatus.For example, as long as user is to above-mentioned shifting Dynamic terminal installation tells a certain requirement, such as wants to look into train number, looks into weather or be intended to call, and system will be according to use The voice signal of person takes corresponding action.Above-mentioned action may be with voice mode answer user's problem or according to User's instruction goes to drive the system of mobile terminal apparatus to be acted.
However, in the technology evolution of voice system, the solution of some problems demands is but faced.Such as:Voice combines The problems such as convenience that the Information Security of cloud server, voice system start.
It is currently with voice interactive system combination high in the clouds technology for the Information Security of voice combination cloud server Concept, will be complicated and speech processes process that powerful operational capability is needed to support transfers to cloud server to perform.Although this The cost of configuration hardware needed for mobile terminal apparatus can be greatly reduced in the mode of sample.But for needing to carry out by address list Call is passed for the actions such as news in brief, is recorded into cloud server to look for call or is passed news in brief due to that need to pass through upload communication Object, therefore the secrecy of address list will be an important subject under discussion.Although encryption line may be employed in cloud server, and adopts The instant mode for passing, not preserving is taken, is still difficult to eliminate worry of the user to the above-mentioned practice.
On the other hand, mostly it is the screen for triggering mobile terminal apparatus at present for the convenience of voice system startup Application program shown by it starts or is started by the physical button set by mobile terminal apparatus.Above-mentioned sets Meter all must in itself be started by mobile terminal apparatus, but in some occasions, above-mentioned design is comparable inconvenience.Such as It says:During the road, and mobile terminal apparatus is placed in pocket or handbag or when kitchen is cooked, it is necessary to dial Mobile phone positioned at parlor to inquire that the users such as friend's recipe details can not touch mobile terminal apparatus immediately, but need to make The situation that voice system is opened.
In addition, the sound amplification function in mobile terminal apparatus equally also has similar problem.Although current user can lead to Cross finger manipulation mobile phone or with single hand grip mobile phone mobile phone is started sound amplification function close to ear. But when user can not touch mobile terminal apparatus immediately, but need to make sound amplification function, mobile terminal apparatus need to be passed through at present Itself will cause the inconvenience of user come the design that starts.
Therefore, these above-mentioned shortcomings how are improved, become subject under discussion urgently to be resolved hurrily.
The content of the invention
The present invention provides a kind of auxiliary actuating apparatus, speech control system and its method, and user can be allowed to pass through auxiliary Starter and wirelessly start the voice dialogue function that mobile communications device is provided, with promote use upper convenience.
The present invention proposes a kind of speech control system, this speech control system includes an auxiliary actuating apparatus and a movement eventually End device.Above-mentioned auxiliary actuating apparatus is aiding in opening a voice system of mobile terminal apparatus, and auxiliary actuating apparatus bag Include one first wireless transport module.Mobile terminal apparatus includes one second wireless transport module and above-mentioned voice system.Second Wireless transport module is matched with the first wireless transport module, and voice system couples the second wireless transport module.When assistant starting fills It puts when being triggered, the first wireless transport module passes through a wireless communication protocol and the second wireless transport module of mobile terminal apparatus Connection, to start the voice system of mobile terminal apparatus.
The present invention separately proposes a kind of auxiliary actuating apparatus, to aid in opening a voice system of a mobile terminal apparatus. Above-mentioned mobile terminal apparatus includes one first wireless transport module and couples the voice system of the first wireless transport module.It is auxiliary Starter is helped to include one second wireless transport module and a trigger module.Second wireless transport module and the first wireless transmission mould Block- matching, trigger module couple the second wireless transport module.When trigger module is triggered, the second wireless transport module passes through one First wireless transport module of wireless communication protocol and mobile terminal apparatus links, to start the voice system of mobile terminal apparatus System.
The present invention proposes a kind of method of speech control again, suitable for a mobile terminal apparatus and an auxiliary actuating apparatus. Above-mentioned auxiliary actuating apparatus to aid in open mobile terminal apparatus voice system.Auxiliary actuating apparatus and mobile terminal apparatus It is respectively provided with the first wireless transport module and the second wireless transport module being mutually matched.The method of above-mentioned speech control is first Wireless transport module receives a trigger signal.Then, start the first wireless transport module, and send a wireless transmission signal.So Afterwards, the second wireless transport module receives wireless transmission signal, to start voice system.
The present invention also proposes a kind of speech control system, including:One auxiliary actuating apparatus, to aid in opening a movement One voice system of terminal installation, the auxiliary actuating apparatus include one first wireless transport module;And the mobile terminal apparatus, The mobile terminal apparatus includes:One second wireless transport module is matched with first wireless transport module;The voice system, coupling Connect second wireless transport module;One voice identification module;And a speech processing module, wherein, when the auxiliary actuating apparatus When being triggered, which passes through second wireless transmission of a wireless communication protocol and the mobile terminal apparatus Module links, to start the voice system of the mobile terminal apparatus, wherein, which receives the voice system The voice signal, is converted into that multiple segmentations are semantic and wherein, and the speech processing module is according to the plurality of point by voice signal Duan Yuyi is parsed to be meant representated by the plurality of segmentation semanteme.
The present invention also proposes a kind of auxiliary actuating apparatus, to aid in a voice system of one mobile terminal apparatus of unlatching simultaneously And a voice identification module of the mobile terminal is caused to receive the voice signal of the voice system so that the voice signal to be converted into Multiple speech processing modules for being segmented semanteme and causing the mobile terminal parse the plurality of according to the plurality of segmentation semanteme Be segmented semanteme representated by it is meant that the mobile terminal apparatus include one first wireless transport module, couple this first wireless transmission The voice system of module, the voice identification module and the speech processing module, the auxiliary actuating apparatus include:One second nothing Line transport module is matched with first wireless transport module;And a trigger module, second wireless transport module is coupled, In when the trigger module is triggered, which passes through a wireless communication protocol and the mobile terminal apparatus First wireless transport module links, to start the voice system of the mobile terminal apparatus.
The present invention also proposes a kind of method of speech control, suitable for a mobile terminal apparatus and an auxiliary actuating apparatus, For the auxiliary actuating apparatus to aid in opening a voice system of the mobile terminal apparatus, which has one first Wireless transport module, the mobile terminal apparatus have one second wireless transmission mould being mutually matched with first wireless transport module Block, the voice system, a voice identification module and a speech processing module, the method for the speech control include:This is first wireless Transport module receives a trigger signal;Start first wireless transport module, and send a wireless transmission signal;This is second wireless Transport module receives the wireless transmission signal, to start the voice system;The voice identification module receives the language of the voice system It is semantic to be converted into multiple segmentations by sound signal for the voice signal;And the speech processing module is semantic according to the plurality of segmentation It parses and means representated by the plurality of segmentation semanteme.
Based on above-mentioned, when mobile communications device receives the wireless transmission signal from auxiliary actuating apparatus to start voice system During system, mobile communications device can start receive user voice signal, with by speech understanding module to parse predicate Sound signal.Thus, user wirelessly starts the voice pair that mobile communications device is provided by auxiliary actuating apparatus Function is talked about, enhancement is used and uses upper convenience.
To make the foregoing features and advantages of the present invention clearer and more comprehensible, special embodiment below, and it is detailed that attached drawing is coordinated to make Carefully it is described as follows.
Description of the drawings
Fig. 1 is the block diagram according to the speech control system depicted in one embodiment of the invention.
Fig. 2 is the block diagram according to the speech control system depicted in another embodiment of the present invention.
Fig. 3 is the flow chart according to the voice control method depicted in one embodiment of the invention.
Fig. 4 is the block diagram of the voice interactive system according to one embodiment of the invention.
Fig. 5 is the schematic diagram of the voice communication flow for voice interactive system according to one embodiment of the invention.
Fig. 6 is the system schematic of the mobile terminal apparatus according to one embodiment of the invention.
