KR102158210B1 - Speech recognition apparatus and method thereof - Google Patents

Abstract

The present specification relates to a speech recognition apparatus and method capable of accurately recognizing a user's voice by changing a threshold value according to a user usage pattern. The speech recognition apparatus according to an embodiment disclosed in the present specification includes a predetermined reliability score A voice recognition unit for recognizing a user's voice based on voice models; And a control unit for allowing or rejecting the recognized user voice based on a reliability score and a threshold value of the recognized user voice, and the control unit may change the threshold value according to a user voice pattern.

Description

Speech recognition apparatus and its method TECHNICAL FIELD [SPEECH RECOGNITION APPARATUS AND METHOD THEREOF}

The present specification relates to a speech recognition apparatus and method thereof.

In general, a speech recognition apparatus according to the prior art receives the uttered speech signal when a user utters, compares the received speech signal with a predetermined model, and recognizes the user speech according to the comparison result. do. That is, the speech recognition system according to the prior art recognizes the user's voice through a method of measuring confidence. A speech recognition apparatus according to the prior art is disclosed in Korean Patent Application No. 10-2009-0057093.

An object of the present specification is to provide a speech recognition apparatus and method capable of accurately recognizing a user's voice by changing a threshold value according to a user usage pattern.

A speech recognition apparatus according to an embodiment disclosed in the present specification includes: a speech recognition unit for recognizing a user speech based on predetermined speech models providing a reliability score; And a control unit for allowing or rejecting the recognized user voice based on a reliability score and a threshold value of the recognized user voice, and the control unit may change the threshold value according to a user voice pattern.

As an example related to the present specification, the controller may increase or decrease the threshold value according to the voice pattern used by the user.

As an example related to the present specification, the controller may allow the recognized user voice if the reliability score of the recognized user voice is higher than the increased or decreased threshold.

As an example related to the present specification, the control unit may reject the recognized user voice when the reliability score of the recognized user voice is lower than the increased or decreased threshold.

As an example related to the present specification, the controller may change the threshold value based on the voice pattern used by the user classified in advance according to the function of the video display device.

As an example related to the present specification, the pre-categorized user use voice pattern includes a first user voice usage rate for controlling a channel and volume of the video display device, and a first user voice usage rate for controlling a channel and volume of the video display device, 2 Including at least one or more of a usage rate of a user's voice, a usage rate of a third user's voice for executing an application program through the video display device, and a usage rate of a fourth user voice for searching a broadcast program by the video display device. An audio processing device characterized in that.

As an example related to the present specification, the control unit may preset the user use voice pattern.

As an example related to the present specification, the controller may receive the user use voice pattern from a server.

As an example related to the present specification, the user voice usage rate may be an average user voice usage rate.

As an example related to the present specification, when multiple user voices having similar pronunciation are recognized, the controller may increase the probability of recognizing the plurality of user voices having similar pronunciation by increasing the threshold.

A speech recognition method according to an embodiment disclosed herein includes the steps of recognizing a user's speech based on predetermined speech models providing a confidence score; Changing a threshold according to a user's voice pattern; And allowing or rejecting the recognized user voice based on the reliability score of the recognized user voice and the threshold.

The voice recognition apparatus and method thereof according to embodiments of the present invention change a threshold according to a user usage pattern (a usage rate of each user's voice classified in advance according to functions of an electronic device such as a video display device and a mobile communication terminal). Thus, the user's voice can be accurately recognized.

The voice recognition apparatus and method according to embodiments of the present invention can accurately recognize a user voice by changing a threshold value according to a user use function pattern (a usage rate of each function of an electronic device such as a video display device and a mobile communication terminal). I can.

1 is a block diagram showing an image display device and an external input device related to the present invention.
2 is a block diagram illustrating a configuration of a 3D image display device to which an image processing device according to embodiments of the present invention is applied.
3 is a flow chart showing a speech recognition method according to an embodiment of the present invention.
4 is an exemplary diagram showing a user use voice pattern according to an embodiment of the present invention.
5 is a flowchart illustrating a speech recognition method according to another embodiment of the present invention.
6 is an exemplary diagram showing a user use function pattern according to an embodiment of the present invention.

It should be noted that the technical terms used in the present specification are only used to describe specific embodiments, and are not intended to limit the present invention. In addition, the technical terms used in the present specification should be interpreted as generally understood by those of ordinary skill in the technical field to which the present invention belongs, unless otherwise defined in the present specification, and excessively comprehensive It should not be construed as a human meaning or an excessively reduced meaning. In addition, when a technical term used in the present specification is an incorrect technical term that does not accurately express the spirit of the present invention, it will be replaced with a technical term that can be correctly understood by those skilled in the art to be understood. In addition, general terms used in the present invention should be interpreted as defined in the dictionary or according to the context before and after, and should not be interpreted as an excessively reduced meaning.

In addition, the singular expression used in the present specification includes a plurality of expressions unless the context clearly indicates otherwise. In the present application, terms such as "consist of" or "include" should not be construed as necessarily including all of the various elements or various steps described in the specification, and some of the elements or some steps It may not be included, or it should be interpreted that it may further include additional elements or steps.

In addition, terms including ordinal numbers such as first and second used herein may be used to describe various elements, but the elements should not be limited by the terms. These terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numerals regardless of the reference numerals, and redundant descriptions thereof will be omitted.

In addition, in describing the present invention, when it is determined that a detailed description of a related known technology may obscure the subject matter of the present invention, a detailed description thereof will be omitted. In addition, it should be noted that the accompanying drawings are only for easily understanding the spirit of the present invention and should not be construed as limiting the spirit of the present invention by the accompanying drawings.

In this specification, the video display device includes both a device for receiving and displaying a broadcast, recording and reproducing a video, and a device for recording and reproducing audio. Hereinafter, as such an example, a television will be described as an example.

1 is a block diagram showing an image display device 100 and an external input device 190 related to the present invention. The video display device 100 includes a tuner 110, a demodulation unit 120, a signal input/output unit 130, an interface unit 140, a control unit 150, a storage unit 160, a display unit 170, and an audio system. It includes an output unit 180. However, the external input device 190 may be a separate device from the image display device 100 or may be included as a component of the image display device 100.

Referring to FIG. 1, the tuner 110 selects an RF broadcast signal corresponding to a channel selected by a user among radio frequency (RF) broadcast signals received through an antenna, and converts the RF broadcast signal to an intermediate frequency signal or a baseband image. /Convert to audio signal. For example, if the RF broadcast signal is a digital broadcast signal, the tuner 110 converts the RF broadcast signal into a digital IF signal (DIF). On the other hand, if the RF broadcast signal is an analog broadcast signal, the tuner 110 converts the RF broadcast signal into an analog baseband video/audio signal (CVBS/SIF). As such, the tuner 110 may be a hybrid tuner capable of processing a digital broadcast signal and an analog broadcast signal.

