KR101728941B1 - Application operating apparatus based on voice recognition and Control method thereof - Google Patents

Abstract

The present invention discloses a speech recognition-based application driving apparatus and a control method. According to an embodiment of the present invention, there is provided a device for driving a speech recognition based application, comprising: a processor; And a memory coupled to the processor, wherein the memory is running in a background state; Storing a plurality of trigger instructions; Determine whether an incoming user voice corresponds to one of the stored plurality of trigger commands; There is provided a speech recognition based application driving apparatus for storing program instructions executable by the processor to call an application according to the corresponding trigger instruction when the user voice corresponds to one of the stored plurality of trigger instructions.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a voice recognition-

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to a device for driving a speech recognition-based application and a control method thereof, and more particularly, to a device for driving a speech recognition-based application and a control method for enabling various applications to be executed immediately with a single utterance.

Speech recognition technology converts speech user speech into electrical signals and then extracts and recognizes the frequency characteristics of the speech signal.

Recently, speech recognition technology has been used to control mobile devices.

1 is a flowchart illustrating a process of controlling a mobile device based on speech recognition according to the related art.

Referring to FIG. 1, a voice recognition application installed on a mobile device is activated by a user's operation of a button (step 100).

Here, the activation of the speech recognition application may be performed by selecting a predetermined number of times or more of the home button disposed on the front side of the mobile device, or by selecting the speech recognition application icon through the touch screen.

The activated speech recognition application determines whether a voice corresponding to one or more preset words is input from the user (step 102).

For example, one or more preset words may include words such as " high galaxy ", " GOOGLE GOOGLE ", and "

Herein, the preset one or more words are trigger commands for allowing the speech recognition application to perform a process of recognizing a user's voice inputted subsequently.

That is, the trigger command is defined as a command for performing a process of analyzing a user's voice inputted through a microphone.

If the trigger command is input and then another user voice is input, the voice recognition application recognizes the user voice (step 104) and executes the function corresponding to the recognized user voice (step 106).

According to the related art, in order to control a mobile device based on speech recognition, a button operation of a user is required to activate a voice recognition application, which may inconvenience a user in a situation where the user can not use the device during operation or freely using the device .

In addition, since the input of a predetermined trigger command is essentially required as a pre-step for executing a predetermined function, there is a problem that the user must go through various steps in order to perform a desired function originally.

In order to solve the problems of the related art as described above, the present invention proposes a speech recognition-based application driving apparatus and a control method that allow a user to use a desired function with one voice input.

Other objects of the invention will be apparent to those skilled in the art from the following examples.

According to a preferred embodiment of the present invention, there is provided a device for driving a speech recognition based application, the device comprising: a processor; And a memory coupled to the processor, wherein the memory is running in a background state; Storing a plurality of trigger instructions; Determine whether an incoming user voice corresponds to one of the stored plurality of trigger commands; There is provided a speech recognition based application driving apparatus for storing program instructions executable by the processor to call an application according to the corresponding trigger instruction when the user voice corresponds to one of the stored plurality of trigger instructions.

The application may be an application for at least one of a call, a camera, music, video, and navigation.

The plurality of trigger instructions may include an identification name and a word for application operation corresponding to the identification name.

The plurality of trigger commands may be instructions for making a call to a predetermined number or less of a plurality of contacts included in the address book.

The memory outputting an interface for selection of one or more of a plurality of contacts according to a user's request; Identify one or more contacts selected by a user from among the plurality of contacts; And store program instructions executable by the processor to generate a trigger instruction for each of the identified one or more contacts.

The memory outputting an interface for selection of one or more of a plurality of contacts according to a user's request; Identify one or more contacts selected by a user from among the plurality of contacts; When the user voice input at the first time corresponds to a preset single trigger instruction and the user voice input at the second time corresponds to the contact, Lt; RTI ID = 0.0 > executable < / RTI >

Wherein the memory is adapted to determine whether the input user voice corresponds to one of the stored plurality of trigger commands in accordance with an attitude of the driving device sensed by an embedded sensor, proximity of a user, Lt; RTI ID = 0.0 > executable < / RTI >

According to another aspect of the present invention, there is provided a device for driving a speech recognition based application, comprising: at least one sensor for sensing movement of the device, proximity of a user, or ambient brightness; A processor; And a memory coupled to the processor, the memory storing a plurality of trigger instructions; Determine whether the input user voice corresponds to one of the stored plurality of trigger commands if the device has a predetermined attitude or the user is determined to be proximate by the sensor; There is provided a speech recognition based application driving apparatus for storing program instructions executable by the processor to call an application according to the corresponding trigger instruction when the user voice corresponds to one of the stored plurality of trigger instructions.