Fig. 7 is the stream of the automatic starting method of the call sound amplification function of the mobile terminal apparatus according to one embodiment of the invention Cheng Tu.
【Main element symbol description】
100、200:Speech control system
110:Auxiliary actuating apparatus
112、122:Wireless transport module
114:Trigger module
116:Wireless charging battery
1162:Battery unit
1164:Wireless charging module
120、220、420:Mobile terminal apparatus
121、426:Voice system
124、610:Speech sample module
127:Voice output interface
128、424:Communication module
130、410:(high in the clouds) server
132:Speech understanding module
1322:Voice identification module
1324:Speech processing module
400:Voice interactive system
412、422、660:Processing unit
414:Communication module
428:Storage unit
429:Address list
330:Display unit
620:Input unit
630:Pull and connect unit
640:Receiver
650:Public address equipment
670:Earphone
S302~S312, S501~S519, S710~S770:Step
DRC:Call receives data
DTC:Call transmission data
SAI:Input audio signal
SAO:Exports audio signal
SIO:Input operation signal
Specific embodiment
Although mobile terminal apparatus now can provide voice system, user to be allowed to send voice and mobile terminal Device is linked up, but user is when starting this voice system, still has in itself start by mobile terminal apparatus.Therefore make User can not touch mobile terminal apparatus immediately, but the situation that need to open voice system, often can not meet user immediately Demand.For this purpose, the present invention proposes a kind of device of assistant voice system unlatching and its corresponding method, allow user can be more Easily open voice system.It is special below really for embodiment as the present invention in order to become apparent present disclosure Enough examples implemented according to this.
Fig. 1 is the block diagram according to the speech control system depicted in one embodiment of the invention.It refer to Fig. 1, voice behaviour Control system 100 includes auxiliary actuating apparatus 110, mobile terminal apparatus 120 and server 130.In the present embodiment, auxiliary opens Dynamic device 110 can be by wireless transmission signal, to start the voice system of mobile terminal apparatus 120 so that mobile terminal apparatus 120 are linked up according to voice signal and server 130.
Specifically, auxiliary actuating apparatus 110 includes the first wireless transport module 112 and trigger module 114, wherein touching Hair module 114 is coupled to the first wireless transport module 112.First wireless transport module 112 is, for example, to support Wireless Fidelity (Wireless fidelity, Wi-Fi), global intercommunication microwave access (Worldwide Interoperability for Microwave Access, WiMAX), bluetooth (Bluetooth), ultra wide band (ultra-wideband, UWB) or radio frequency identification The device of communication protocols such as (Radio-frequency identification, RFID), can send wireless transmission signal, with It corresponds to each other with another wireless transport module and establishes wireless link.Trigger module 114 is, for example, button, button etc..In this reality It applies in example, after user, which presses this trigger module 114, generates a trigger signal, the first wireless transport module 112 receives this and touches It signals and starts, the first wireless transport module 112 can send wireless transmission signal at this time, and pass through the first wireless transport module 112 transmit this wireless transmission signal to mobile terminal apparatus 120.In one embodiment, above-mentioned auxiliary actuating apparatus 110 can be One bluetooth headset.
Although it is worth noting that, at present some hand-frees earphone also have start mobile terminal apparatus 120 certain The design of a little functions, but in another embodiment of the present invention, auxiliary actuating apparatus 110 can be different from above-mentioned earphone/Mike Wind.Above-mentioned earphone is by the line with mobile terminal apparatus, to substitute earphone/wheat on mobile terminal apparatus 120 Gram wind and listened/talked, startup function is additional design, but the auxiliary actuating apparatus 110 " only " of the application moves for opening Voice system in dynamic terminal installation 120, and without the function of listening/talking, therefore internal circuit design can simplify, cost It is relatively low.In other words, for above-mentioned hands-free headsets/microphone, auxiliary actuating apparatus 110 is other device, even if User may be provided simultaneously with the earphone of hand-free and the auxiliary actuating apparatus 110 of the application.
In addition, the body of above-mentioned auxiliary actuating apparatus 110 can be user whip can and articles for use, such as ring, The ornaments such as wrist-watch, earrings, necklace, glasses, i.e., various Portable articles or installation component, are for example, configured at Driving accessory on steering wheel, is not limited to above-mentioned.That is, auxiliary actuating apparatus 110 is the device of " life-stylize ", by interior The setting of portion's system allows user that can touch trigger module 114 easily, to open voice system.For example, when auxiliary When the body of starter 110 being helped to be ring, user can move finger easily makes it to press the trigger module 114 of ring It is triggered.On the other hand, when the body of auxiliary actuating apparatus 110 is to be configured at the device of driving accessory, user also can Trigger the trigger module 114 of driving accessory device easily during the road.In addition, it is carried out compared to earphone is worn The discomfort listened/talked, can be by the voice system in mobile terminal apparatus 120 using the auxiliary actuating apparatus 110 of the application System open or even and then open sound amplification function (will be described afterwards) so that user be not required to wear earphone, still can be straight Mobile terminal apparatus 120 was connected to be listened/talked.In addition, for user, the assistant starting dress of these " life-stylizes " 110 are put as the articles that will wear or use originally, therefore uncomfortable or discomfort is not had on using the problem of, i.e., not It needs to take time to adapt to.For example, when user when kitchen is cooked, it is necessary to when dialing the mobile phone for being positioned over parlor, Assuming that it wears the auxiliary actuating apparatus 110 of the present invention with ring, necklace or wrist-watch body, it is possible to touch ring, item Chain or wrist-watch inquire friend's recipe details to open voice system.Although part has earphone/Mike of startup function at present Wind can also achieve the purpose that above-mentioned, but during cooking every time, not be required for calling every time consulting friend, Therefore for the user, wear earphone at any time to cook, in case manipulation mobile terminal apparatus can say it is comparable at any time It is inconvenient.
In other embodiments, auxiliary actuating apparatus 110 may also be configured with wireless charging battery 116, to drive first Wireless transport module 112.Furthermore, wireless charging battery 116 includes battery unit 1162 and wireless charging module 1164, wherein wireless charging module 1164 is coupled to battery unit 1162.Here, wireless charging module 1164 can be received from one The energy that wireless power supply (not illustrating) is supplied, and this energy is converted into electric power to charge to battery unit 1162.Such as This one, the first wireless transport module 112 of auxiliary actuating apparatus 110 can be carried out conveniently by wireless charging battery 116 It charges.
On the other hand, mobile terminal apparatus 120 is, for example, mobile phone (Cell phone), personal digital assistant (Personal Digital Assistant, PDA) mobile phone, smart mobile phone (Smart phone) or communication software is installed Palmtop computer (Pocket PC), Tablet PC (Tablet PC) or notebook computer etc..Mobile terminal Device 120 can be any portable (Portable) mobile device for possessing communication function, be not intended to limit its scope herein.This Outside, mobile terminal apparatus 120 can be used Android operation system, microsoft operating system, Android operation system, (SuSE) Linux OS etc. is not limited to above-mentioned.
Mobile terminal apparatus 120 includes the second wireless transport module 122, and the second wireless transport module 122 can be opened with auxiliary First wireless transport module 112 of dynamic device 110 matches, and the corresponding wireless communication protocol of use (such as it is wireless compatible The communication protocols such as certification, global intercommunication microwave access, bluetooth, ultra-wideband communication protocol or radio frequency identification), it uses with first wirelessly Transport module 112 establishes wireless link.It is worth noting that, " first " wireless transport module 112 described herein, " second " nothing Line transport module 122 is not limited to the present invention to illustrate that wireless transport module is configured at different devices.
In other embodiments, mobile terminal apparatus 120 further includes voice system 121, this voice system 121 is coupled to Two wireless transport modules 122, therefore after user triggers the trigger module 114 of auxiliary actuating apparatus 110, the first wireless biography can be passed through Defeated 112 and second wireless transport module 122 of module wirelessly starts voice system 121.In one embodiment, this voice system 121 may include speech sample module 124 and voice output interface 127.Speech sample module 124 comes from user to receive Voice signal, this speech sample module 124 is, for example, the device that microphone (Microphone) etc. receives audio.Above-mentioned language Sound output interface 127 is, for example, loudspeaker or earphone etc..
In addition, mobile terminal apparatus 120 may also be configured with communication module 128.Communication module 128 is, for example, that can transfer and connect Receive the element of wireless signal, such as RF transceiver.Furthermore, communication module 128 can allow user to pass through mobile terminal Other services that device 120 is answered or called or provided using telecommunication operator.In the present embodiment, communication module 128 Can by internet receive the response message from server 130, and according to this response message establish mobile terminal apparatus 120 with Call line between an at least electronic device, wherein the electronic device is, for example, another mobile terminal apparatus (not illustrating).