The digital IF signal (DIF) output from the tuner 110 is input to the demodulator 120, and the analog baseband video/audio signal (CVBS/SIF) output from the tuner 110 is input to the controller 160. I can. The tuner 120 may receive an RF broadcast signal of a single carrier according to an Advanced Television Systems Committee (ATSC) method or an RF broadcast signal of multiple carriers according to a Digital Video Broadcasting (DVB) method.

Although one tuner 110 is shown in the drawing, the present invention is not limited thereto, and the video display device 100 may include a plurality of tuners, for example, first and second tuners. In this case, the first tuner may receive the first RF broadcast signal corresponding to the broadcast channel selected by the user, and the second tuner may sequentially or periodically receive the second RF broadcast signal corresponding to the previously stored broadcast channel. . The second tuner may convert an RF broadcast signal into a digital IF signal (DIF) or an analog baseband video/audio signal (CVBS/SIF) in the same manner as the first tuner. In embodiments of the present invention, only one tuner 110 is used, thereby reducing manufacturing cost.

The demodulator 120 receives the digital IF signal DIF converted by the tuner 110 and performs a demodulation operation. For example, if the digital IF signal DIF output from the tuner 110 is an ATSC method, the demodulator 120 performs 8-VSB (8-Vestigal Side Band) demodulation. In this case, the demodulator 120 may perform channel decoding such as trellis decoding, de-interleaving, and Reed-Solomon decoding. To this end, the demodulator 120 may include a Trellis decoder, a de-interleaver, a Reed Solomon decoder, and the like.

For another example, if the digital IF signal DIF output from the tuner 110 is a DVB type, the demodulator 120 performs Coded Orthogonal Frequency Division Modulation (COFDMA) demodulation. In this case, the demodulator 120 may perform channel decoding such as convolutional decoding, deinterleaving, and Reed-Solomon decoding. To this end, the demodulator 120 may include a convolution decoder, a deinterleaver, and a Reed-Solomon decoder.

The signal input/output unit 130 is connected to an external device to perform signal input and output operations, and to this end, may include an A/V input/output unit and a wireless communication unit.

A/V input/output is an Ethernet terminal, USB terminal, CVBS (Composite Video Banking Sync) terminal, component terminal, S-video terminal (analog), DVI (Digital Visual Interface) terminal, HDMI (High Definition Multimedia Interface) terminal , Mobile High-definition Link (MHL) terminal, RGB terminal, D-SUB terminal, IEEE 1394 terminal, SPDIF terminal, Liquid HD terminal, and the like. Digital signals input through these terminals may be transmitted to the controller 150. In this case, the analog signal input through the CVBS terminal and the S-video terminal may be converted into a digital signal through an analog-digital converter (not shown) and transmitted to the controller 150.

The wireless communication unit may perform wireless Internet access. For example, the wireless communication unit performs wireless Internet access using WLAN (Wireless LAN) (Wi-Fi), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access), etc. can do. In addition, the wireless communication unit may perform short-range wireless communication with other electronic devices. For example, the wireless communication unit can perform short-range wireless communication using Bluetooth, Radio Frequency Identification (RFID), infrared data association (IrDA), Ultra Wideband (UWB), and ZigBee. have.

The signal input/output unit 130 includes video signals and audio provided from external devices such as a digital versatile disk (DVD) player, a Blu-ray player, a game device, a camcorder, a computer (laptop), a mobile device, and a smart phone. Signals and data signals may be transmitted to the controller 150. In addition, video signals, audio signals, and data signals of various media files stored in an external storage device such as a memory device or a hard disk may be transmitted to the controller 150. Also, an image signal, an audio signal, and a data signal processed by the control unit 150 may be output to another external device.

The signal input/output unit 130 may be connected to a set-top box, for example, a set-top box for Internet Protocol TV (IPTV) through at least one of the aforementioned various terminals to perform signal input and output operations. For example, the signal input/output unit 130 may transmit a video signal, an audio signal, and a data signal processed by the IPTV set-top box to enable two-way communication, and the processed by the control unit 150 The signals can also be delivered to a set-top box for IPTV. Here, IPTV may include ADSL-TV, VDSL-TV, FTTH-TV, etc. classified according to transmission networks.

The digital signals output from the demodulation unit 120 and the signal output unit 130 may include a stream signal TS. The stream signal TS may be a signal in which a video signal, an audio signal, and a data signal are multiplexed. For example, the stream signal TS may be an MPEG-2 Transprt Stream (TS) in which an MPEG-2 standard video signal and a Dolby AC-3 standard audio signal are multiplexed. Here, the MPEG-2 TS may include a header of 4 bytes and a payload of 184 bytes.

The interface unit 140 may receive an input signal for power control, channel selection, screen setting, etc. from the external input device 190 or may transmit a signal processed by the controller 160 to the external input device 190. . The interface unit 140 and the external input device 190 may be connected by wire or wirelessly.

As an example of the interface unit 140, a sensor unit may be provided, and the sensor unit is configured to detect the input signal from a remote controller, for example, a remote control.

The network interface unit (not shown) provides an interface for connecting the video display device 100 to a wired/wireless network including an Internet network. The network interface unit may include an Ethernet terminal for connection to a wired network, and for connection to a wireless network, WLAN (Wireless LAN) (Wi-Fi), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access) communication standards, etc. may be used.

The network interface unit (not shown) may access a predetermined web page through a network. That is, by accessing a predetermined web page through a network, the server and data can be transmitted or received. In addition, content or data provided by a content provider or a network operator may be received. That is, content such as movies, advertisements, games, VODs, broadcast signals, and related information provided from a content provider or a network provider may be received through a network. In addition, it is possible to receive update information and an update file of the firmware provided by the network operator. It can also transmit data to the Internet or content provider or network operator.

In addition, the network interface unit (not shown) may select and receive a desired application from among applications open to the public through a network.

The controller 150 may control the overall operation of the image display device 100. More specifically, the controller 150 is formed to control the generation and output of an image. For example, the controller 150 may control the tuner 110 to tune an RF broadcast signal corresponding to a channel selected by the user or a pre-stored channel. Although not shown in the drawings, the control unit 150 may include a demultiplexer, an image processing unit, an audio processing unit, a data processing unit, an On Screen Display (OSD) generation unit, and the like. In addition, the control unit 150 may include a CPU or a peripheral device in hardware.