According to another aspect of the present invention, there is provided a method of controlling a speech recognition based on an application driving apparatus, the method comprising: storing a plurality of trigger commands; Determining, in the background state, whether the incoming user voice corresponds to one of the stored plurality of trigger commands; And invoking an application according to the corresponding trigger instruction when the user voice corresponds to one of the stored plurality of trigger commands.

According to yet another aspect of the present invention, there is provided a computer program stored on a medium comprising a series of instructions for performing the method.

According to the present invention, since the speech recognition engine is executed in the background state and a plurality of trigger commands are stored, there is an advantage that it is not necessary to perform various steps for controlling the speech recognition based device.

1 is a flowchart illustrating a process of controlling a mobile device based on speech recognition according to the related art.
2 is a block diagram of a speech recognition-based driving apparatus according to a preferred embodiment of the present invention.
3-4 illustrate interfaces for establishing a limited number of contacts according to an embodiment of the present invention.
5 is a diagram illustrating a module configuration of a speech recognition engine according to an embodiment of the present invention.
6 is a diagram for explaining a speech recognition process according to a posture of an application driving apparatus according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

2 is a block diagram of a speech recognition-based driving apparatus according to a preferred embodiment of the present invention.

As shown in FIG. 2, the driving apparatus according to the present embodiment may include a processor 200 and a memory 202.

The processor 200 may include a central processing unit (CPU) or other virtual machine capable of executing a computer program.

Memory 202 may include non-volatile storage such as a fixed hard drive or a removable storage device. The removable storage device may include a compact flash unit, a USB memory stick, and the like. The memory 202 may also include volatile memory such as various random access memories.

Such memory 202 stores program instructions that are executable by the processor 200.

The speech recognition-based application driving apparatus according to the present embodiment may be a mobile apparatus having a call function, and hereinafter, the apparatus will be mainly described as a mobile apparatus, but the present invention is not limited thereto.

According to a preferred embodiment of the present invention, the memory 202 stores a plurality of trigger commands in the mobile device, determines whether the input user voice corresponds to one of a plurality of trigger commands, Program instructions for causing an application corresponding to a voice to be executed are stored.

In this specification, the speech recognition function is defined as an application that performs the above-described functions for speech recognition and application execution.

Preferably, the speech recognition engine according to the present embodiment is executed in the background state.

In addition, the speech recognition engine according to the present embodiment stores a plurality of trigger commands.

As described above, the trigger command is a command for performing a process for recognizing a user's voice. Conventionally, only a single trigger command is used.

However, the speech recognition engine according to the present embodiment stores a plurality of trigger commands and determines whether the input user voice corresponds to one of a plurality of trigger commands.

Here, a plurality of trigger commands are defined as "AAA telephone (outgoing)", "BBB telephone (reception)", "telephone reception (reception)", "music reproduction", "movie reproduction" And a word for operation of the application corresponding to the identification word.

Here, the identification word may be a contact-related word (name of the other party) included in the address book or a word related to the function such as music, camera, and the like.

According to the present embodiment, when the user voice corresponding to the trigger command is input, the voice recognition engine executed in the background state calls the application corresponding to the identification word without requesting the other operation of the user, Or music reproduction can be performed.

In order to prevent malfunction, a plurality of trigger commands may be limited to a predetermined number or less, for example, 20 or 30.

According to a preferred embodiment of the present invention, the plurality of trigger commands may include an instruction for making a call (dialing) to a predetermined number or less of a plurality of contacts included in the address book.

3-4 illustrate interfaces for establishing a limited number of contacts according to an embodiment of the present invention.

3 is an initial interface. When the user selects the contact selection menu 300 in the initial interface of FIG. 3, a contact list interface including a check box for selecting one or more of a plurality of contacts is output as shown in FIG.

As shown in FIG. 4, the contact list interface may include a wake up check box 400 and a command check box 402 for each contact.

When the wake-up check box 400 is selected, the speech recognition engine generates a trigger command for the selected contact.

For example, if a wakeup check box 400 is selected for a contact named AAA, the speech recognition engine generates a trigger command " AAA phone ", and subsequently a user voice including an " , The call application is called to make a call to the telephone number corresponding to the AAA.