Server 130 is, for example, network server or cloud server etc., with speech understanding module 132.In this reality It applies in example, speech understanding module 132 includes voice identification module 1322 and speech processing module 1324, wherein speech processes mould Block 1324 is coupled to voice identification module 1322.It is transmitted here, voice identification module 1322 can be received from speech sample module 124 Voice signal, it is semantic (such as vocabulary or words and expressions etc.) to convert voice signals into multiple segmentations.Speech processing module 1324 Then it can parse according to these segmentation semantemes and mean (such as intention, time, place etc.) representated by these segmentation semantemes, into And judge the meaning represented in above-mentioned voice signal.In addition, speech processing module 1324 can also be according to the result parsed Generate corresponding response message.In the present embodiment, speech understanding module 132 can be composed of one or several logic gates Hardware circuit carrys out implementation or carrys out implementation with computer program code.It is noted that in another embodiment, language Sound Understanding Module 132 is configured in mobile terminal apparatus 220, speech control system 200 as shown in Figure 2.
Above-mentioned speech control system 100 is arranged in pairs or groups to illustrate the method for speech control below.Fig. 3 is real according to the present invention one Apply the flow chart of the voice control method depicted in example.Referring to Fig. 1 and Fig. 3, in step 302, auxiliary actuating apparatus 110 send wireless transmission signal to mobile terminal apparatus 120.Detailed description is that first when auxiliary actuating apparatus 110 is wireless When transport module 112 is triggered because receiving a trigger signal, this auxiliary actuating apparatus 110 can send wireless transmission signal to shifting Dynamic terminal installation 120.Specifically, when the trigger module 114 in auxiliary actuating apparatus 110 is depressed by a user, touch at this time Hair module 114 can be triggered because of trigger signal, and the first wireless transport module 112 is made to send wireless transmission signal to mobile terminal Second wireless transport module 122 of device 120 is used so that the first wireless transport module 112 passes through wireless communication protocol and Two wireless transport modules 122 link.Above-mentioned auxiliary actuating apparatus 110 is only used for opening the voice in mobile terminal apparatus 120 System, and without the function of listening/talking, therefore internal circuit design can simplify, cost is relatively low.In other words, compared with For hands-free headsets/microphone attached by general mobile terminal apparatus 120, auxiliary actuating apparatus 110 is another device, even if User may be provided simultaneously with the earphone of hand-free and the auxiliary actuating apparatus 110 of the application.
It is noted that the body of above-mentioned auxiliary actuating apparatus 110 can be user whip can and articles for use, example The various Portable articles of such as ring, wrist-watch, earrings, necklace, glasses or installation component, for example, side of being configured at Driving accessory on disk, is not limited to above-mentioned.That is, auxiliary actuating apparatus 110 is the device of " life-stylize ", pass through inside The setting of system allows user that can touch trigger module 114 easily, to open voice system 121.Therefore, this is used The auxiliary actuating apparatus 110 of application can open the voice system 121 in mobile terminal apparatus 120 or even and then unlatching expansion Sound function (will be described) afterwards so that user is being not required to wear earphone, still can directly pass through mobile terminal apparatus 120 It is listened/talked.In addition, for user, the auxiliary actuating apparatus 110 of these " life-stylizes " will to wear originally or The article used, therefore uncomfortable or discomfort is not had on using the problem of.
In addition, the first wireless transport module 112 and the second wireless transport module 122 all can be at sleep pattern or Working mould Formula.Wherein, sleep pattern refers to that wireless transport module is in off state, that is, wireless transport module will not receive/detect nothing Line transmission signal, and can not link with other wireless transport modules.Operating mode refers to wireless transport module as opening, That is, wireless transport module constantly detecting wireless transmission signal or can send wireless transmission signal at any time, and can with it is other Wireless transport module links.Here, when trigger module 114 is triggered, if the first wireless transport module 112 is in sleep mould Formula, then trigger module 114 can wake up the first wireless transport module 112, make the first wireless transport module 112 into operating mode, And the first wireless transport module 112 is made to send wireless transmission signal to the second wireless transport module 122, and allow the first wireless transmission Module 112 is linked by the second wireless transport module 122 of wireless communication protocol and mobile terminal apparatus 120.
On the other hand, in order to avoid the first wireless transport module 112 persistently maintains operating mode and consumes excessive electricity Power, it is interior into the preset time (being, for example, 5 minutes) after operating mode in the first wireless transport module 112, if trigger module 114 are not triggered again, then the first wireless transport module 112 can enter sleep pattern, and stopping and mobile terminal from operating mode Second wireless transport module 120 of device 120 links.
Afterwards, in step 304, the second wireless transport module 122 of mobile terminal apparatus 120 can receive wireless transmission letter Number, to start voice system 121.Then, in step S306, when the second wireless transport module 122 detects wireless transmission signal When, mobile terminal apparatus 120 can start voice system 121, and 121 sampling modules 124 of voice system can start to receive voice Signal, such as " temperature several years today", " phone Lao Wang.", " ask enquiring telephone number." etc..
In step S308, above-mentioned voice signal can be sent to the speech understanding in server 130 by speech sample module 124 Module 132, to parse voice signal by speech understanding module 132 and generate response message.Furthermore, speech understanding Voice identification module 1322 in module 132 can receive the voice signal from speech sample module 124, and voice signal is divided It is semantic to be cut into multiple segmentations, and speech processing module 1324 semantic to above-mentioned segmentation can then carry out speech understanding, with generate to Respond the response message of voice signal.
In another embodiment of the invention, produced by mobile terminal apparatus 120 can more receive speech processing module 1324 Response message, be output by voice the interior response message that perhaps performs that interface 127 is exported in response message according to this and assigned Operation.In step S310, mobile terminal apparatus 120 can receive response message caused by speech understanding module 132, and foundation should The content (such as vocabulary or words and expressions etc.) answered in information generates voice answer-back.Also, in step S312, voice output interface 127 It can receive and export this voice answer-back.
For example, when user presses the trigger module 114 in auxiliary actuating apparatus 110, the first wireless transmission mould Block 112 can then send wireless transmission signal to the second wireless transport module 122 so that mobile terminal apparatus 120 starts voice system The speech sample module 124 of system 121.In this, it is assumed that the voice signal from user is an inquiry sentence, such as " today temperature Several years", then speech sample module 124 will receive and this voice signal is sent to the speech understanding module in server 130 132 are parsed, and response message caused by parsing can be sent back mobile terminal apparatus 120 by speech understanding module 132.It is false If the content in response message caused by speech understanding module 132 is " 30 DEG C ", then voice output interface 127 can be by this voice It should report to user.
In another embodiment, it is assumed that the voice signal from user is an imperative sentence, such as " is phoned old King.", then this imperative sentence can be picked out in speech understanding module 132 as " request dialed to Lao Wang ".In addition, speech understanding Module 132 can generate new response message, such as " whether PLSCONFM sets aside Lao Wang " again, and this new response message is sent to Mobile terminal apparatus 120.It is reported here, this new response message is output by voice interface 127 in user.Further It says, when the response of user is the affirmative answer of "Yes" etc, similarly, speech sample module 124 can receive and transmit this Voice signal is to server 130, speech understanding module 132 to be allowed to be parsed.After speech understanding module 132 parses, just There can be a dial instruction information in response message record, and be sent to mobile terminal apparatus 120.At this point, communication module 128 then can The contact information that foundation call database is recorded inquires the telephone number of " Lao Wang ", to establish mobile terminal apparatus 120 Call line between another electronic device, that is, dial to " Lao Wang ".
In other embodiments, in addition to above-mentioned speech control system 100, can also be used speech control system 200 or its His similar system, is carried out above-mentioned operating method, is not limited with the above embodiments.
In conclusion in the speech control system and method for the present embodiment, auxiliary actuating apparatus can be opened wirelessly The phonetic function of mobile terminal apparatus.Moreover, the body of this auxiliary actuating apparatus can be user whip can and " life The articles for use of change ", such as the ornaments such as ring, wrist-watch, earrings, necklace, glasses, i.e., various Portable articles or peace Component is filled, the driving accessory being for example, configured on steering wheel is not limited to above-mentioned.Thus, it is worn compared to other at present The discomfort of hands-free headsets/microphone is opened using the auxiliary actuating apparatus 110 of the application in mobile terminal apparatus 120 Voice system will be more convenient.