The controller 150 may demultiplex the stream signal TS, for example, MPEG-2 TS, and divide it into a video signal, an audio signal, and a data signal.

The controller 150 may perform image processing, for example, decoding on the demultiplexed image signal. In more detail, the control unit 150 decodes an MPEG-2 standard coded video signal using an MPEG-2 decoder, and uses an H.264 decoder to convert a digital multimedia broadcasting (DMB) method or DVB-H. It is possible to decode an encoded video signal of the .264 standard. In addition, the controller 150 may process an image so that brightness, tint, and color of an image signal are adjusted. The image signal processed by the control unit 150 may be transmitted to the display unit 170 or may be transmitted to an external output device (not shown) through an external output terminal.

The controller 150 may perform voice processing, for example, decoding on the demultiplexed voice signal. In more detail, the control unit 150 decodes the encoded audio signal of the MPEG-2 standard using an MPEG-2 decoder, and uses the MPEG 4 decoder to comply with the MPEG 4 Bit Sliced Arithmetic Coding (BSAC) standard according to the DMB method. The encoded audio signal may be decoded, and an encoded audio signal of the AAC (Advanced Audio Codec) standard of MPEG 2 according to the satellite DMB method or DVB-H may be decoded using the AAC decoder. In addition, the control unit 150 may process a base, a treble, and a volume control. The audio signal processed by the controller 150 may be transmitted to the audio output unit 180, for example, a speaker, or may be transmitted to an external output device.

The controller 150 may perform signal processing on an analog baseband video/audio signal (CVBS/SIF). Here, the analog baseband video/audio signal CVBS/SIF input to the controller 150 may be an analog baseband video/audio signal output from the tuner 110 or the signal input/output unit 130. The signal-processed video signal is displayed through the display unit 170, and the signal-processed audio signal is output through the audio output unit 180.

The controller 150 may perform data processing, for example, decoding on the demultiplexed data signal. Here, the data signal may include EPG (Electronic Program Guide) information including broadcast information such as a start time and an end time of a broadcast program aired on each channel. The EPG information may include, for example, ATSC-Program and System Information Protocol (TSC-PSIP) information in the ATSC scheme, and DVB-Service Information (DVB-SI) information in the DVB scheme. ATSC-PSIP information or DVB-SI information may be included in the header (4 bytes) of the MPEG-2 TS.

The controller 150 may perform a control operation for OSD processing. In more detail, the controller 150 is an OSD for displaying various types of information in a graphic or text format based on at least one of an image signal and a data signal or an input signal received from the external input device 190. Can generate signals. The OSD signal may include various data such as a user interface screen, a menu screen, a widget, and an icon of the video display device 100.

The storage unit 160 may store a program for signal processing and control of the controller 150, or may store a signal-processed video signal, an audio signal, and a data signal. The storage unit 160 includes a flash memory, a hard disk, a multimedia card micro type, a card type memory (for example, SD or XD memory), and a random access memory. memory; RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk It may include at least one of the storage media.

The display unit 170 may generate a driving signal by converting an image signal, a data signal, an OSD signal, and the like processed by the controller 150 into an RGB signal. Through this, the display unit 170 outputs an image. The display unit 170 includes a plasma display panel (PDP), a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFT-LCD), and an organic light emitting diode (Organic). Light Emitting Diode: OLED), flexible display (flexible display), 3D display (3D display), electronic ink display (e-ink display) can be implemented in various forms. In addition, the display 180 may be implemented as a touch screen to perform a function of an input device.

The audio output unit 180 outputs an audio signal processed by the controller 150, for example, a stereo signal or a 5.1 signal. The audio output unit 180 may be implemented with various types of speakers.

Meanwhile, a photographing unit (not shown) for photographing a user may be further provided. The photographing unit (not shown) may be implemented with one camera, but is not limited thereto, and may be implemented with a plurality of cameras. Image information captured by the photographing unit (not shown) is input to the control unit 150.

Meanwhile, in order to detect a user's gesture, as described above, a sensing unit (not shown) including at least one of a touch sensor, a voice sensor, a position sensor, and a motion sensor may be further provided in the image display device 100. have. The signal detected by the sensing unit (not shown) may be transmitted to the control unit 150 through the user input interface unit 140.

The controller 150 may detect a user's gesture by combining or combining an image captured from a photographing unit (not shown) or a signal detected from a sensing unit (not shown).

A power supply unit (not shown) supplies corresponding power to the entire video display device 100. In particular, power is supplied to the control unit 150 that can be implemented in the form of a System On Chip (SOC), the display unit 170 for displaying an image, and the audio output unit 180 for outputting audio. I can.

To this end, the power supply unit (not shown) may include a converter (not shown) for converting AC power into DC power. Meanwhile, for example, when the display unit 170 is implemented as a liquid crystal panel having a plurality of backlight lamps, an inverter (not shown) capable of PWM operation may be further provided for luminance variable or dimming driving. May be.

The external input device 190 is connected to the interface unit 140 by wire or wirelessly, and transmits an input signal generated according to a user input to the interface unit 140. The external input device 190 may include a remote controller, a mouse, and a keyboard. The remote controller may transmit an input signal to the interface unit 140 through Bluetooth, RF communication, infrared communication, UWB (Ultra Wideband), ZigBee method, or the like. The remote controller can be implemented as a space remote control device. The space remote control device may generate an input signal by detecting the motion of the body in space.

The video display device 100 includes ATSC system (8-VSB system) digital broadcasting, DVB-T system (COFDM system) digital broadcasting, DVB-C system (QAM system) digital broadcasting, DVB-S system (QPSK system) ) Digital broadcasting, ISDB-T method (BST-OFDM method) digital broadcasting, etc. may be implemented as a fixed digital broadcasting receiver capable of receiving at least one of. In addition, the video display device 100 includes terrestrial DMB type digital broadcasting, satellite DMB type digital broadcasting, ATSC-M/H type digital broadcasting, DVB-H type (COFDM type) digital broadcasting, and media forward. It may be implemented as a mobile digital broadcasting receiver capable of receiving at least one of digital broadcasting of the Link Only method. In addition, the video display device 100 may be implemented as a digital broadcasting receiver for cable, satellite communication, and IPTV.

Meanwhile, the video display device of the present invention is configured to provide a stereoscopic image. The term 3-D or 3D is used to describe a visual expression or display technology that attempts to reproduce a stereoscopic image (hereinafter, referred to as '3D image') having an optical illusion of depth. For the left eye image and the right eye image, the viewer's visual cortex interprets the two images as one 3D image.

