KR20210015986A - Electronic device for speech recognition and method thereof - Google Patents

Abstract

Provided are an electronic device and a voice recognition method thereof. The voice recognition method of the present electronic device comprises the steps of: receiving a trigger voice; analyzing the trigger voice, and storing the characteristics of a user voice for voice recognition; determining whether or not the user voice corresponds to the characteristics of the user voice when the user voice is inputted; and performing voice recognition on the user voice when the user voice corresponds to the characteristics of the user voice. Accordingly, the user can easily use a voice recognition function of the electronic device.

Description

Electronic device and its speech recognition method {ELECTRONIC DEVICE FOR SPEECH RECOGNITION AND METHOD THEREOF}

* The present invention relates to an electronic device and a voice recognition method thereof, and more particularly, to an electronic device capable of performing voice recognition using a trigger voice, and a voice recognition method thereof.

Users want to use electronic devices more conveniently. Accordingly, technology for easily controlling electronic devices is gradually developing. That is, a technology for easily controlling an electronic device started with a method of controlling an electronic device through an input unit attached to the electronic device, and developed into a method using an external remote controller that can be controlled even in a short distance. In recent years, as the use of a display unit having a touch panel in electronic devices has become common, a technology for controlling an electronic device using a touch input is commonly used.

However, in the method of controlling an electronic device by touch, there is an inconvenience that the user must be within a distance that can be touched with the electronic device. Accordingly, the need to control electronic devices without external devices such as remote controllers within a user's close range has increased.

Accordingly, speech recognition technology has been developed, but there is a problem that the speech recognition technology responds to external noise (eg, the sound of a companion animal) in addition to the user's voice. Therefore, in order to respond only to the user's voice, a method of pressing a button attached to the electronic device or attached to a remote controller is used whenever a voice for controlling the electronic device is uttered.

However, this method caused inconvenience to the user because the user needs an action such as pressing a button attached to an electronic device or a remote controller at every utterance.

Accordingly, there has been a need for a technology that enables a user to easily use a voice recognition function even in the presence of external noise or a plurality of users.

The present invention has been devised in accordance with the above-described necessity, and an object of the present invention is to provide an electronic device and a method for recognizing a voice thereof through which a user can easily use a voice recognition function.

According to an embodiment of the present invention for achieving the above object, the voice recognition method of an electronic device includes determining whether the input user voice corresponds to a trigger voice when a user voice is input, and the user voice is a trigger voice. When it is determined as, converting the mode of the electronic device to a voice recognition mode, analyzing the user voice and storing the characteristics of the user voice, and when a control voice for controlling the electronic device is input, the control Analyzing the voice and comparing the analyzed characteristic of the control voice with the characteristic of the user voice, and performing a function corresponding to the control voice based on the comparison result.

On the other hand, the storing may include storing at least one of the energy of the user voice, a frequency bandwidth, a ringing value when the user voice is uttered, and a voice signal-to-noise ratio as a characteristic of the user voice.

And the performing of the data is obtained by analyzing at least one of the energy of the control voice, the frequency bandwidth, the ringing value at the time of the control voice, and the voice signal-to-noise ratio, the energy of the trigger voice, the frequency bandwidth, and the trigger voice. When at least one of a resonant value and a voice signal-to-noise ratio of is within a preset range of data analyzed, a function corresponding to the control voice may be performed.

On the other hand, the comparing may include, when a plurality of user voices are input, analyzing the plurality of user voices, and having a result matching the analysis result of the stored user voice among the results of analyzing the plurality of user voices. It may further include determining one user voice as the control voice, and the performing may include performing a function corresponding to the determined at least one control voice.

And when the analyzed control voice characteristic does not correspond to the user voice characteristic, the step of bypassing the control voice may be further included.

Meanwhile, the method of claim 1, further comprising displaying a UI indicating that the voice recognition mode is in the case where the user voice is determined as a trigger voice and the mode of the electronic device is converted to the voice recognition mode. .

The displaying may include displaying an indicator on the UI when a function corresponding to the control voice is performed according to the comparison result.

Meanwhile, the trigger voice may be a preset voice for switching the mode of the electronic device to a voice recognition mode for performing the voice recognition.

In addition, the user voice and the control voice may be received through a microphone included in at least one of an external device or the electronic device.

Meanwhile, when the control voice is not input for a preset time, terminating the voice recognition mode may be further included.

On the other hand, according to an embodiment of the present invention, the electronic device includes a voice receiving unit receiving a user voice, a voice signal analyzing unit analyzing the received voice, a storage unit storing characteristics of the user voice, and the input user voice. It is determined whether it corresponds to the trigger voice, and when the user voice is determined to be the trigger voice, converts the mode of the electronic device to a voice recognition mode, analyzes the user voice, and stores the characteristics of the user voice in the storage unit. And a control unit for controlling the electronic device, wherein the control unit controls the voice signal analysis unit to analyze the control voice when a control voice for controlling the electronic device is input, and determines the characteristics of the analyzed control voice by the user It may be characterized in that the function corresponding to the control voice is performed based on the comparison result compared with the characteristics of the voice.

In addition, the control unit may control the storage unit to store at least one of the energy of the user voice, a frequency bandwidth, a ringing value when the user voice is uttered, and a voice signal-to-noise ratio as a characteristic of the user voice. have.

Meanwhile, the control unit includes data obtained by analyzing at least one of the energy of the control voice, the frequency bandwidth, the ringing value when the control voice is uttered, and the voice signal-to-noise ratio. When it is within a preset range of data obtained by analyzing at least one of a resonant value and a voice signal-to-noise ratio at the time of speech, control to perform a function corresponding to the control voice may be performed.