It is taken it is worth noting that, the above-mentioned server 130 with speech understanding module may be network server or high in the clouds It is engaged in device, and the problem of cloud server may be related to the right of privacy of user.For example, user need to upload complete communication Record could be completed such as to call, send out news in brief and the relevant operation of address list to cloud server.Even if cloud server is adopted With encryption line, and it is instant biography do not preserve, the load for being still difficult to eliminate user is excellent.Accordingly, another language presented below Sound manipulation method and its corresponding voice interactive system, mobile terminal apparatus can in the case where not uploading complete address list, Interactive voice service is performed with cloud server.In order to become apparent present disclosure, spy is for embodiment conduct below The example that the present invention can actually be implemented according to this.
Fig. 4 is the block diagram of the voice interactive system according to one embodiment of the invention.It refer to Fig. 4, voice interactive system 400 may include cloud server 410 and mobile terminal apparatus 420, and cloud server 410 and mobile terminal apparatus 420 can Interconnecting line.Voice interactive system 400 is to carry out interactive voice service by cloud server 410.That is, by with powerful fortune The cloud server 410 of calculation ability handles speech recognition, thereby reduces the data processing load of mobile terminal apparatus 420, also The accuracy and recognition speed of speech recognition can be promoted.
In mobile terminal apparatus 420, including processing unit 422, communication module 424, voice system 426, storage unit 428.In one embodiment, mobile terminal apparatus 420 is also configured with a display unit 430.Wherein, processing unit 422 is coupled to Communication module 424, voice system 426, storage unit 428 and display unit 430.It is logical that one is more stored in storage unit 428 News record 429.
Above-mentioned processing unit 422 is the hardware (such as chipset, processor etc.) for possessing operational capability, to control movement The overall operation of terminal installation 420.The e.g. central processing unit of processing unit 422 (Central Processing Unit, ) or other programmable microprocessor (Microprocessor), digital signal processor (Digital Signal CPU Processor, DSP), programmable controller, special application integrated circuit (Application Specific Integrated Circuits, ASIC), programmable logic device (Programmable Logic Device, PLD) or other similar devices.
Above-mentioned communication module 424 is, for example, network card, can be via wire transmission or wireless transmission and cloud service Device 410 is linked up.And above-mentioned voice system 426 includes at least the radio reception devices such as microphone, to convert sound into electronic signal. Said memory cells 428 are, for example, random access memory (Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), flash memory (Flash memory) or disk storage device (Magnetic disk Storage device) etc..Above-mentioned display unit 430 is, for example, liquid crystal display (Liquid Crystal Display, LCD) Or Touch Screen (touch screen) with touch-control module etc..
On the other hand, cloud server 410 for the entity host with powerful operational capability or can be real by a group One super virtual computer of body host composition, uses to perform large-scale task.Here, cloud server 410 includes processing Unit 412 and communication module 414.Here, the communication module 414 of cloud server 410, is coupled to its processing unit 412.Communication Module 414 is linked up to the communication module 424 with mobile terminal apparatus 420.Communication module 414 is, for example, network card, Can be linked up via wire transmission or wireless transmission with mobile terminal apparatus 420.
In addition, the processing unit 412 in cloud server 410 is with more powerful operational capability, it is, for example, multi-core CPU or form CPU arrays by multiple CPU.The processing unit 412 of cloud server 410 for example, at least includes such as Fig. 1 Shown speech understanding module 132.Processing unit 412 can be by speech understanding module come to being connect from mobile terminal apparatus 420 The voice signal of receipts is parsed.And the result of parsing is sent to mobile terminal by cloud server 410 by communication module 414 Device 420 so that mobile terminal apparatus 420 is able to perform corresponding action according to result.
Above-mentioned Fig. 4 is arranged in pairs or groups to be illustrated in the exchange of speech flow of voice interactive system below.
Fig. 5 is the schematic diagram of the voice communication flow for voice interactive system according to one embodiment of the invention.It please be same When with reference to Fig. 4 and Fig. 5, in step S501, in mobile terminal apparatus 420, pass through voice system 426 and receive the first voice and believe Number, and in step S503, the first voice signal is sent to by cloud server 410 by communication module 424.Here, it moves Dynamic terminal installation 420 is, for example, to receive the first voice signal from user by elements such as the microphones in voice system 426. As an example it is assumed that mobile terminal apparatus 420 is mobile phone, user says " phoning Lao Wang " against mobile phone, then voice system System 426 " can be phoned this voice signal by communication module 424 after this voice signal " phoning Lao Wang " is received Lao Wang " is sent to cloud server 410.In one embodiment, above-mentioned voice system 426 can be by Fig. 1~shown in Fig. 3 auxiliary Starter is helped to be started.
Then, in step S505, beyond the clouds in server 410, processing unit 412 is parsed using speech understanding module First voice signal, also, in step s 507, the communication target that processing unit 412 will be obtained by the first voice signal is led to It crosses communication module 414 and is sent to mobile terminal apparatus 420.By taking the content " phoning Lao Wang " of the first voice signal as an example, cloud The processing unit 412 of end server 410 can parse the first voice signal using speech understanding module, thereby obtain communication instruction With communication target.That is, speech understanding module, which can parse the first voice signal, includes " making a phone call " and " Lao Wang ", accordingly, high in the clouds The processing unit 412 of server 410 just can interpolate that out that communication instruction is dial instruction and communication target is " Lao Wang ", and Mobile terminal apparatus 420 is sent to by communication module 414.
Then, in step S509, in mobile terminal apparatus 420, the processing unit 422 of mobile terminal apparatus 420 according to The address list 429 in storage unit 428 is searched according to communication target, and obtains the selective listing for meeting communication target.It is for example, mobile The processing unit 422 of terminal installation 420 finds the more contact informations with " king " during address list is searched, because And selective listing is generated, and be shown in display unit 430, so that user makes choice.
For example, selective listing searches the connection for meeting communication target " Lao Wang " for example shown in the following table 1 of bottom in address list Network people's information.In this instance, it is assumed that find 4 contact informations met, and by contact person's title in contact information, That is " Wang Congming ", " king five ", " WANG Zeng-qi " and " Wang Wei ", write into selective listing.
Table 1
And if user speaks against mobile terminal apparatus 420, as shown in step S511,420 meeting of mobile terminal apparatus Second voice signal is received by voice system 426.And receive the same of the second voice signal in mobile terminal apparatus 420 When, in step S513, mobile terminal apparatus 420 can by the second voice signal and selective listing by communication module 424 simultaneously It is sent to cloud server 410.Such as:User says after selective listing is watched against mobile terminal apparatus 420 The contents such as " the 1st " or " Wang Congming ", and during the second voice signal of formation, mobile terminal apparatus 420 will believe the second voice Number cloud server 410 is sent to together with selective listing.
In addition, user also can arbitrarily say other content, that is to say, that no matter the content said of user why, only Mobile terminal apparatus 420 is wanted to receive the second voice signal, will the second voice signal and selective listing be sent to cloud simultaneously Hold server 410.
It is noted that in this application, the address list of " complete " is not uploaded to cloud server 410, and only Communication target will be met in the form of " selective listing ", be uploaded to cloud server 410 to carry out second of speech signal analysis. In other words, the contact data of only " part " can be uploaded.In one embodiment, mobile terminal apparatus 420 is uploaded to cloud Contact person's title can be only included by holding in the selective listing of server 410, without including telephone number or other information.It is uploaded The content of selective listing can be set according to the demand of user.
Furthermore it is noted that in this application, the second voice signal is sent to cloud service simultaneously with selective listing Device 410 need to parse each voice signal and each list by several times compared to the communication means for being not required to upload communication record at present, That is a step only includes an information, and the voice switching method of the application is more quick.
Then, beyond the clouds in server 410, processing unit 412 can be believed using speech understanding module to parse the second voice Number, as shown in step S515.For example, it is the " the 3rd that the content included by the second voice signal is parsed using speech understanding module It is a ", then the processing unit 412 of cloud server 410 can further go to compare the selection received from mobile terminal apparatus 420 The 3rd contact information in list.By taking table 1 as an example, the 3rd contact information is " WANG Zeng-qi ".