Three-dimensional (3D) display technology employs a technology of 3D image processing and expression for a device capable of displaying a 3D image. Optionally, a device capable of displaying a 3D image may need to use a special observation device to effectively provide a 3D image to an observer.

Examples of 3D image processing and representation include stereoscopic image/video capture, multi-view image/video capture using multiple cameras, and processing of two-dimensional images and depth information. Examples of display devices capable of displaying 3D images include liquid crystal displays (LCDs), digital TV screens, and computer monitors provided with appropriate hardware and/or software supporting 3D image display technology. Examples of special observation devices include specialized glasses, goggles, headgear, and eyewear.

Specifically, 3D image display technology includes anaglyph stereoscopic images (usually using passive red and red glasses), polarized stereoscopic images (usually used with passive polarized glasses), and alternate-frame sequencing. ) (Usually used with active shutter glasses/headgear), autostereoscopic displays with lenticular or barrier screens.

For 3D image processing, a stereo image or a multi-view image may be compressed and encoded and transmitted by various methods including MPEG (Moving Picture Experts Group). For example, a stereo image or a multiview image may be compressed and encoded using H.264/AVC (Advanced Video Coding) and transmitted. In this case, the receiving system may obtain a 3D image by decoding the received image in the reverse of the H.264/AVC coding scheme. In this case, the receiving system may be provided as a component of a 3D stereoscopic image display device.

Hereinafter, the configuration of the 3D stereoscopic image display apparatus 200 will be described with reference to FIG. 2.

2 is a block diagram illustrating a configuration of a 3D image display device to which an image processing device according to embodiments of the present invention is applied.

As shown in FIG. 2, the 3D image display apparatus 200 according to the embodiments of the present invention includes a tuner 210, a demodulation unit 220, an external device interface unit 230, a network interface unit 235, and A storage unit 240, a user input interface unit 250, a control unit 270, a display unit 280, an audio output unit 285, and a 3D viewing device 295 may be included. Hereinafter, for the same configuration as in FIG. 1, a portion related to the output of a 3D image will be mainly described, and a portion overlapping with the above-described portion will be omitted.

The tuner (tuner unit) 210 receives a broadcast signal, detects a corresponding signal, corrects an error, and generates a transport stream for left-eye and right-eye images.

The demodulator 220 is a first decoder that decodes a reference view video, and may include a second decoder that decodes an extended view video. In this case, by the demultiplexer, the video stream is output to the first decoder if it corresponds to the reference view video, and to the second decoder if it corresponds to the extended view video.

The external device interface unit 230 may transmit or receive data with a connected external device. To this end, the external device interface unit 230 may include an A/V input/output unit (not shown) or a wireless communication unit (not shown).

The external device interface unit 230 may be connected to an external device (not shown) such as a digital versatile disk (DVD), a Blu ray, a game device, a camera, a camcorder, a computer (laptop), etc. by wire/wireless. I can. The external device interface unit 230 transmits a video, audio or data signal input from the outside through a connected external device to the control unit 270 of the image display device 200. In addition, the image, audio, or data signal processed by the controller 270 may be output to a connected external device. To this end, the external device interface unit 230 may include an A/V input/output unit (not shown) or a wireless communication unit (not shown).

The A/V input/output unit is a USB terminal, CVBS (Composite Video Banking Sync) terminal, component terminal, S-video terminal (analog), DVI so that video and audio signals from external devices can be input to the video display device 200. It may include a (Digital Visual Interface) terminal, a High Definition Multimedia Interface (HDMI) terminal, an RGB terminal, and a D-SUB terminal.

The wireless communication unit may perform short-range wireless communication with another electronic device. The image display device 200 communicates with Bluetooth, Radio Frequency Identification (RFID), infrared data association (IrDA), Ultra Wideband (UWB), ZigBee, and Digital Living Network Alliance (DLNA). Depending on the standard, other electronic devices can be connected to the network.

In addition, the external device interface unit 230 may be connected through various set-top boxes and at least one of the aforementioned various terminals to perform input/output operations with the set-top box.

Meanwhile, the external device interface unit 230 may transmit and receive data to and from the 3D viewing device 295.

The network interface unit 235 provides an interface for connecting the image display device 200 to a wired/wireless network including an Internet network. The network interface unit 235 may include an Ethernet terminal or the like for connection to a wired network, and for connection to a wireless network, WLAN (Wireless LAN) (Wi-Fi), Wibro (Wireless broadband), World Interoperability for Microwave Access (Wimax), High Speed Downlink Packet Access (HSDPA) communication standards, etc. may be used.

The network interface unit 235 may receive content or data provided by the Internet or a content provider or a network operator through a network. That is, content such as movies, advertisements, games, VODs, broadcast signals, etc. provided from the Internet and content providers, and related information may be received through the network. In addition, it is possible to receive update information and an update file of the firmware provided by the network operator. It can also transmit data to the Internet or content provider or network operator.

In addition, the network interface unit 235 is connected to an Internet Protocol (IP) TV, for example, to enable two-way communication, by receiving a video, audio, or data signal processed by an IPTV set-top box, and the controller 270 It can be transferred to, and the signals processed by the control unit 270 can be transferred to the IPTV set-top box.

Meanwhile, the above-described IPTV may mean including ADSL-TV, VDSL-TV, FTTH-TV, etc., depending on the type of transmission network, and TV over DSL, Video over DSL, TV overIP (TVIP), and Broadband TV ( BTV) or the like. In addition, IPTV may also mean Internet TV and full browsing TV with Internet access.

The storage unit 240 may store a program for processing and controlling each signal in the control unit 270 or may store a signal-processed image, audio, or data signal.

In addition, the storage unit 240 may perform a function for temporary storage of an image, audio, or data signal input to the external device interface unit 230. In addition, the storage unit 240 may store information on a predetermined broadcast channel through a channel storage function such as a channel map.

The storage unit 240 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg, SD or XD memory, etc.), It may include at least one type of storage medium among RAM and ROM (EEPROM, etc.). The image display device 200 may reproduce and provide a file (movie file, still image file, music file, document file, etc.) stored in the storage unit 240 to a user. 2 shows an embodiment in which the storage unit 240 is provided separately from the control unit 270, but the scope of the present invention is not limited thereto. The storage unit 240 may be included in the control unit 270.

The description of the user input interface unit 250 is replaced with the description of the interface unit 140 described above with reference to FIG. 1.