In addition, when a plurality of user voices are input through the voice receiving unit, the control unit controls the voice signal analysis unit to analyze the plurality of user voices, and the stored user voice from among the results of analyzing the plurality of user voices. At least one user voice having a result matched with the analysis result may be determined as the control voice, and control to perform a function corresponding to the determined at least one control voice.

Meanwhile, the control unit may control to bypass the control voice when the analyzed control voice characteristics do not correspond to the user voice characteristics.

And further comprising a display, the control unit, when the user voice is determined as a trigger voice and converts the mode of the electronic device to a voice recognition mode, controls the display to display a UI indicating that the voice recognition mode is in It can be characterized by that.

Meanwhile, the control unit may control the display unit to display an indicator on the UI when performing a function corresponding to the control voice according to the comparison result.

In addition, the trigger voice may be a voice preset to change the mode of the electronic device to a voice recognition mode for performing the voice recognition.

Meanwhile, the communication unit may further include a communication unit, and the control unit may control the communication unit to receive the input voice when the user voice and the control voice are input through an external device.

In addition, when the control voice is not input for a preset time, the control unit may control to end the voice recognition mode.

According to various embodiments of the present disclosure, by determining whether the user's voice uttered by the user is intentionally uttered by the user, the user can easily use the voice recognition function of the electronic device.

1 is a diagram illustrating a method of inputting a trigger voice to an electronic device according to an embodiment of the present invention;
2 is a diagram showing a method of inputting a trigger voice using an external device according to an embodiment of the present invention;
3 is a block diagram schematically showing a configuration of an electronic device according to an embodiment of the present invention;
4 is a block diagram showing in detail the configuration of an electronic device according to an embodiment of the present invention;
5 is a flowchart illustrating a method of performing voice recognition by analyzing a user's voice according to an embodiment of the present invention;
6 is a flowchart illustrating a method of performing voice recognition by analyzing a user's voice and ending a voice recognition mode according to an embodiment of the present invention; and
7 to 10 are diagrams illustrating a UI display according to an embodiment of the present invention.

Hereinafter, various embodiments of the present invention will be described in more detail with reference to the accompanying drawings. In describing the present invention, when it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the subject matter of the present invention, a detailed description thereof will be omitted. In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of users or operators. Therefore, the definition should be made based on the contents throughout this specification.

1 is a diagram illustrating a state in which a user utters a trigger voice in order to use a voice recognition function of the electronic device 100 according to an embodiment of the present invention. In FIG. 1, a TV is shown as an example of the electronic device 100, but this is only an embodiment. The electronic device 100 includes a mobile phone, a tablet PC, a digital camera, a camcorder, a notebook PC, a PDA, etc. It can be implemented with the same various electronic devices.

The electronic device 100 may include a microphone. Accordingly, the electronic device 100 may receive a user's voice spoken within a certain distance. In addition, by analyzing the voice received from the user, it is possible to determine whether it is a trigger voice. That is, the trigger voice may be a short word with a preset length of three or four syllables, such as “Hi TV”.

When it is determined that the received voice is a preset trigger voice, the electronic device 100 may change the mode of the electronic device 100 to a voice recognition mode. Also, the electronic device 100 may store characteristics of a user's voice included in the trigger voice.

Specifically, the characteristics of the user's voice may include the user's speech condition and the speech environment. The user speech condition may include energy of a user's voice and a frequency band distribution of the user's voice. In addition, the speech environment may include a resonant value (RT) or a speech signal-to-noise ratio (SNR) at the time of speech speech.

That is, the characteristics of the user's voice may include the energy of the user's voice, the distribution of the frequency band of the user's voice, the reverberation value (RT) at the time of speech, or the voice signal-to-noise ratio (SNR).

For example, the size of the user's voice who uttered a trigger voice such as "Hi TV", the frequency band distribution according to the user's gender or age, the reverberation value of the user's voice that varies depending on the location of the electronic device 100, or Voice-to-noise ratio (SNR), which varies depending on the quiet interior, the presence of a construction site outside, the presence of companion animals, and the number of people existing indoors, may correspond to the characteristics of the user's voice.

When a user voice is input after the result of analyzing the trigger voice is stored as a characteristic of the user voice, the electronic device 100 analyzes the input user voice and determines whether it corresponds to the characteristic of the stored user voice. That is, the electronic device 100 determines whether the characteristics of the input user voice are similar to the characteristics of the user voice described above.

When it is determined that the input user voice has a characteristic similar to that of the stored user voice, voice recognition for the user voice is performed. For example, if the user utters “Hi TV” as a trigger voice and utters “channel thirteen” as a characteristic of the same user voice, the electronic device 100 may change the displayed channel to number 13.

Meanwhile, FIG. 2 is a diagram illustrating a state in which a user utters a trigger voice using a remote control 10 including a microphone in order to use the voice recognition function of the electronic device 100 according to an embodiment of the present invention. .

Specifically, when a user's voice is received through the remote control 10 and the voice recognition function is performed, the user may utter a user voice after pressing the input button 20 for receiving the voice of the remote control 10. . At this time, a user voice received first after pressing the input button 20 may be a trigger voice. That is, even when a phrase such as "Hi TV" is previously set as the trigger voice in the electronic device 100, a signal indicating that a voice is input is received through the input button 20, so the first time after pressing the input button 20 The user voice received as a trigger voice may be.

Accordingly, as illustrated in FIG. 2, when the input button 20 is pressed from the user and a user voice "channel ship" is received, the electronic device 100 may recognize "channel ship" as a trigger voice. Then, the electronic device 100 converts to a voice recognition mode by a trigger voice called "channel ship" and performs voice recognition. That is, the electronic device 100 may change the displayed channel to ten (10).