It is worth noting that, by the design of speech understanding module 132 as shown in Figure 1, user is not required to completely tell The content of selective listing is as the second voice signal, such as " the 1st Wang Congming ", it is only necessary to tell the content of part selective listing, such as " the 1st " or " Wang Congming " is used as the second voice signal, and selective listing of arranging in pairs or groups simultaneously is uploaded to the voice reason of cloud server Solve module 132, you can parse selection target.In other words, selective listing content includes multiple project information, and each Mesh information, which at least has, numbers and corresponds to the content of this number (such as:Name, telephone number etc.), and the second voice signal comes from The partial content or number of this corresponding number.
Afterwards, in step S517, cloud server 410 is by its communication module 414 by communication instruction and selection target It is sent to mobile terminal apparatus 420.And in other embodiments, cloud server 410 also can parse first in step S505 After voice signal, i.e., first transmission communication instruction to mobile terminal apparatus 420 stores, and transmits selection target again afterwards, herein simultaneously The delivery time point of communication instruction is not limited.
After mobile terminal apparatus 420 receives communication instruction and selection target, in step S519, mobile terminal dress 420 are put by its processing unit 422 to selection target, performs the corresponding communication operation of communication instruction.Above-mentioned communication instruction is for example The instruction of the address list content need to be used for dial instruction or citation instruction etc., and communication instruction is by 410 base of cloud server It is obtained in the first voice signal.For example, it is assumed that the content of the first voice signal is " phoning Lao Wang ", then cloud server 410 are judged that communication instruction is dial instruction by " making a phone call ".In another example, it is assumed that the content of the first voice signal is " biography letter It interrogates to Lao Wang ", then cloud server 410 is judged that communication instruction instructs for citation by " biography news in brief ".In addition, above-mentioned selection mesh Mark is then to be based on the second voice signal and selective listing by cloud server 410 and obtained.With the alternative column shown in above-mentioned table 1 Exemplified by table, it is assumed that the content of the second voice signal is " the 3rd ", then cloud server 410 can judge that selection target is " king Pacify stone ".For example, it calls to selection target or starts a citation interface, to transmit news in brief to selection target.
It is worth noting that, it can only be wrapped in the selective listing that mobile terminal apparatus 420 is obtained in above-mentioned steps S509 Contact person's title is included, without including telephone number or other information.Therefore, when mobile terminal apparatus 420 is from cloud server 410 When receiving communication instruction with selection target, the processing unit 422 of mobile terminal apparatus 420 can take out corresponding choosing from address list It selects the telephone number of target, and the corresponding communication operation of communication instruction is performed according to telephone number.
In addition, in other embodiments, in the selective listing that mobile terminal apparatus 420 is obtained in above-mentioned steps S509 It can include contact person's title and telephone number simultaneously or may also include other information.Therefore, in step S515, high in the clouds clothes The processing unit 412 of business device 410 just can be based on the second voice signal and selective listing, and obtain the phone number of selection target Code, and in step S517, communication instruction and telephone number are sent to mobile terminal apparatus 420.Accordingly, in step S519 In, mobile terminal apparatus 420 performs the corresponding communication operation of communication instruction according to telephone number.
In conclusion the application is produced using selective listing, the second voice signal caused by the first voice is uploaded simultaneously The mode of raw selection target performs speech understanding program, and this alternative column to the cloud server with powerful operational capability Table only includes the address list of part.Therefore, the speech control system of the application can possess simultaneously higher treatment efficiency and preferably Security.
On the other hand, it is notable that although above-mentioned auxiliary actuating apparatus solves user and can not touch immediately Mobile terminal apparatus, but voice system problem need to be used so that user can allow user with moving by speech understanding technology Dynamic terminal installation carries out question and answer.However, in the case of sound amplification function is needed to open, still needed at present through mobile terminal apparatus sheet Body starts sound amplification function, when user can not touch mobile terminal apparatus immediately, but need to make sound amplification function, need to pass through at present The design that mobile terminal apparatus starts in itself will cause the inconvenience of user.For this purpose, the present invention proposes that a kind of unlatching amplifies The method of function and its corresponding device, allow user that can more easily open sound amplification function.In order to make present disclosure It becomes apparent, below the special example that can actually implement according to this as the present invention for embodiment.
Fig. 6 is the system schematic of the mobile terminal apparatus according to one embodiment of the invention.Fig. 6 is refer to, in this implementation In example, mobile terminal apparatus 600 includes voice system, input unit 620, pulls and connects unit 630, receiver 640, public address equipment 650 And processing unit 660.In another embodiment of the invention, mobile terminal apparatus 600 may also include earphone 670.Mobile terminal Device 600 can be mobile phone or other similar electronic devices, be similar to the mobile terminal apparatus 120 of Fig. 1, in detail Content can refer to foregoing teachings, and details are not described herein.Processing unit 660 couples speech sample module 610, input unit 620, dials Order member 630, receiver 640, public address equipment 650, earphone 670.Voice system includes speech sample module 610, this speech sample Module 610 converts sound into input speech signal SAI, and above-mentioned speech sample module 610 can be microphone or similar Electronic component.In other words, speech sample module 610 can be considered a part for voice system, and the voice system class described in this The voice system 121 of Fig. 1 is similar to, detailed content can refer to foregoing teachings, and details are not described herein.The correspondence of input unit 620 makes The operation of user provides input operation signal SIO, and input unit 620 can be keyboard, touch panel or similar electronics member Part.It pulls and connects unit 630 and pulls and connects function to be controlled by the execution of processing unit 660.Receiver 640, public address equipment 650, earphone 670 are used Sound is converted to the output voice signal SAO for providing processing unit 660, therefore can be considered sound output interface.Above-mentioned expansion Sound equipment 650 is, for example, loud speaker etc..Above-mentioned earphone 670 can be at least one of wired earphone and wireless headset.
From the foregoing, it will be observed that phonetic function open can by press mobile communications device physical button, manipulation screen or It is the auxiliary actuating apparatus using the present invention.In the case of assuming that phonetic function has turned on, when user is against mobile terminal When device 600 is talked, input speech signal SAI can be converted sound by speech sample module 610, processing unit 660 can According to input speech signal SAI, for contact person's title in address list or telephone number when information carry out content matching, when When information in address list is consistent with input speech signal SAI, processing unit 660 can then open pull and connect unit 630 pull and connect work( Energy and public address equipment 650, after connecting, user can be with the call of contact person.Detailed description is 660 meeting of processing unit Input speech signal SAI is converted into an input word string, and word string and multiple contact person's titles, more in address list will be inputted The information such as a telephone number compare.When input word string meet the information such as these contact person's titles, these telephone numbers wherein it For the moment, processing unit 660 open pull and connect unit 630 pull and connect function.On the contrary, when input word string does not meet these contact names Claim and during these telephone numbers, what processing unit 660 was not turned on pulling and connecting unit 630 pulls and connects function.
In other words, in the present embodiment, the content in 660 confirmation input voice signal SAI of processing unit and address list During matching, processing unit 660 can provide enabling signal, to automatically turn on the call sound amplification function of mobile terminal apparatus 100.Tool For body, processing unit 660 can automatically provide enabling signal to public address equipment 650, and input speech signal SAI is converted to Call transmission data DTC, and to contact person, (another mobile terminal fills by pulling and connecting the transmission call transmission data DTC of unit 630 It puts, does not illustrate).Meanwhile processing unit 660 can receive call reception data DRC by pulling and connecting unit 630, and connect according to call It receives data DRC and provides exports audio signal SAO to public address equipment 650, exports audio signal SAO is converted into sound, and with The mode to amplify exports sound.
It is still using by mobile terminal apparatus sheet it is noted that in a manner of currently active sound amplification function Body carries out come the mode started, but when user can not touch mobile terminal apparatus immediately, but need using sound amplification function, at present Design will cause the inconvenience of user.So in the present embodiment, in the case where voice system is opened, language can be passed through The action that sound is pulled and connected, further opens sound amplification function, is user-friendly for conversing.