The control unit 270 demultiplexes the input stream through the tuner 210 or the demodulation unit 220 or the external device interface unit 230 or processes the demultiplexed signals to output a video or audio signal. Can be created and printed.

The image signal processed by the control unit 270 may be input to the display unit 280 and displayed as an image corresponding to the corresponding image signal. In addition, the image signal processed by the controller 270 may be input to an external output device through the external device interface unit 230.

The audio signal processed by the controller 270 may be sound output to the audio output unit 285. In addition, the voice signal processed by the controller 270 may be input to an external output device through the external device interface unit 230.

The control unit 270 may include a demultiplexer, an image processing unit, and the like. The controller 270 may control the overall operation of the image display device 200. For example, the controller 270 may control the tuner 210 to select (Tuning) an RF broadcast corresponding to a channel selected by the user or a pre-stored channel.

In addition, the controller 270 may control the image display apparatus 200 according to a user command or an internal program input through the user input interface unit 250.

For example, the controller 270 controls the tuner 210 to input a signal of a selected channel according to a predetermined channel selection command received through the user input interface unit 250. Then, the video, audio, or data signal of the selected channel is processed. The control unit 270 enables channel information selected by the user to be output through the display unit 280 or the audio output unit 285 together with the processed image or audio signal.

As another example, the control unit 270 may be configured from an external device input through the external device interface unit 230, for example, a camera or camcorder, according to an external device image playback command received through the user input interface unit 250. The video signal or audio signal of can be output through the display unit 280 or the audio output unit 285.

The controller 270 may control the display unit 280 to display an image. For example, a broadcast image input through the tuner 210, an external input image input through the external device interface unit 230, an image input through the network interface unit 235, or an image stored in the storage unit 240 May be controlled to be displayed on the display unit 280. In this case, the image displayed on the display unit 280 may be a still image or a moving image, and may be a 2D image or a 3D image.

The control unit 270 generates and displays a predetermined object as a 3D object among the images displayed on the display unit 280. For example, the object may be at least one of a connected web screen (newspaper, magazine, etc.), EPG (Electronic Program Guide), various menus, widgets, icons, still images, moving pictures, and text. Such a 3D object may be processed to have a depth different from that of an image displayed on the display unit 280. The controller 270 may process the 3D object to protrude compared to the image displayed on the display unit 280.

The control unit 270 recognizes a user's location based on an image captured by a photographing unit (not shown). For example, a distance (z-axis coordinate) between the user and the image display device 200 may be determined. In addition, the x-axis coordinates and the y-axis coordinates in the display unit 280 corresponding to the user's location may be identified.

Meanwhile, although not shown in FIG. 2, a channel browsing processing unit for generating a thumbnail image corresponding to a channel signal or an external input signal may be further provided. The channel browsing processing unit receives the stream signal TS output from the demodulator 220 or the stream signal output from the external device interface unit 230, and extracts an image from the input stream signal to generate a thumbnail image. I can. The generated thumbnail image may be input to the controller 270 as it is or after being encoded. In addition, the generated thumbnail image may be encoded in a stream format and input to the controller 270.

The controller 270 may display a thumbnail list including a plurality of thumbnail images on the display unit 280 by using the input thumbnail images. In this case, the thumbnail list may be displayed in a simple view method displayed in a partial area while a predetermined image is displayed on the display unit 280, or may be displayed in a full view method displayed in most areas of the display unit 280. . The thumbnail images in the thumbnail list may be sequentially updated.

The display unit 280 converts an image signal, a data signal, an OSD signal, a control signal or an image signal, a data signal, and a control signal received from the external device interface unit 230 processed by the control unit 270 to convert a driving signal Create

The display unit 280 may be a PDP, an LCD, an OLED, a flexible display, or the like, and in particular, according to an embodiment of the present invention, a 3D display may be possible.

For viewing a 3D image, the display unit 280 may be divided into an additional display method and an independent display method. The single display method is a display unit 280 (no glasses 3D display) alone, without a separate additional display, for example, without glasses, can implement a 3D image, for example, lenticular method, para Various methods, such as a parallax barrier, can be applied. The additional display method may implement a 3D image by using an additional display in addition to the display unit 280, and various methods such as a head mounted display (HMD) type and a glasses type may be applied.

The glasses type may be further divided into a passive method such as a polarizing glasses type and an active method such as a shutter glass type. Meanwhile, the head mounted display type can also be divided into a passive type and an active type.

The 3D viewing apparatus (glass for 3D) 295 for viewing a stereoscopic image may include a passive polarizing glass or an active shirt glass, and is described as a concept including the aforementioned head mount type.

Meanwhile, the display unit 280 may be configured as a touch screen and used as an input device other than an output device.

The audio output unit 285 receives a signal processed by the control unit 270, for example, a stereo signal, a 3.1 channel signal, or a 5.1 channel signal, and outputs it as audio. The audio output unit 185 may be implemented with various types of speakers.

Meanwhile, in order to detect the user's gesture, as described above, a sensing unit (not shown) including at least one of a touch sensor, a voice sensor, a position sensor, and a motion sensor is further provided in the image display device 200. I can. The signal detected by the sensing unit (not shown) is transmitted to the control unit 170 through the user input interface unit 150.

The controller 270 may detect a user's gesture by combining or combining an image captured from a photographing unit (not shown) or a signal detected from a sensing unit (not shown).

The remote control device 260 transmits a user input to the user input interface unit 250. To this end, the remote control device 260 may use Bluetooth, Radio Frequency (RF) communication, infrared (IR) communication, Ultra Wideband (UWB), ZigBee, or the like. In addition, the remote control device 260 may receive an image, audio, or data signal output from the user input interface unit 250 and display or output an audio signal on the remote control device 260.

The above-described video display device 200 is a fixed type, such as ATSC system (7-VSB system) digital broadcasting, DVB-T system (COFDM system) digital broadcasting, ISDB-T system (BST-OFDM system) digital broadcasting, etc. It may be a digital broadcast receiver capable of receiving at least one of. In addition, as a mobile type, terrestrial DMB method digital broadcasting, satellite DMB method digital broadcasting, ATSC-M/H method digital broadcasting, DVB-H method (COFDM method) digital broadcasting, media flow (Media Forward Link Only) method It may be a digital broadcasting receiver capable of receiving at least one of digital broadcasting and the like. In addition, it may be a digital broadcasting receiver for cable, satellite communication, and IPTV.

The image display device described in this specification may include a TV receiver, a mobile phone, a smart phone, a notebook computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), and the like. have.