With the electronic device as described above, the user can easily use the voice recognition function of the electronic device by firing a trigger voice. A specific voice recognition method of the electronic device will be described later.

3 is a block diagram schematically illustrating a configuration of an electronic device according to an embodiment of the present invention. As shown in FIG. 3, the electronic device 100 includes a voice receiving unit 110, a voice signal analyzing unit 120, a storage unit 130, and a control unit 140. At this time, the electronic device 100 may be a TV, but this is only an example, and may be implemented as various electronic devices such as a tablet PC, digital camera, camcorder, notebook PC, PDA, mobile phone, etc. have.

The voice receiver 110 is a component for receiving a user voice. The voice receiver 110 may include a microphone (not shown), and may receive a user voice through the microphone. The microphone may be included in the electronic device 100. Also, the microphone may be included in an external device. For example, the external device may be a remote controller, and the remote controller may receive a user's voice through a microphone and transmit it to the voice receiver 110.

That is, the voice receiver 110 receives the user's voice input through the microphone and processes it as electrical voice data. In addition, the voice receiver 110 transmits the processed voice data to the voice signal analysis unit 120.

The voice signal analysis unit 120 is a component for analyzing the voice received through the voice receiving unit 110. For example, the voice signal analyzer 120 may analyze the user voice to obtain the energy of the received user voice, a frequency band distribution, or a reverberation time (RT) of the user voice.

Also, as the user's voice is received, noise around the user is often received together. Accordingly, the voice signal analysis unit 120 may analyze the user voice to obtain a signal to noise ratio (SNR).

Meanwhile, the storage unit 130 may store various results analyzed by the speech signal analysis unit 120. Specifically, the storage unit 130 may store the analyzed characteristics of the user voice, that is, the energy of the received user voice, a frequency band distribution, a resonant value of the user voice, or a signal-to-noise ratio of the user voice.

In addition, the storage unit 130 may store various software modules and data for driving the electronic device 100. For example, software including a speech recognition module, a base module, a sensing module, a communication module, a presentation module, a web browser module, and a service module may be stored in the storage unit 130.

Meanwhile, the controller 140 is a component for controlling the overall operation of the electronic device 100. In particular, the control unit 140 may determine whether the voice input through the voice receiving unit 110 corresponds to a trigger voice.

The trigger voice is a voice for converting the mode of the electronic device 100 to a voice recognition mode for performing voice recognition. Specifically, the trigger voice may be a word having a length of three or four syllables preset in the electronic device 100. For example, the electronic device 100 may initially set "Hi TV" as a trigger voice. That is, the trigger voice is a user voice that uttered a preset phrase received through the voice receiver 110 as described above, or an input button included in an external device of the electronic device 100 such as a remote control is pressed and input first. It may be the user's voice.

When it is determined that the input voice corresponds to the trigger voice, the controller 140 may convert the mode of the electronic device 100 into a voice recognition mode. In addition, the control unit 140 may control the storage unit 130 to store user voice characteristics by analyzing the trigger voice through the voice signal analysis unit 120.

The characteristics of the user voice may include energy of the user voice, a frequency band distribution, a resonant value of the user voice, or a signal-to-noise ratio of the user voice, which are examples of the result of the analysis by the voice signal analysis unit 120.

Also, when a control voice for controlling the electronic device 100 is input, the controller 140 may control the voice signal analysis unit 120 to analyze the control voice.

The controller 140 may compare the analyzed characteristics of the control voice with the characteristics of the user voice stored in the storage unit 130. Further, the controller 140 may control to perform a function corresponding to the control voice based on the comparison result.

Specifically, data obtained by analyzing at least one of the energy of the control voice input through the voice receiving unit 110, the frequency bandwidth, the ringing value when the control voice is uttered, or the voice signal-to-noise ratio is the energy of the user voice corresponding to the trigger voice, When it is within a preset range of data obtained by analyzing at least one of a frequency bandwidth, a ringing value at the time of a trigger voice, or a voice signal-to-noise ratio, the controller 140 may control to perform a function corresponding to the control voice.

In addition, the control unit 140 may control the storage unit 130 to store the user speech condition or the user speech environment of the user speech analyzed by the speech signal analysis unit 120 as a characteristic of the user speech.

Meanwhile, the controller 140 may control to end the voice recognition mode when a preset time is required. That is, even if the user voice input through the voice receiver 110 is determined to be the trigger voice and the voice recognition mode is performed, when a preset time is required because the control voice is not input, the controller 140 selects the voice recognition mode. You can control it to exit.

In addition, when the characteristics of the control voice analyzed by the voice signal analysis unit 120 do not correspond to the user voice characteristics stored in the storage unit 130, the control unit 140 may control to bypass the control voice.

Meanwhile, according to FIG. 4, the electronic device 100 includes a voice receiving unit 110, an audio signal analyzing unit 120, a storage unit 130, a control unit 140, an image receiving unit 150, an image processing unit 160, A display unit 170, an audio processing unit 180, an audio output unit 190, a communication unit 200, and an input unit 210 may be included. FIG. 4 is an example of a device having various functions, such as a voice recognition function, a communication function, a video playback function, and a display function, as an example, and comprehensively shows various components. Accordingly, depending on embodiments, some of the components illustrated in FIG. 4 may be omitted or changed, and other components may be further added.

The voice receiver 110 is a component for receiving a user voice. The voice receiver 110 may include a microphone (not shown), and may receive a user's voice through the microphone. The microphone may be included in the electronic device 100. Also, the microphone may be included in an external device. For example, the external device may be a remote controller, and the remote controller may receive a user's voice through a microphone and transmit it to the voice receiver 110.

That is, the voice receiver 110 receives the user's voice input through the microphone and processes it as electrical voice data. In addition, the voice receiver 110 transmits the processed voice data to the voice signal analysis unit 120.