In another embodiment, in the case that public address equipment 650 and earphone 670 are all with 600 line of mobile terminal apparatus (i.e. public address equipment 650 with earphone 670 all couple processing unit), provided that processing unit 660 be input speech signal SAI, processing unit 660 can be according to the settings of user, and it is the first preferential talking mode (preset value) to make the call of earphone 670, is expanded Sound equipment 650 is the second preferential talking mode.It (is preset alternatively, public address equipment 650 is set to the first preferential talking mode Value), the call of earphone 670 is set to the second preferential talking mode.The order of above-mentioned talking mode is set, is because user may It can not touch mobile terminal apparatus immediately, therefore all be conversed using public address equipment 650 and earphone 670.
In addition, it in another embodiment, when user provides input operation signal SIO by input unit 620, represents User can not touch the problem of mobile terminal apparatus immediately, therefore in processing unit 660 according to input operation signal SIO After carrying out address book data matching, by processing unit 660, pull and connect unit 630 and exports audio signal SAO can be sent to and amplify The sound output interfaces such as equipment 650, receiver 640 or earphone 670, end regard the default output interface of user (preset value) and It is fixed.
For example, when user says against mobile terminal apparatus " Lao Wang " is phoned, speech sample module 610 at this time After receiving this sound, input speech signal SAI is changed into, and the solution that this input speech signal SAI passes through speech understanding module Analysis, obtain communication instruction (such as:Make a phone call) and communication target (such as:Lao Wang), and and then obtain selection target (such as:King Pacify stone).By being the communication instruction parsed from " voice ", therefore processing unit 660 automatically provides enabling signal and opens expansion Sound equipment 650, with the subsequent call that amplifies of profit.That is, after pulling and connecting unit completion and pulling and connecting, user is set using amplifying It is standby directly to talk with Lao Wang.Alternatively, in another example, when user says against mobile terminal apparatus " answer the call ", language at this time After sound sampling module 610 receives this sound, input speech signal SAI is changed into, and this input speech signal SAI passes through voice The parsing of Understanding Module obtains communication instruction (such as:It answers the call).By being the communication instruction parsed from " voice ", Gu Chu Reason unit 660 automatically provides enabling signal and opens public address equipment 650, and public address equipment can be utilized directly and Lao Wang with sharp user Dialogue.Configuration mode on above-mentioned speech understanding module has been described in the embodiment of front with correlative detail, no longer superfluous herein It states.In addition, on communication target and last obtained selection target, embodiments thereof can take foregoing utilization high in the clouds to take The method or other similar methods of business device, details are not described herein.It is of course also possible, as described before, when public address equipment 650 and earphone 670 And in the case of depositing, processing unit 660 can be according to the setting of user, and it is the first preferential talking mode to make the call of earphone 670, is expanded Sound equipment 650 is the second preferential talking mode.
In another example, if user by the display unit 430 of similar Fig. 4, to utilize button or touch-control Select in address list " WANG Zeng-qi " when, when providing input operation signal SIO by then passing through input unit 620, processing unit 660 can carry out address book data matching according to input operation signal SIO, and pass through processing unit 660, pull and connect unit 630 and make Exports audio signal SAO is sent to the sound output interfaces such as public address equipment 650, receiver 640 or earphone 670 by the setting of user, So that user can talk with WANG Zeng-qi.
According to above-mentioned, can converge it is whole go out a mobile terminal apparatus a kind of call sound amplification function automatic starting method.Fig. 7 is The flow chart of the automatic starting method of the call sound amplification function of mobile terminal apparatus according to one embodiment of the invention.Please join simultaneously According to Fig. 7, in the present embodiment, judge whether the processing unit 660 of mobile terminal apparatus 600 by unlatching pulls and connects function (step S710).In other words, the input operation signal SIO from input unit 620 or the input voice of speech sample module 610 letter Number SAI may not be likely to be the other operations of progress with pulling and connecting related.Such as:Enable the computer in mobile terminal apparatus Function or utilization voice system inquiry weather etc..When unlatching is pulled and connected unit by processing unit 660 according to input-signal judging 630 when pulling and connecting function, that is, input signal pulls and connects that action is related with one, the judging result of step S710 is "Yes", then performs Step S720;Conversely, when processing unit 660 will not pull and connect function according to input-signal judging, that is, step S710 sentences Disconnected result is "No", then terminates the automatic starting method of this call sound amplification function.
Then, in step S720, judge whether processing unit 660 receives to open the input voice for pulling and connecting function letter Number SAI.When processing unit 660 receive from speech sample module 610 opening the input speech signal SAI for pulling and connecting function When, that is, the judging result of step S720 is "Yes", whether meeting detection process unit 660 is connected (step S730) with earphone 670. When processing unit 660 is connected with earphone 670, that is, the judging result of step S730 is "Yes", and processing unit 660 automatically provides Enabling signal is to start earphone, and exports audio signal SAO is to earphone 670 (step S740);Conversely, work as processing unit 660 not When being connected with earphone 670, that is, the judging result of step S730 is "No", and processing unit 660 automatically provides enabling signal to open Dynamic public address equipment 650, and voice signal SAO is exported to the public address equipment 650 of mobile terminal apparatus 600, to open mobile terminal The call sound amplification function (step S750) of device 600.It is noted that pull and connect work(when processing unit 660 receives to open During the input speech signal of energy, above-mentioned step 730~step 750 is that earphone 670 is set as to preferential sound in user It is carried out in the case of output interface (assuming that public address equipment 650 and all lines of earphone 670).In other embodiments, user Public address equipment 650 can be set as to preferential sound output interface.Certainly, in earphone 670 and public address equipment 650 only wherein One of line when, then can set the sound output interface of equipment on line as priority.Above-mentioned implementation steps are this field Technical staff can make corresponding variation according to its demand.
On the other hand, when processing unit 660 is not received from speech sample module 610 function is pulled and connected to open During input speech signal SAI, that is, the judging result of step S720 be "No", can then detection process unit 660 whether with ear Machine 670 connects (step S760).Specifically, processing unit 660 does not receive the input voice letter from speech sample module 610 Number SAI, but unlatching is pulled and connected function by processing unit again, represents that processing unit 660 receives the input operation from input unit 620 Signal SIO, and with one to pull and connect action related by this input operation signal SIO.When processing unit 660 is connected with earphone 670, that is, The judging result of step S760 is "Yes", and processing unit 660 can automatically provide enabling signal to start earphone 670, and export language Sound signal SAO is to earphone 670 (step S740).Conversely, when processing unit 660 is not connected with earphone 670, that is, step S760 Judging result for "No", processing unit 660 provides output voice signal SAO to public address equipment and receiver according to a preset value One of them (step S770).Wherein, as purposes of discussion, the embodiment of the present invention is not limited for the order system of above-mentioned steps. It is noted that when step 760 is judged as " be ", then exports audio signal SAO will be provided to earphone 670, and above-mentioned condition is Earphone 670 is set as preferential sound output interface (assuming that receiver 640, public address equipment 650, earphone 670 all connect by user Line) situation.In other embodiments, receiver 640 or public address equipment 650 can also be set as that preferential sound is defeated by user Outgoing interface.Certainly, in receiver 640, public address equipment 650,670 equipment of earphone only one of them line, then it can set and connect The sound output interface of the equipment of line as priority.Above-mentioned implementation steps can correspond to for those skilled in the art according to its demand Variation.
In conclusion the automatic starting method of the mobile terminal apparatus of the embodiment of the present invention and its sound amplification function of conversing, when When processing unit is received to open the input speech signal for pulling and connecting function, in addition to function is pulled and connected in unlatching, can more it automatically turn on Sound amplification function will export voice signal to public address equipment.Thus, when user can not touch mobile terminal dress immediately When putting, but sound amplification function need to be made, can sound amplification function be started by voice system, to improve the ease of use of mobile terminal.
Although the present invention is disclosed as above with embodiment, however, it is not to limit the invention, and those skilled in the art exist It does not depart from the spirit and scope of the present invention, when can make a little change and retouch, therefore protection scope of the present invention is appended when regarding Subject to claims confining spectrum.