As described above, generating the trigger command only for a predetermined number or less of the contacts among the plurality of contacts is for preventing the speech recognition engine from malfunctioning due to the continuously input user voice.

According to the present embodiment, the speech recognition engine can invoke the application requested by the user while maintaining the execution state, and can directly control necessary functions.

Without being limited thereto, the speech recognition engine may be terminated during execution of the application requested by the user, and may return to the background state after the execution of the requested application is terminated.

Here, when the speech recognition engine according to the present embodiment is terminated and then returned, it may be limited to the period during which the call application is executed. This means that the operation of the speech recognition engine according to the present embodiment is temporarily stopped when a call is made through the microphone.

On the other hand, when the command check box 402 is selected, a previously set single trigger command is input at the first time, and then the command check box 402 selects the "contact name" and " Quot; telephone " is input, the calling application is called.

As described above, it is possible to execute the application in accordance with a plurality of trigger commands because the speech recognition performance and the rejection performance of the speech recognition engine are enhanced.

5 is a diagram illustrating a module configuration of a speech recognition engine according to an embodiment of the present invention.

5, the speech recognition engine according to the present embodiment includes a preprocessing module 500, a rejection module 502, a garbage acoustic model 504, a phoneme analysis module 506, a phoneme model 508, Module 510, a list of trigger commands 512, and an application execution module 514.

The preprocessing module 500 searches for a section to be recognized from the input user voice, removes noise, and extracts characteristics of the input voice.

The reject module 502 refers to the garbage sound module 504 and determines whether the inputted user voice corresponds to garbage.

Only the user voice not corresponding to the garbage is input to the phoneme analysis module 506. [

The phoneme analysis module 506 refers to the phoneme model 508 and performs phoneme analysis on the user's voice.

The trigger command determination module 510 refers to the trigger command list 512 to determine whether the input user voice corresponds to one of a plurality of trigger commands stored in advance.

The application execution module 514 executes an application corresponding to the analyzed user voice when the user voice corresponds to one of a plurality of trigger commands.

According to the present embodiment, the trigger instruction list 512 can be updated by the user's contact selection and application selection process to operate based on speech recognition.

The present invention can store a plurality of trigger commands in response to a user's request, rather than a single trigger command, and allow a user to execute an application desired by the user as one step according to the inputted user's voice.

As shown in FIG. 3, when the user selects the power save mode in the interface displayed on the screen according to the execution of the speech recognition application according to the present embodiment, An analysis process such as determination of whether or not to respond to a trigger command can be performed only in a state where an external power source is connected or in a state in which a voice recognition based device control is expected to be performed by a built-in sensor.

6 is a diagram for explaining a speech recognition process according to a posture of an application driving apparatus according to an embodiment of the present invention.

The application driving apparatus according to the present embodiment may include a sensor capable of sensing an acceleration, an angular velocity, or a magnetic field change according to movement of the apparatus, such as an acceleration sensor, a gyro sensor, and a magnetic field sensor, .

Further, according to the present embodiment, a brightness sensor can be additionally used.

Here, when the illuminance is low due to the brightness sensor, it is located in the pocket, and when the illuminance is higher than a predetermined value, it can be determined that the user intends to use the mobile device.

By the built-in sensor, the control process by voice recognition can be performed only when the attitude of the application driving apparatus has a predetermined attitude or when it is determined that the user is close or when the brightness is equal to or greater than a predetermined value.

If the device is a mobile device, the preset orientation may be set to the range of the tilt (angle) of the mobile device relative to the ground.

For example, when a horizontal state on the ground is defined as 0 degrees, a predetermined attitude for speech recognition may be defined as a case where the inclination of the mobile device is in the range of 60 to 300 degrees. Where the angle may be an angle to at least one of the x, y, and z axes.

Referring to FIG. 6, the speech recognition engine uses information sensed by the built-in sensor to determine whether the attitude of the device is a preset attitude or proximity of a user (step 600).

Here, the step 600 may be defined as a process of determining whether to perform the recognition process of the user's voice.

If it is determined that the device has a preset attitude or there is a user proximity, the speech recognition engine analyzes the inputted user voice to determine whether it corresponds to one of a plurality of trigger commands (step 602).

In step 602, determination of rejection and phoneme analysis using the garbage acoustic model may be performed.