The voice signal analysis unit 120 is a component for analyzing the voice received through the voice receiving unit 110. For example, the voice signal analyzer 120 may analyze the user voice to obtain the energy of the received user voice, a frequency band distribution, or a reverberation time (RT) of the user voice.

Also, as the user's voice is received, noise around the user is often received together. Accordingly, the voice signal analysis unit 120 may analyze the user voice to obtain a signal to noise ratio (SNR).

Meanwhile, the storage unit 130 may store various results analyzed by the speech signal analysis unit 120. Specifically, the storage unit 130 may store the analyzed characteristics of the user voice, that is, the energy of the received user voice, a frequency band distribution, a resonant value of the user voice, or a signal-to-noise ratio of the user voice.

In addition, the storage unit 130 may store various software modules and data for driving the electronic device 100. For example, software including a speech recognition module, a base module, a sensing module, a communication module, a presentation module, a web browser module, and a service module may be stored in the storage unit 130.

Meanwhile, the controller 140 is a component for controlling the overall operation of the electronic device 100. In particular, the control unit 140 may determine whether the voice input through the voice receiving unit 110 corresponds to a trigger voice.

The trigger voice is a voice for converting the mode of the electronic device 100 to a voice recognition mode for performing voice recognition. Specifically, the trigger voice may be a word having a length of three or four syllables preset in the electronic device 100. For example, the electronic device 100 may initially set "Hi TV" as a trigger voice. That is, the trigger voice is a user voice that uttered a preset phrase received through the voice receiver 110 as described above, or an input button included in an external device of the electronic device 100 such as a remote control is pressed and the first received It may be the user's voice.

Specifically, when the preset phrase is "Hi TV", when "Hi TV" is input through the microphone, the controller 140 converts the mode of the electronic device 100 to a voice recognition mode, and input user voice " The voice signal analysis unit 120 may be controlled to analyze "Hi TV". The microphone may be included in the electronic device 100 or may be included in an external device of the electronic device 100 such as a remote control. In addition, when a user command for pressing an input button included in the remote control is input and a voice is input for the first time, the controller 140 may determine the inputted first voice as a trigger voice.

That is, when it is determined that the input voice corresponds to a preset trigger voice, the controller 140 converts the mode of the electronic device 100 to a voice recognition mode and analyzes the trigger voice through the voice signal analysis unit 120. Thus, it is possible to control the storage unit 130 to store the user voice characteristics. For example, the control unit 140 may control the storage unit 130 to store a result of analyzing the energy of the trigger voice, the frequency bandwidth, the ringing value at the time of the trigger voice, or the voice signal-to-noise ratio.

After converting to the voice recognition mode, when a control voice is input through the voice receiving unit 110, the controller 140 may control the voice signal analysis unit 120 to analyze the control voice. The control voice may include all user voices capable of controlling functions of the electronic device 100. In addition, the control unit 140 may control the voice signal analysis unit 120 to recognize and analyze a user's voice having more than a preset energy as a control voice.

For example, when the control voice “channel thirteen” is received through the voice receiving unit 110 after converting to the voice recognition mode, the control unit 140 controls “channel thirteen” through the voice signal analysis unit 120 It can be controlled to analyze the energy of the voice, the frequency bandwidth, the reverberation value when the control voice is uttered, or the voice signal-to-noise ratio.

The energy of the control voice called "channel thirteen", the frequency bandwidth, the ringing value when the control voice is uttered, or the analysis result of the voice signal-to-noise ratio are stored in the storage unit 130, and the energy of the trigger voice, the frequency bandwidth, and the trigger voice are uttered If it falls within a preset range of the result of analyzing the resonant value of the time or the voice signal-to-noise ratio, the controller 140 performs voice recognition on the control voice and selects the channel of the image displayed by the electronic device 100 thirteen times. Can be changed to

Alternatively, when a user voice “channel thirteen” is received by pressing an input button included in the external device, the controller 140 may determine “channel thirteen” as a trigger voice. In addition, the controller 140 may analyze "channel thirteen" by the above-described method, store the analysis result as a characteristic of the user's voice, and convert the mode of the electronic device 100 into a voice recognition mode. Also, the channel of the image displayed by the electronic device 100 may be changed to thirteen (13) by performing voice recognition.

And after changing the channel of the displayed image to thirteen times, when a control voice "volume up" is received through the voice receiving unit 110, the control unit 140 performs the control voice received through the voice signal analysis unit 120. It is determined whether or not the analysis result falls within a preset range of the characteristics of the user's voice. When the analyzed result falls within a preset range of the characteristics of the generated user's voice, the controller 140 may perform voice recognition and control to increase the volume of the image displayed by the electronic device 100.

Meanwhile, when a plurality of user voices are received through the voice receiving unit 110 after converting to the voice recognition mode, the control unit 140 may control the voice signal analysis unit 120 to analyze each of the plurality of user voices. In addition, among the plurality of user voices, a user voice having an analysis result similar to a characteristic result of the user voice stored in the storage unit 130 may be determined as the control voice. The controller 140 may perform voice recognition according to the determined control voice.

For example, the first, second, and third users are speaking near the electronic device 100, and the first user utters a preset trigger voice "Hi TV", and through the voice receiver 110 When the voice of the first user is received and the control unit 140 converts the mode of the electronic device 100 to the voice recognition mode, the control unit 140 performs the voice signal analysis unit 120 to analyze the trigger voice of the first user. Can be controlled.