Claims (23)

1. a kind of speech control system, including:
One auxiliary actuating apparatus, to aid in opening a voice system of a mobile terminal apparatus, which includes One first wireless transport module;And
The mobile terminal apparatus, the mobile terminal apparatus include:
One second wireless transport module is matched with first wireless transport module;
The voice system couples second wireless transport module;
One voice identification module;And
One speech processing module,
Wherein, when the auxiliary actuating apparatus is triggered, which passes through a wireless communication protocol and the shifting Second wireless transport module connection of dynamic terminal installation, to start the voice system of the mobile terminal apparatus,
Wherein, which receives the voice signal of the voice system, which is converted into multiple segmentations Semanteme and
Wherein, which parses according to the plurality of segmentation semanteme and means representated by the plurality of segmentation semanteme.
2. speech control system as described in claim 1, wherein the assistant starting equipment are only whole to aid in opening the movement The voice system of end device does not possess the function of earphone, microphone or combination.
3. speech control system as described in claim 1 further includes a hands-free headsets, with the mobile terminal apparatus line.
4. speech control system as described in claim 1 further includes a hands-free microphone, with the mobile terminal apparatus line.
5. speech control system as described in claim 1, the wherein auxiliary actuating apparatus further include a trigger module, the triggering Module is coupled with first wireless transport module.
6. speech control system as claimed in claim 5, wherein when the trigger module is triggered, if the first wireless biography Defeated module is in a sleep pattern, then the trigger module wakes up first wireless transport module, makes first wireless transport module Into an operating mode, and second wireless transport module for passing through the wireless communication protocol and the mobile terminal apparatus links.
7. speech control system as claimed in claim 6, wherein after first wireless transport module enters the operating mode A preset time in, if the trigger module is not triggered, then first wireless transport module from the operating mode into should Sleep pattern, and stop linking with second wireless transport module of the mobile terminal apparatus.
8. speech control system as described in claim 1, the wherein auxiliary actuating apparatus are a bluetooth headset.
9. the body of speech control system as described in claim 1, the wherein auxiliary actuating apparatus is the body of an ornament.
10. speech control system as claimed in claim 9, the wherein ornament include ring, wrist-watch, earrings, necklace, eye Mirror.
11. speech control system as described in claim 1, the wherein mobile terminal apparatus use Android operation system.
12. a kind of auxiliary actuating apparatus, to aid in opening a voice system of a mobile terminal apparatus and cause the movement One voice identification module of terminal receives the voice signal of the voice system so that the voice signal is converted into multiple segmentation semantemes, And a speech processing module of the mobile terminal is caused to parse the plurality of segmentation semantic institute's generation according to the plurality of segmentation semanteme Table it is meant that the mobile terminal apparatus includes one first wireless transport module, couple the voice of first wireless transport module System, the voice identification module and the speech processing module, the auxiliary actuating apparatus include:
One second wireless transport module is matched with first wireless transport module;And
One trigger module couples second wireless transport module,
Wherein when the trigger module is triggered, which passes through a wireless communication protocol and the mobile terminal First wireless transport module connection of device, to start the voice system of the mobile terminal apparatus.
13. auxiliary actuating apparatus as claimed in claim 12, wherein the assistant starting equipment are only aiding in opening the movement The voice system of terminal installation does not possess the function of earphone, microphone or combination.
14. auxiliary actuating apparatus as claimed in claim 12, wherein when the trigger module is triggered, if this is second wireless Transport module is in a sleep pattern, then the trigger module wakes up second wireless transport module, makes the second wireless transmission mould Block enters an operating mode, and first wireless transport module for passing through the wireless communication protocol and the mobile terminal apparatus connects Knot.
15. auxiliary actuating apparatus as claimed in claim 14, wherein entering the operating mode in second wireless transport module In a preset time afterwards, if the trigger module is not triggered, then second wireless transport module enters from the operating mode The sleep pattern, and stop linking with first wireless transport module of the mobile terminal apparatus.
16. auxiliary actuating apparatus as claimed in claim 12, the wherein auxiliary actuating apparatus are a bluetooth headset.
17. the body of auxiliary actuating apparatus as claimed in claim 12, the wherein auxiliary actuating apparatus is the shape of an ornament Body.
18. auxiliary actuating apparatus as claimed in claim 17, the wherein ornament include ring, wrist-watch, earrings, necklace, eye Mirror.
19. auxiliary actuating apparatus as claimed in claim 12, the wherein mobile terminal apparatus use Android operation system.
20. a kind of method of speech control, suitable for a mobile terminal apparatus and an auxiliary actuating apparatus, the auxiliary actuating apparatus To aid in opening a voice system of the mobile terminal apparatus, which has one first wireless transport module, The mobile terminal apparatus has one second wireless transport module being mutually matched with first wireless transport module, the voice system System, a voice identification module and a speech processing module, the method for the speech control include:
First wireless transport module receives a trigger signal;
Start first wireless transport module, and send a wireless transmission signal;
Second wireless transport module receives the wireless transmission signal, to start the voice system;
The voice identification module receives the voice signal of the voice system, and it is semantic which is converted into multiple segmentations; And
The speech processing module is parsed according to the plurality of segmentation semanteme to be meant representated by the plurality of segmentation semanteme.
21. the method for speech control as claimed in claim 20, wherein the assistant starting equipment are only aiding in opening the shifting The voice system of dynamic terminal installation does not possess the function of earphone, microphone or combination.
22. the method for speech control as claimed in claim 20, the wherein auxiliary actuating apparatus are a bluetooth headset.
23. the method for speech control as claimed in claim 20, the wherein mobile terminal apparatus use Android operations system System.
CN201711423107.7A 2012-12-31 2013-05-17 Auxiliary actuating apparatus, speech control system and its method Pending CN108124043A (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN 201210593061 CN103077716A (en) 2012-12-31 2012-12-31 Auxiliary starting device and speed control system and method
CN2012105930614 2012-12-31
CN2013101832176A CN103280086A (en) 2012-12-31 2013-05-17 Auxiliary starter, voice control system and method thereof