The configuration diagram of the image display device 200 shown in FIG. 2 is a configuration diagram for embodiments of the present invention. Each component of the configuration diagram may be integrated, added, or omitted according to the specifications of the image display device 200 that is actually implemented. That is, if necessary, two or more components may be combined into one component, or one component may be subdivided into two or more components. In addition, the functions performed by each block are for explaining the embodiments of the present invention, and specific operations or devices thereof do not limit the scope of the present invention.

The video signal decoded by the video display device 200 may be a 3D video signal of various formats. For example, it may be a 3D image signal composed of a color image and a depth image, or may be a 3D image signal composed of a multi-view image signal. The multi-view image signal may include, for example, a left-eye image signal and a right-eye image signal. Here, the format of the 3D video signal is a side-by-side format in which the left-eye video signal (L) and the right-eye video signal (R) are arranged left and right, and the top-down (Top / Down) format is arranged up and down. Format, Frame Sequential format arranged by time division, Interlaced format that mixes left-eye video signal and right-eye video signal by line, Checker Box that mixes left-eye video signal and right-eye video signal by box It may be a format, etc.

In addition, the video display device described above can also be applied to a mobile terminal. The mobile terminal includes a mobile phone, a smart phone, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation system, a slate PC, and a tablet PC. Tablet PC), ultrabook, etc.

When the video display device is used as a mobile terminal, a wireless communication unit may be added.

The wireless communication unit may include one or more modules that enable wireless communication between the image display device 100 and a wireless communication system or between a mobile terminal and a network in which the mobile terminal is located. For example, the wireless communication unit may include at least one of a broadcast reception module, a mobile communication module, a wireless Internet module, a short-range communication module, and a location information module.

The broadcast receiving module receives a broadcast signal and/or broadcast-related information from an external broadcast management server through a broadcast channel.

The broadcast channel may include a satellite channel and a terrestrial channel. The broadcast management server may mean a server that generates and transmits a broadcast signal and/or broadcast-related information, or a server that receives and transmits a previously-generated broadcast signal and/or broadcast-related information to a terminal. The broadcast signal may include not only a TV broadcast signal, a radio broadcast signal, and a data broadcast signal, but also a broadcast signal in a form in which a data broadcast signal is combined with a TV broadcast signal or a radio broadcast signal.

The broadcast related information may mean information related to a broadcast channel, a broadcast program, or a broadcast service provider. The broadcast-related information may also be provided through a mobile communication network. In this case, it may be received by the mobile communication module 112.

The broadcast-related information may exist in various forms. For example, it may exist in the form of an Electronic Program Guide (EPG) of Digital Multimedia Broadcasting (DMB) or an Electronic Service Guide (ESG) of Digital Video Broadcast-Handheld (DVB-H).

The broadcast receiving module includes, for example, Digital Multimedia Broadcasting-Terrestrial (DMB-T), Digital Multimedia Broadcasting-Satellite (DMB-S), Media Forward Link Only (MediaFLO), and Digital Video Broadcast-Handheld (DVB-H). , ISDB-T (Integrated Services Digital Broadcast-Terrestrial), and other digital broadcasting systems may be used to receive digital broadcasting signals. Of course, the broadcast reception module 111 may be configured to be suitable for not only the digital broadcasting system described above, but also other broadcasting systems.

Broadcast signals and/or broadcast related information received through the broadcast reception module may be stored in a memory.

The mobile communication module transmits and receives a radio signal with at least one of a base station, an external terminal, and a server on a mobile communication network. The wireless signal may include a voice call signal, a video call signal, or various types of data according to transmission/reception of text/multimedia messages.

The mobile communication module is configured to implement a video call mode and a voice call mode. The video call mode refers to a state in which a call is made while viewing the video of the other party, and the voice call mode refers to a state in which a call is made without viewing the image of the other party. In order to implement the video call mode and the voice call mode, the mobile communication module 112 is formed to transmit and receive at least one of audio and video.

The wireless Internet module refers to a module for wireless Internet access, and may be built-in or external to the mobile terminal 100. Wireless Internet technologies include WLAN (Wireless LAN), WiFi (Wireless Fidelity) Direct, DLNA (Digital Living Network Alliance), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access), etc. Can be used.

The short-range communication module refers to a module for short-range communication. Short-range communication technologies include Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi. Direct or the like can be used.

The location information module is a module for acquiring a location of a mobile terminal, and representative examples thereof include a GPS (Global Position System) module or a WiFi (Wireless Fidelity) module.

On the other hand, when the display unit and the sensor for detecting a touch motion (hereinafter referred to as'touch sensor') form a mutual layer structure (hereinafter, referred to as'touch screen'), the display unit 151 inputs input other than the output device. It can also be used as a device. The touch sensor may have, for example, a touch film, a touch sheet, a touch pad, or the like.

The touch sensor may be configured to convert a change in pressure applied to a specific portion of the display unit or a capacitance generated in a specific portion of the display unit into an electrical input signal. The touch sensor may be configured to detect not only a location and an area at which a touch object is touched on the touch sensor, but also a pressure when a touch object is touched. Here, the touch object is an object that applies a touch to the touch sensor, and may be, for example, a finger, a touch pen, a stylus pen, or a pointer.

When there is a touch input to the touch sensor, a signal(s) corresponding thereto is transmitted to the touch controller. The touch controller processes the signal(s) and then transmits the corresponding data to the controller. As a result, the control unit can know whether an area of the display unit 151 has been touched.

The position detection unit 291 detects the user's position through a head tracking technique, and outputs the detected user position to the control unit 270. For example, the position detection unit 291 may detect the user's position by detecting and tracking the user's head from an image captured by the camera 293.

The voice recognition unit 292 recognizes a user voice and outputs the recognized user voice to the control unit 270. The voice recognition unit 292 may include a microphone.

Hereinafter, a voice recognition apparatus capable of accurately recognizing a user voice by changing a threshold value according to a user voice pattern and a method thereof will be described.

3 is a flow chart showing a speech recognition method according to an embodiment of the present invention.

First, the voice recognition unit 292 receives a user voice according to a user's speech (S11).

The speech recognition unit 292 compares the user speech input by the user's utterance with predetermined models that provide confidence scores representing the similarity between the input speech and a plurality of speech models. The user's voice is recognized, and the recognized result is output to the control unit 270 (S12). The recognized user voice includes a confidence score. For example, assuming that the user voice according to the user's utterance is channel up, channel down, volume up, etc., the channel up may have a 6252 reliability score, the channel down may have a 8242 reliability score, and the volume up May have a 2024 confidence score. Here, a method of recognizing a user's voice using the reliability score is also disclosed in US Patent No. 6,735,562.