Specifically, the voice signal analysis unit 120 may analyze the energy of the first user's voice and the frequency band distribution of the first user's voice. In addition, the voice signal analysis unit 120 may analyze the resonant value RT at the time of the first user's speech utterance and the voice signal-to-noise ratio (SNR) of the first user. In addition, the control unit 140 may control the storage unit 130 to store the analysis result of the trigger voice of the first user as a characteristic of the user voice.

After the characteristics of the user's voice for the trigger voice are stored, the first, second, and third users utter “volume up”, “end” and “channel thirteen” respectively, and the voice of each user through the voice receiver 110 When this is input, the control unit 140 may control the voice signal analysis unit 120 to analyze the input voice of each user.

The voice signal analysis unit 120 may analyze at least one of the energy of each user's voice, a frequency band distribution, a resonant value, and a voice signal-to-noise ratio. In addition, the control unit 140 may compare the analysis result of the characteristics of each user's voice with the characteristics of the user's voice stored in the storage unit 130. That is, the controller 140 may determine that the result of analyzing the “volume up” spoken by the same user is most similar to the characteristics of the user's voice stored in the storage unit 130. Accordingly, the controller 140 may control to increase the volume of the electronic device 100 according to "volume up".

In addition, the control unit 140 may bypass utterances of the second and third users having different characteristics and analysis results of the user's voice stored in the storage unit 130. Accordingly, the electronic device 100 receives "end" and "channel thirteen" through the voice receiver 110, but does not perform a function corresponding thereto.

On the other hand, the controller 140 performs voice recognition and, when a preset time is elapsed, may control to end voice recognition for the user's voice. That is, even if a command for ending speech recognition is not input from the user, if the user's voice including the control voice is not received through the voice receiver 110 for a preset time, the control unit 140 is the electronic device 100 You can control to end speech recognition.

In addition, when the characteristics of the control voice analyzed by the voice signal analysis unit 120 do not correspond to the user voice characteristics stored in the storage unit 130, the control unit 140 may control to bypass the control voice.

For example, the control unit 140 analyzes the user voice determined as the trigger voice through the voice signal analysis unit 120 and stores the speech energy of the voice and the voice signal-to-noise ratio as a characteristic of the user voice. Control.

After the characteristics of the user's voice are stored, when a control voice is received through the voice receiving unit 110, the control unit 140 stores the result of analyzing the user’s voice through the voice signal analysis unit 120 It is determined whether it corresponds to the characteristic of voice. In addition, when it is determined that the user voice does not correspond to the characteristics of the user voice because the trigger voice and the speech energy or the voice signal-to-noise ratio are different from each other, the electronic device 100 responds by the received user voice as described above. It is possible to control to bypass the received user voice so that it is not controlled.

Meanwhile, the image receiving unit 150 receives image data through various sources. For example, the image receiver 150 may receive broadcast data from an external broadcasting station, receive image data in real time from an external server, and receive image data stored in the internal storage unit 130. have.

The image processing unit 160 is a component that processes image data received by the image receiving unit 150. The image processing unit 160 may perform various image processing such as decoding, scaling, noise filtering, frame rate conversion, and resolution conversion on image data.

The display unit 170 displays at least one of a video frame processed by the image processing unit 160 and various screens generated by the graphic processing unit 143 of image data received from the image receiving unit 150.

In particular, the display unit 170 may display a UI indicating that it is in the voice recognition mode. For example, when “Hi TV” is input through the voice receiving unit 110 and “Hi TV” input through the voice signal analysis unit 120 is analyzed and determined as a trigger voice, the display unit 170 A UI indicating that the trigger voice has been recognized and that the mode of the electronic device 100 is in the voice recognition mode may be displayed.

Specifically, as illustrated in FIG. 7, the display unit 170 may display “the following words: Channel nineteen, volume up” as an example of a voice recognition function. In addition, the display unit 170 may display "What would you like to do?" as a phrase indicating that the user's voice is ready to be received.

In addition, when a control voice is input in the voice recognition mode to perform a function corresponding to the control voice, the display unit 170 may display an indicator on the UI under the control of the control unit 140.

Specifically, while the control voice is input through the voice receiving unit 110 and the control voice is analyzed through the voice signal analysis unit 120 in the voice recognition mode state, the display unit 170 informs that the control voice is being analyzed. A preset color (eg, white) may be displayed on a part of the display unit 170 or an indicator flashing a preset color (eg, white) may be displayed. The indicator as described above is only an exemplary embodiment, and the display unit 170 may display various types of indicators on a UI indicating that the voice recognition mode is in a state.

For example, as illustrated in FIG. 8, the display unit 170 may display an indicator on a microphone-shaped icon included in the UI. In addition, in order to notify that the voice is being recognized, the display unit 170 may display a phrase such as "Recognizing the voice."

Meanwhile, a UI indicating that the voice recognition mode is in a state may be displayed on a part of the display unit 170. For example, even when a trigger voice and a control voice are input as shown in FIG. 9, the display unit 170 notifies a part of the display unit 170 that it is in the voice recognition mode while continuously displaying the displayed content. UI can be displayed.

And even when the control voice is input and the control voice is analyzed, as shown in FIG. 10, the display unit 170 continuously displays the displayed content and informs a part of the display unit 170 that it is in the voice recognition mode. You can display an indicator on the UI.

The audio processing unit 180 is a component that processes audio data. The audio processing unit 180 may perform various processing such as decoding, amplification, noise filtering, or the like for audio data. Audio data processed by the audio processing unit 180 may be output to the audio output unit 190.

The audio output unit 190 is a component that outputs not only various audio data processed by the audio processing unit 180 but also various notification sounds or voice messages. In this case, the audio output unit 190 may be implemented as a speaker, but this is only an embodiment and may be implemented as an audio terminal.