If the user voice corresponds to one of the plurality of trigger commands, the speech recognition engine invokes the application according to the corresponding trigger command (step 604).

Then, it is determined whether or not the called application is terminated (step 606), and the speech recognition engine returns to the background state after the application is terminated (step 608).

The above-described steps 606 to 608 may be selectively performed only when a call application is called.

As described above, the present invention has been described with reference to particular embodiments, such as specific elements, and specific embodiments and drawings. However, it should be understood that the present invention is not limited to the above- And various modifications and changes may be made thereto by those skilled in the art to which the present invention pertains. Accordingly, the spirit of the present invention should not be construed as being limited to the embodiments described, and all of the equivalents or equivalents of the claims, as well as the following claims, belong to the scope of the present invention .

Claims (10)

A speech recognition-based application driver,
A processor; And
A memory coupled to the processor,
The memory comprising:
Run in background state;
Storing a plurality of trigger instructions;
Determine whether an incoming user voice corresponds to one of the stored plurality of trigger commands;
Storing program instructions executable by the processor to call an application according to the corresponding trigger instruction if the user voice corresponds to one of the stored plurality of trigger instructions,
Wherein the program instructions are terminated during execution of the called application and return to the background state upon termination of the called application,
Wherein the trigger instruction comprises an identification word and a word for application operation corresponding to the identification word, the identification word and the word for application operation being limited to a predetermined number or less,
The plurality of trigger commands are commands for making a call to a contact of a predetermined number or less among a plurality of contacts included in the address book
Wherein the program instructions generate a single trigger instruction for a contact selected by a user at a first point in time, and if the user voice input at a second point in time after the first point of time includes the contact from which the single trigger command was generated, Wherein the single triggering instruction causes the application to execute a call to the generated contact.
The method according to claim 1,
Wherein the application is an application for at least one of a call, a camera, music, video, and navigation.
delete delete The method according to claim 1,
The memory comprising:
Outputting an interface for selection of one or more of the plurality of contacts according to a user's request;
Identify one or more contacts selected by a user from among the plurality of contacts;
To generate a trigger command for each of the identified contacts
And storing program instructions executable by the processor.
delete The method according to claim 1,
The memory comprising:
And determines whether or not the input user voice corresponds to one of the stored plurality of trigger commands according to the posture of the driving device sensed by the built-in sensor, proximity of the user, or ambient brightness
And storing program instructions executable by the processor. A speech recognition-based application driver,
One or more sensors for sensing movement of the device, proximity of a user, or ambient brightness;
A processor; And
A memory coupled to the processor,
The memory comprising:
Storing a plurality of trigger instructions;
Determine whether the input user voice corresponds to one of the stored plurality of trigger commands if the device has a predetermined attitude or the user is determined to be proximate by the sensor;
Storing program instructions executable by the processor to call an application according to the corresponding trigger instruction if the user voice corresponds to one of the stored plurality of trigger instructions,
Wherein the trigger instruction comprises an identification word and a word for application operation corresponding to the identification word, the identification word and the word for application operation being limited to a predetermined number or less,
Wherein the plurality of trigger commands are instructions for making a call to a predetermined number or less of a plurality of contacts included in the address book,
Wherein the program instructions generate a single trigger instruction for a contact selected by a user at a first point in time, and if the user voice input at a second point in time after the first point of time includes the contact from which the single trigger command was generated, Wherein the single triggering instruction causes the application to execute a call to the generated contact.
A speech recognition-based control method of an application driving apparatus,
Storing a plurality of trigger instructions;
Determining, in the background state, whether the incoming user voice corresponds to one of the stored plurality of trigger commands;
Invoking an application according to the corresponding trigger instruction if the user voice corresponds to one of the stored plurality of trigger instructions;
Terminating the execution of the called application; And
When the called application is terminated, returning to the background state
Lt; / RTI >
Wherein the trigger instruction comprises an identification word and a word for application operation corresponding to the identification word, the identification word and the word for application operation being limited to a predetermined number or less,
Wherein the plurality of trigger commands are instructions for making a call to a predetermined number or less of a plurality of contacts included in the address book,
Wherein the storing of the plurality of trigger instructions comprises:
Generating a single trigger instruction for the contact selected by the user,
The method of claim 1,
And if the user voice includes the contact from which the single triggering instruction was generated, causing the single triggering instruction to execute an application for a call to the generated contact.
A computer program stored in a medium comprising a series of instructions for performing the method according to claim 9.

Images