The controller 270 determines whether the recognized user voice corresponds to a reliability score higher than a threshold value, and if the recognized user voice corresponds to a reliability score higher than a threshold value, the user voice Accpept.

On the other hand, the controller 270 rejects the recognized user voice signal when the recognized user voice corresponds to a reliability score lower than the threshold, and then a preset guide message (for example, talk a little slowly. Please) to re-induce speech recognition. For example, assuming that the threshold value is 6000, the control unit 270 sets "channel up" with the 6252 reliability score and "channel down" with the 8242 reliability score as the user's voice. Recognizes and rejects the "volume up" having the 2024 confidence score without recognizing the user's voice.

The control unit 270 lists user voices corresponding to the threshold value or higher in order of reliability scores. For example, the control unit 270 may order "channel down" having the 8242 reliability score and "channel up" having the 6252 reliability score.

The control unit 270 may change the threshold value according to a user voice usage rate (user voice usage pattern) (S13). The user use voice pattern includes a first user voice usage rate for controlling a channel and volume of the video display device, a second user voice usage rate for executing a web browser through the video display device, and the video display device. At least one or more of a usage rate of a third user's voice for executing an application program and a usage rate of a fourth user's voice for searching a broadcast program of the video display device may be included.

The control unit 270 may increase the probability of user voice recognition by changing the threshold value based on a user voice usage rate (user use voice pattern) classified in advance according to the function of the video display device 200. For example, the controller 270 may include a first user's voice (eg, channel up, channel down, volume down, volume up, etc.) for controlling the channel and volume of the video display device 200, A second user's voice (eg, Internet, web site, etc.) for executing a web browser through the video display device 200, and various application programs (eg, messenger, etc.) through the video display device 200 A third user voice (e.g., messenger, mail, etc.) for executing a mail application program, and a fourth user voice (e.g., drama name, entertainment) for searching a broadcast program of the video display device 200 Program name, etc.). The first to fourth user voices may be predefined or may be received from a server.

4 is an exemplary diagram showing a user use voice pattern according to an embodiment of the present invention.

As shown in FIG. 4, the first user's voice usage rate is 60% (4-1) of the total (100%), and the second user voice usage rate is 10% (4-1) of the total (100%). 2), and the third user voice usage rate is 20% (4-3) out of the total (100%), and the fourth user voice usage rate is 10% (4-4) out of the total (100%). When the first user voice (eg, channel up, channel down, volume down, volume up, etc.) is recognized by the voice recognition unit 292, the control unit 270 sets the threshold at 6000. By increasing it to 6500, the user's voice recognition rate for speech similar in pronunciation (eg, channel up, channel down, volume down, volume up, etc.) is increased. When the fourth user voice (e.g., drama name, entertainment program name, etc.) is recognized by the voice recognition unit 292, the control unit 270 reduces the threshold value from 6000 to 5000, which is not used frequently. Increases the user's voice recognition rate for the non-user voice The first to fourth user voice usage rates may be the average voice usage rates used by users.

Therefore, the control unit 270, when the use rate is high, such as the first user voice (for example, channel up, channel down, volume down, volume up, etc.), a voice having a similar pronunciation (for example, channel up , Channel down, volume down, volume up, etc.), the user's voice for similar pronunciation (e.g., channel up, channel down, volume down, volume up, etc.) by increasing the threshold. Increase recognition rate. When the usage rate is low, such as the fourth user voice (for example, a drama name, an entertainment program name, etc.), the control unit 270 may have a voice (for example, a drama name, an entertainment program name, etc.) Since there is a low possibility that there are many, the user voice recognition rate for the fourth user voice is increased by reducing the threshold. When a plurality of user voices having similar pronunciation are recognized, the controller 270 may increase the probability of recognizing the plurality of user voices having similar pronunciation by increasing the threshold.

The controller 270 calculates the usage rate of each of the various user voices by counting the number of times of use of the various user voices (the number of utterances) whenever various user voices are recognized, and the threshold value according to the calculated user voice usage rates. You can also change

The controller 270 determines whether the recognized user voice corresponds to a reliability score higher than the changed threshold value (S14), and the recognized user voice corresponds to a reliability score higher than a threshold value. If so, the user's voice is allowed (accpept) (S15).

On the other hand, the controller 270 rejects the recognized user voice signal (S16) when the recognized user voice corresponds to a reliability score lower than the changed threshold (S16), and then a preset guidance message (for example, , Please talk a little slowly) to reinduce speech recognition.

Accordingly, the voice recognition apparatus and method thereof according to an embodiment of the present invention have a threshold value according to a user voice pattern (a usage rate of each user voice classified in advance according to functions of an electronic device such as a video display device and a mobile communication terminal). By changing, the user's voice can be accurately recognized.

5 is a flowchart illustrating a speech recognition method according to another embodiment of the present invention.

First, the voice recognition unit 292 receives a user voice according to a user's speech (S21).

The speech recognition unit 292 compares the user speech input by the user's utterance with predetermined models that provide confidence scores representing the similarity between the input speech and a plurality of speech models. The user's voice is recognized, and the recognized result is output to the control unit 270 (S22). The recognized user voice includes a confidence score. For example, assuming that the user voice according to the user's utterance is channel up, channel down, volume up, etc., the channel up may have a 6252 reliability score, the channel down may have a 8242 reliability score, and the volume up May have a 2024 confidence score.

The controller 270 determines whether the recognized user voice corresponds to a reliability score higher than a threshold value, and if the recognized user voice corresponds to a reliability score higher than a threshold value, the user voice Accpept.

On the other hand, the controller 270 rejects the recognized user voice signal when the recognized user voice corresponds to a reliability score lower than the threshold, and then a preset guide message (for example, talk a little slowly. Please) to re-induce speech recognition. For example, assuming that the threshold value is 6000, the control unit 270 sets "channel up" with the 6252 reliability score and "channel down" with the 8242 reliability score as the user's voice. Recognizes and rejects the "volume up" having the 2024 confidence score without recognizing the user's voice.

The control unit 270 lists user voices corresponding to the threshold value or higher in order of reliability scores. For example, the control unit 270 may order "channel down" having the 8242 reliability score and "channel up" having the 6252 reliability score.

The controller 270 may change the threshold value according to a user's usage function pattern (eg, a usage rate of each function of an electronic device such as a video display device and a mobile communication terminal) (S23). The usage function pattern may include a usage rate of a first user usage function for controlling a channel and volume of the video display device, a usage rate of a second user usage function for executing a web browser through the video display device, and the video display device. At least one or more of a use rate of a third user use function for executing an application program through and a use rate of a fourth user use function for searching a broadcast program of the video display device may be included.