The communication unit 200 is a component that communicates with various types of external devices according to various types of communication methods. The communication unit 200 may include various communication modules such as a USB module, a WiFi module, a Bluetooth module, and an NFC module. At this time, the WiFi module, the Bluetooth module, and the NFC module perform communication in a WiFi method, a Bluetooth method, and an NFC method, respectively. Among them, the NFC module refers to a module that operates in a Near Field Communication (NFC) method using a 13.56 MHz band among various RF-ID frequency bands such as 135 kHz, 13.56 MHz, 433 MHz, 860 to 960 MHz, and 2.45 GHz. In the case of using a Wi-Fi module or a Bluetooth module, various types of connection information such as an SSID and a session key may be transmitted and received first, and then various types of information may be transmitted and received after a communication connection using the same.

In addition, the communication unit 200 may receive the input voice when a user voice and a control voice are input through an external device. For example, when a user's voice is input through a microphone included in the remote control, the electronic device 100 may receive the voice input through the communication unit 200.

The input unit 210 receives a user command for controlling the overall operation of the electronic device 100. In this case, the input unit 210 may be implemented as a remote control including a vertical key and a confirmation key, but this is only an example, and may be implemented by various input devices such as a touch screen, a mouse, and a pointing device. I can.

In addition, when the input unit 210 is implemented as a remote control, the remote control may include an input button for receiving a voice. After pressing the input button on the remote control, the user can speak the user's voice. In addition, a user voice first received after pressing the input button may be a trigger voice.

Meanwhile, as shown in FIG. 4, the control unit 140 includes a RAM 141, a ROM 142, a graphic processing unit 143, a main CPU 144, and the first to n interfaces 145-1 to 145-n. ), including the bus 146. In this case, the RAM 141, the ROM 142, the graphic processing unit 143, the main CPU 144, the first to n interfaces 145-1 to 145-n, and the like may be connected to each other through the bus 146. .

The ROM 142 stores an instruction set for booting a system, and the like. When the turn-on command is input and power is supplied, the main CPU 144 copies the O/S stored in the storage unit 130 to the RAM 141 according to the instruction stored in the ROM 142 and executes the O/S. To boot the system. When booting is completed, the main CPU 144 copies various application programs stored in the storage unit 130 to the RAM 141, and executes the application programs copied to the RAM 141 to perform various operations.

The graphic processing unit 143 generates a screen including various objects such as icons, images, texts, etc. using an operation unit (not shown) and a rendering unit (not shown). The operation unit calculates attribute values such as coordinate values, shape, size, color, etc. to display each object according to the layout of the screen by using the control command received from the input unit 210. The rendering unit generates screens of various layouts including objects based on the attribute values calculated by the calculation unit. The screen generated by the rendering unit is displayed in the display area of the display unit 170. In particular, the graphic processing unit 143 may generate a UI indicating that a trigger voice has been recognized and a user voice can be received.

The main CPU 144 accesses the storage unit 130 and performs booting using the O/S stored in the storage unit 130. In addition, the main CPU 144 performs various operations using various programs, contents, and data stored in the storage unit 130.

Further, the first to nth interfaces 295-1 to 295-n are connected to the various components described above.

Meanwhile, FIG. 5 is a flowchart illustrating a method of performing voice recognition by analyzing a user voice according to an embodiment of the present invention.

First, the electronic device 100 receives a user's voice (S500). The electronic device 100 may receive a user's voice through a microphone included in the electronic device 100. In addition, a user's voice may be input through a microphone included in an external device such as a remote control.

The electronic device 100 determines whether the input user voice corresponds to the trigger voice (S510). The trigger voice may be a voice for switching the mode of the electronic device to a voice recognition mode for performing voice recognition. In addition, the trigger voice may be preset in the electronic device 100 or may be set as a specific phrase having a certain length according to the user's setting. For example, when the trigger voice is preset to “Hi, TV”, the electronic device 100 determines whether the received user voice is “Hi, TV”. When it is determined that the received user's voice is "Hi, TV" (S510-Y), the electronic device 100 converts the mode of the electronic device to a voice recognition mode (S520).

On the other hand, when the user's voice is received through an external device such as a remote control, the electronic device 100 recognizes the first received user voice as a trigger voice after the input button included in the external device such as the remote control is pressed. I can. That is, even when the trigger voice is preset to “Hi TV”, the electronic device 100 firstly inputs “channel thirteen” after an input button included in an external device such as a remote control is pressed, the input “channel” Thirteen" itself can be recognized as a trigger voice.

Further, the electronic device 100 analyzes the user voice determined as the trigger voice and stores the characteristics of the user voice (S530). Specifically, the characteristics of the user's voice may include the user's speech condition and the speech environment. The user speech condition may include energy of a user's voice and a frequency band distribution of the user's voice. In addition, the speech environment may include a resonant value (RT) or a speech signal-to-noise ratio (SNR) at the time of the user speech speech. That is, the characteristics of the user's voice may include the energy of the user's voice, the distribution of the frequency band of the user's voice, the reverberation value (RT) at the time of speech, or the voice signal-to-noise ratio (SNR).

When a control voice for controlling the electronic device 100 is input (S540-Y), the electronic device 100 analyzes the control voice and compares the characteristics of the control voice with the characteristics of the user voice (S550). The control voice may include all user voices capable of controlling functions of the electronic device 100. Also, the electronic device 100 may recognize and analyze a user's voice having more than a preset energy as a control voice.

Then, the electronic device 100 performs a function corresponding to the control voice based on the comparison result (S560). Specifically, data obtained by analyzing at least one of the energy of the control voice, the frequency bandwidth, the ringing value when the control voice is uttered, or the voice signal-to-noise ratio corresponds to the energy of the user voice corresponding to the trigger voice, the frequency bandwidth, and the trigger voice. The electronic device 100 performs a function corresponding to the control voice when it is within a preset range of data obtained by analyzing at least one of a resonant value at the time of speaking of a user voice or a voice signal-to-noise ratio.