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN2013101832176A Division CN103280086A (en) 2012-12-31 2013-05-17 Auxiliary starter, voice control system and method thereof

Publications (1)

Publication Number Publication Date
CN108124043A true CN108124043A (en) 2018-06-05

Family

ID=48154224

Family Applications (3)

Application Number Title Priority Date Filing Date
CN 201210593061 Pending CN103077716A (en) 2012-12-31 2012-12-31 Auxiliary starting device and speed control system and method
CN201711423107.7A Pending CN108124043A (en) 2012-12-31 2013-05-17 Auxiliary actuating apparatus, speech control system and its method
CN2013101832176A Pending CN103280086A (en) 2012-12-31 2013-05-17 Auxiliary starter, voice control system and method thereof

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN 201210593061 Pending CN103077716A (en) 2012-12-31 2012-12-31 Auxiliary starting device and speed control system and method

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN2013101832176A Pending CN103280086A (en) 2012-12-31 2013-05-17 Auxiliary starter, voice control system and method thereof

Country Status (2)

Country Link
CN (3) CN103077716A (en)
TW (1) TWI633484B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103728906B (en) * 2014-01-13 2017-02-01 江苏惠通集团有限责任公司 Intelligent home control device and method
CN103838159B (en) * 2014-03-17 2017-03-01 联想(北京)有限公司 A kind of control method, device and electronic equipment
CN104134442A (en) * 2014-08-15 2014-11-05 广东欧珀移动通信有限公司 Method and device for starting voice services
WO2018023417A1 (en) * 2016-08-02 2018-02-08 张阳 Information pushing method for use when making telephone call, and glasses
CN106714023B (en) * 2016-12-27 2019-03-15 广东小天才科技有限公司 A kind of voice awakening method, system and bone conduction earphone based on bone conduction earphone
TWI712944B (en) * 2019-11-28 2020-12-11 睿捷國際股份有限公司 Sound-based equipment surveillance method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1703923A (en) * 2002-10-18 2005-11-30 中国科学院声学研究所 Portable digital mobile communication apparatus and voice control method and system thereof
CN1831937A (en) * 2005-03-08 2006-09-13 台达电子工业股份有限公司 Method and device for voice identification and language comprehension analysing
CN101923539A (en) * 2009-06-11 2010-12-22 珠海市智汽电子科技有限公司 Man-machine conversation system based on natural language
US20100330908A1 (en) * 2009-06-25 2010-12-30 Blueant Wireless Pty Limited Telecommunications device with voice-controlled functions
CN102006373A (en) * 2010-11-24 2011-04-06 深圳市子栋科技有限公司 Vehicle-mounted service system and method based on voice command control
CN102779509A (en) * 2011-05-11 2012-11-14 联想(北京)有限公司 Voice processing equipment and voice processing method

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI407765B (en) * 2009-05-08 2013-09-01 Htc Corp Mobile device, power saving method and computer executable medium
CN101951553B (en) * 2010-08-17 2012-10-10 深圳市车音网科技有限公司 Navigation method and system based on speech command
CN102821424B (en) * 2011-06-09 2015-02-18 中磊电子股份有限公司 Auxiliary mobile data distribution method, communication device and mobile device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1703923A (en) * 2002-10-18 2005-11-30 中国科学院声学研究所 Portable digital mobile communication apparatus and voice control method and system thereof
CN1831937A (en) * 2005-03-08 2006-09-13 台达电子工业股份有限公司 Method and device for voice identification and language comprehension analysing
CN101923539A (en) * 2009-06-11 2010-12-22 珠海市智汽电子科技有限公司 Man-machine conversation system based on natural language
US20100330908A1 (en) * 2009-06-25 2010-12-30 Blueant Wireless Pty Limited Telecommunications device with voice-controlled functions
CN102006373A (en) * 2010-11-24 2011-04-06 深圳市子栋科技有限公司 Vehicle-mounted service system and method based on voice command control
CN102779509A (en) * 2011-05-11 2012-11-14 联想(北京)有限公司 Voice processing equipment and voice processing method

Also Published As

Publication number Publication date
TWI633484B (en) 2018-08-21
CN103077716A (en) 2013-05-01
CN103280086A (en) 2013-09-04
TW201426531A (en) 2014-07-01

Similar Documents

Publication Publication Date Title
CN103281466B (en) The method of voice interactive system, mobile terminal apparatus and voice communication
CN108124043A (en) Auxiliary actuating apparatus, speech control system and its method
US9729687B2 (en) Wearable communication device
CN108924706A (en) Bluetooth headset method for handover control, bluetooth headset and computer readable storage medium
CN105792050A (en) Bluetooth earphone and communication method based on same
KR20080072889A (en) Method and device for wireless sound production into user's ear
TW200901802A (en) Ear mounted communication devices and methods
CN205726256U (en) A kind of bluetooth earphone
CN103888165A (en) Push-to-talk interphone with multiple Bluetooth link mobile terminals
CN105975063A (en) Method and device for controlling intelligent terminal
CN103517170A (en) Remote-control earphone with built-in cellular telephone module
US8934886B2 (en) Mobile apparatus and method of voice communication
CN108923810A (en) Interpretation method and relevant device
CN104519163A (en) Intelligent wearable device with phone answering function
CN205510026U (en) Miniature intercom
EP1271903B1 (en) Mobile phone monitor and remote control system
CN103281450B (en) Mobile terminal apparatus and automatically open the method for voice output interface of this device
CN203377919U (en) Wrist-worn touch control intelligent telephone
CN203118191U (en) Mobile terminal remote control device
CN204392364U (en) A kind of hand ear also uses formula wireless communication apparatus
TW200832950A (en) Wireless hand-held device having Protocol Control Information Express interface
CN208940167U (en) Bluetooth headset with voice arousal function
CN102014179A (en) Discrete mobile phone
KR20210119920A (en) Housing device
CN113709906A (en) Wireless audio system, wireless communication method and device

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: 20180605

RJ01 Rejection of invention patent application after publication