The control unit 270 may increase a user voice recognition probability by changing the threshold value based on a user use function pattern categorized according to the function of the video display device 200. For example, the control unit 270 includes a first user use function for controlling the channel and volume of the video display device 200 (e.g., a channel up button, a channel down button, a volume down button, a volume up Buttons, etc.), a second user use function (for example, the Internet, a web site, etc.) for executing a web browser through the video display device 200, and various application programs through the video display device 200 ( For example, a third user use function (for example, a messenger, mail, etc.) for executing a messenger, mail application program, etc., and a fourth user use function for searching a broadcast program of the video display device 200 ( For example, it can be classified as a drama name search, an entertainment program name search, etc.). The first to fourth user use functions may be collected and defined according to each user.

6 is an exemplary diagram showing a user use function pattern according to an embodiment of the present invention.

As shown in Fig. 6, the use rate of the first user function is 60% (6-1) of the total (100%), and the use rate of the second user function is 10% ( 6-2), the use rate of the third user function is 20% (6-3) out of the total (100%), and the use rate of the fourth user function is 10% (6- 4), when the first user use function (for example, a channel up button, a channel down button, a volume down button, a volume up button, etc.) is detected, the threshold is at 6000. By increasing it to 6500, the user's voice recognition rate for speech similar in pronunciation (eg, channel up, channel down, volume down, volume up, etc.) is increased. When the fourth user use function (eg, drama name search, entertainment program name search, etc.) is detected, the control unit 270 reduces the threshold value from 6000 to 5000, Increase speech recognition rate. The usage rate of the first to fourth user-use functions may be a usage rate of an average user function or a usage rate of an average user-use function. The control unit 270 transmits the user use function pattern (the use rate of the first to fourth user use functions) to the server, then receives a threshold value corresponding to the user use function pattern from the server, and receives the received threshold value. You may.

Therefore, the control unit 270, the first user function (e.g., channel up button, channel down button, volume down button, volume up button, etc.) For example, since there is a high possibility that there are a large number of channels up, channel down, volume down, volume up, etc.), by increasing the threshold, speech similar in pronunciation (e.g., channel up, channel down, volume down, volume up, etc.) ) To increase the user's voice recognition rate. When the usage rate is low, such as the fourth user use function (for example, a drama name search, an entertainment program name search, etc.), the control unit 270 may have a voice having a similar pronunciation (for example, a drama name, an entertainment program name, etc.). And the like) is unlikely to exist, thereby increasing the user's voice recognition rate for the fourth user use function by reducing the threshold. When a plurality of user voices having similar pronunciation are recognized, the controller 270 may increase the probability of recognizing the plurality of user voices having similar pronunciation by increasing the threshold.

The controller 270 calculates the usage rate of each of the various user voices by counting the number of times of use of the various user voices (the number of utterances) whenever various user voices are recognized, and the threshold value according to the calculated user voice usage rates. You can also change

The controller 270 determines whether the recognized user voice corresponds to a reliability score higher than the changed threshold value (S14), and the recognized user voice corresponds to a reliability score higher than a threshold value. If so, the user's voice is allowed (accpept) (S15). The controller 270 determines whether the recognized user voice corresponds to a reliability score higher than a threshold value received from the server, and the recognized user voice corresponds to a reliability score higher than the threshold value received from the server. If applicable, the user's voice may be allowed (accpept).

On the other hand, the controller 270 rejects the recognized user voice signal (S16) when the recognized user voice corresponds to a reliability score lower than the changed threshold (S16), and then a preset guidance message (for example, , Please talk a little slowly) to reinduce speech recognition. When the recognized user voice corresponds to a reliability score lower than the threshold value received from the server, the controller 270 rejects the recognized user voice signal, and then a preset guide message (for example, a little Please speak slowly) to re-induce speech recognition.

Accordingly, the voice recognition apparatus and method thereof according to another embodiment of the present invention accurately change the user voice by changing the threshold value according to the user use function pattern (the use rate of each function of an electronic device such as a video display device and a mobile communication terminal). I can recognize it.

As described above, the voice recognition apparatus and method thereof according to embodiments of the present invention include a user voice pattern (a usage rate of each user voice classified in advance according to functions of an electronic device such as a video display device and a mobile communication terminal). ), the user's voice can be accurately recognized by changing the threshold.

The voice recognition apparatus and method according to embodiments of the present invention can accurately recognize a user voice by changing a threshold value according to a user use function pattern (a usage rate of each function of an electronic device such as a video display device and a mobile communication terminal). I can.

Those of ordinary skill in the art to which the present invention pertains will be able to make various modifications and variations without departing from the essential characteristics of the present invention. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain the technical idea, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be interpreted as being included in the scope of the present invention.

270: control unit 292: voice recognition unit

Claims (16)

A speech recognition unit for recognizing a user's speech based on predetermined speech models providing a reliability score;
And a control unit for allowing or rejecting the recognized user voice based on a reliability score and a threshold value of the recognized user voice,
The control unit changes the threshold value according to a user voice usage rate of the recognized user voice,
The user voice usage rate is,
According to the function of the video display device, a first user voice usage rate for controlling the channel and volume of the video display device, a second user voice usage rate for executing a web browser through the video display device, through the video display device It may be classified as at least one of a third user voice usage rate for executing an application program and a fourth user voice usage rate for searching a broadcast program of the video display device,
Whenever the user voice is recognized, it is calculated by counting the number of utterances of the user voice,
Wherein the control unit changes the threshold value according to the first user voice usage rate to the fourth user voice usage rate. The method of claim 1, wherein the control unit,
And increasing or decreasing the threshold according to the user's voice usage rate. The method of claim 2, wherein the control unit,
And allowing the recognized user voice if the reliability score of the recognized user voice is higher than the increased or decreased threshold. The method of claim 2, wherein the control unit,
And rejecting the recognized user voice when the reliability score of the recognized user voice is lower than the increased or decreased threshold. delete delete The method of claim 1, wherein the control unit,
A voice processing apparatus, characterized in that the user voice usage rate is preset. The method of claim 1, wherein the control unit,
A voice processing device, characterized in that receiving the user voice usage rate from a server. The method of claim 1, wherein the user voice usage rate is
A voice processing device, characterized in that it is a usage rate of an average user voice. The method of claim 1, wherein the control unit,
When a plurality of user voices having similar pronunciation are recognized, the threshold value is increased to increase a recognition probability of the plurality of user voices having similar pronunciation. delete delete delete delete delete delete

Images