The input user voice “Hi TV” is determined as the trigger voice, and the mode of the electronic device 100 is converted to a voice recognition mode, and the energy of “Hi TV” and the reverberation value at the time of uttering “Hi TV” are used as the user voice characteristics. After storing, the electronic device 100 receives a control voice "channel thirteen" as an example.

The electronic device 100 analyzes the energy of the input control voice "channel thirteen" and the reverberation value at the time of speech of the control voice. And if the analyzed data falls within 10% of the error range of the data value of the user's voice characteristic of the stored trigger voice, the electronic device 100 may determine that the user who uttered the trigger voice and the user who uttered the control voice are the same. have. Also, the electronic device 100 may determine that the input control voice is intentionally uttered by the user to control the electronic device 100. Accordingly, the electronic device 100 may control the displayed image to change to channel thirteen.

Meanwhile, an error range of 10% of the comparison data is only an exemplary embodiment, and may differ according to an initial setting and environment of the electronic device 100.

In addition, the speech energy and reverberation values are only an example of the characteristics of the user's speech, and the user uttering the speech, such as the frequency band distribution of the speech, the resonant value (RT) when the speech is uttered, and the speech signal to noise ratio (SNR). And, of course, all values that vary depending on the speech environment can be analyzed and stored as a user speech recognition condition.

Meanwhile, FIG. 6 is a flowchart illustrating a method of performing voice recognition by analyzing a user's voice and ending a voice recognition mode according to an embodiment of the present invention.

First, the electronic device 100 receives a user's voice (S600). The electronic device 100 may receive a user's voice through a microphone included in the electronic device 100. In addition, a user's voice may be input through a microphone included in an external device such as a remote control.

The electronic device 100 determines whether the input user voice corresponds to the trigger voice (S610). The trigger voice may be a voice for switching the mode of the electronic device to a voice recognition mode for performing voice recognition. In addition, the trigger voice may be preset in the electronic device 100 or may be set as a specific phrase having a certain length according to the user's setting. For example, when the trigger voice is preset to “Hi, TV”, the electronic device 100 determines whether the received user voice is “Hi, TV”. When it is determined that the received user's voice is "Hi, TV" (S610-Y), the electronic device 100 converts the mode of the electronic device to a voice recognition mode (S620).

On the other hand, when the user's voice is received through an external device such as a remote control, the electronic device 100 recognizes the first received user voice as a trigger voice after the input button included in the external device such as the remote control is pressed. I can. That is, even when the trigger voice is preset to “Hi TV”, the electronic device 100 firstly inputs “channel thirteen” after an input button included in an external device such as a remote control is pressed, the input “channel” Thirteen" itself can be recognized as a trigger voice.

Further, the electronic device 100 analyzes the user voice determined as the trigger voice and stores the characteristics of the user voice (S630). Specifically, the characteristics of the user's voice may include the user's speech condition and the speech environment. The user speech condition may include energy of a user's voice and a frequency band distribution of the user's voice. In addition, the speech environment may include a resonant value (RT) or a speech signal-to-noise ratio (SNR) at the time of the user speech speech. That is, the characteristics of the user's voice may include the energy of the user's voice, the distribution of the frequency band of the user's voice, the reverberation value (RT) at the time of speech, or the voice signal-to-noise ratio (SNR).

When a control voice for controlling the electronic device 100 is input (S640-Y), the electronic device 100 analyzes the control voice and compares the characteristics of the control voice with the characteristics of the user voice (S650). The control voice may include all user voices capable of controlling functions of the electronic device 100. Also, the electronic device 100 may recognize and analyze a user's voice having more than a preset energy as a control voice.

When the analyzed characteristic of the control voice falls within a preset range of the stored user voice characteristic (S660-Y), the electronic device 100 performs a function corresponding to the control voice (S670).

On the other hand, when the analyzed characteristics of the control voice is not included within the preset range of the stored user voice characteristics (S660-N), the electronic device 100 bypasses the control voice (S680).

The input user voice “Hi TV” is determined as the trigger voice, and the mode of the electronic device 100 is converted to a voice recognition mode, and the energy of “Hi TV” and the reverberation value at the time of uttering “Hi TV” are used as the user voice characteristics. After storing, the electronic device 100 receives a control voice "channel thirteen" as an example.

The electronic device 100 analyzes the energy of the input control voice "channel thirteen" and the reverberation value at the time of speech of the control voice. And if the analyzed data falls within 10% of the error range of the data value of the user's voice characteristic of the stored trigger voice, the electronic device 100 may determine that the user who uttered the trigger voice and the user who uttered the control voice are the same. have. Also, the electronic device 100 may determine that the input control voice is intentionally uttered by the user to control the electronic device 100. Accordingly, the electronic device 100 may control the displayed image to change to channel thirteen.

On the other hand, the energy of the input control voice "Channel Thirteen" and the data analyzing the reverberation value at the time of the control voice utterance fall within 10% of the error range of the data analyzing the energy of the trigger voice "Hi TV" and the reverberation value at the time of utterance. If not, the electronic device 100 may bypass the input control voice "channel thirteen". Accordingly, the electronic device 100 may not change the channel of an image to be displayed.

Meanwhile, an error range of 10% of the comparison data is only an exemplary embodiment, and may differ according to an initial setting and environment of the electronic device 100.

In addition, the speech energy and reverberation values are only an example of the characteristics of the user's speech, and the user uttering the speech, such as the frequency band distribution of the speech, the resonant value (RT) when the speech is uttered, and the speech signal to noise ratio (SNR). And, of course, all values that vary depending on the speech environment can be analyzed and stored as a user speech recognition condition.

Meanwhile, if a preset time is required (S690-Y), the electronic device 100 ends the voice recognition mode (S700). That is, after performing a function corresponding to the control voice, even if there is no input of a user command for ending the voice recognition mode, if the control voice is not input for a preset time, the sperm device 100 automatically performs the voice recognition mode. To finish. Accordingly, the electronic device 100 may not perform the function of the electronic device 100 in response to the input user voice until the input user voice is determined again as the trigger voice after the voice recognition mode ends.

According to the above-described speech recognition method, a user can easily control functions of an electronic device without error by uttering a speech without additional manipulation.

The speech recognition method of an electronic device according to the various embodiments described above may be coded with software and stored in a non-transitory readable medium. Such a non-transitory readable medium may be mounted and used in various devices.

For example, when a user voice is input, determining whether the input user voice corresponds to a trigger voice, when the user voice is determined to be a trigger voice, converting the mode of the electronic device to a voice recognition mode, and the Analyzing the user voice and storing the characteristics of the user voice, when a control voice for controlling the electronic device is input, analyzing the control voice and comparing the analyzed control voice characteristics with the characteristics of the user voice A program code for performing a step of performing a function corresponding to the control voice based on the step and the comparison result may be stored and provided in a non-transitory readable medium. In addition, the power saving processing method described in the various embodiments described above may be coded as a program and stored in a non-transitory readable medium.

The non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by a device, not a medium that stores data for a short moment, such as a register, cache, or memory. Specifically, it may be a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, or the like.

In addition, although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the present invention belongs without departing from the gist of the present invention claimed in the claims. In addition, various modifications are possible by those of ordinary skill in the art, and these modifications should not be individually understood from the technical spirit or prospect of the present invention.

100: electronic device 110: voice receiver
120: voice signal analysis unit 130: storage unit
140: control unit 150: image receiving unit
160: image processing unit 170: display unit
180: audio processing unit 190: audio output unit
200: communication unit 210: input unit

Claims (14)

In the electronic device,
MIC;
Communication Department
A receiving unit for receiving data including content; And
Process the data to display the content on the screen,
If a user voice input is received through the microphone while the content is displayed on the screen, it is determined whether the user voice input corresponds to a trigger voice input, and if the user voice input corresponds to the trigger voice input, a subsequent Perform a first voice recognition function for receiving a user voice input,
When a signal provided by the external device is received through the communication unit as a button of the external device is pressed, the first voice recognition function is performed, the first voice recognition function is performed, and the content is While being displayed on the screen, if a subsequent user voice input is received from the external device through the communication unit, a second voice for processing the subsequent user voice input without determining whether the subsequent user voice input corresponds to the trigger voice input And a processor that performs a recognition function and provides a UI indicating that the subsequent user voice input is being processed along with the content. The method of claim 1,
The UI is displayed in a first area of the screen, and the content is displayed in a second area of the screen. The method of claim 1,
The UI indicates that the subsequent user voice input is being processed in a voice recognition state. The method of claim 1,
The subsequent user voice input is received from the external device within a preset time from when the signal is received from the external device through the communication unit as a button of the external device is pressed. The method of claim 1,
The processor,
Terminating the first voice recognition function when the subsequent user voice input is not received from the external device within a preset time from when the first voice recognition function is performed as the signal is received from the external device, Electronic device. The method of claim 1,
The subsequent user voice input is a voice input for controlling a function of the electronic device,
The processor,
An electronic device that performs a function corresponding to the subsequent user input. The method of claim 1,
The processor,
When the user voice input corresponding to the trigger voice input is received through the microphone, a UI indicating a voice recognition state is provided, and
If the subsequent user voice input is received from the external device through the communication unit, providing a UI indicating that the subsequent user voice input is being processed in the voice recognition state. In the voice recognition method of an electronic device,
Receiving data including content;
Processing the data to display the content on a screen; And
When a user voice input is received through the microphone of the electronic device while the content is displayed on the screen, it is determined whether the user voice input corresponds to a trigger voice input, and the user voice input corresponds to the trigger voice input If so, performs a first voice recognition function for receiving a subsequent user voice input,
When a signal provided by the external device is received from the external device as a button of the external device is pressed, the first voice recognition function is performed, the first voice recognition function is performed, and the content is While being displayed on the screen, when a subsequent user voice input is received from the external device, a second voice recognition function is performed for processing the subsequent user voice input without determining whether the subsequent user voice input corresponds to the trigger voice input. And a processor that provides a UI indicating that the subsequent user voice input is being processed along with the content. The method of claim 8,
The UI is displayed in a first area of the screen, and the content is displayed in a second area of the screen. The method of claim 8,
Wherein the UI indicates that the subsequent user voice input is being processed in a voice recognition state. The method of claim 8,
The subsequent user voice input is received from the external device within a preset time from when the signal is received from the external device as the button of the external device is pressed. The method of claim 8,
Terminating the first voice recognition function when the subsequent user voice input is not received from the external device within a preset time from when the first voice recognition function is performed as the signal is received from the external device. A method for recognizing voice of an electronic device, further comprising. The method of claim 8,
The subsequent user voice input is a voice input for controlling a function of the electronic device,
The speech recognition method,
Performing a function corresponding to the subsequent user input; further comprising, the voice recognition method of the electronic device. The method of claim 8,
When the user voice input corresponding to the trigger voice input is received through the microphone, a UI indicating a voice recognition state is provided, and
If the subsequent user voice input is received from the external device, providing a UI indicating that the subsequent user voice input is being processed in the voice recognition state; and further comprising a voice recognition method of an electronic device.

Images