KR20190099167A - An artificial intelligence apparatus for performing speech recognition and method for the same - Google Patents

Abstract

The present invention provides an artificial intelligence apparatus capable of recognizing voices of various users. The artificial intelligence apparatus comprises: a database storing correction data replacing a predetermined voice command; a microphone receiving a first voice command from a first user; and a processor storing the first voice command in the database, obtaining the correction data replacing the first voice command from the user, and mapping the first voice command and correction data to store the mapped first voice command and correction data in the database if an operation to be performed for the first voice command is not determined.

Description

Artificial intelligence devices that perform speech recognition {AN ARTIFICIAL INTELLIGENCE APPARATUS FOR PERFORMING SPEECH RECOGNITION AND METHOD FOR THE SAME}

The present invention relates to an artificial intelligence device capable of performing speech recognition by obtaining correction data that replaces a voice command.

The competition for voice recognition technology started in smartphones is expected to ignite in the house, in line with the proliferation of the Internet of Things (IoT).

In particular, it is noteworthy that the device is an artificial intelligence (AI) device that can command and communicate via voice.

The voice recognition service utilizes a huge database to select an optimal answer to a user's question.

The voice search function also converts the input voice data into text in the cloud server, analyzes it, and sends the real-time search results according to the results back to the device.

The cloud server has the computing power to store numerous words and process them in real time by dividing a large number of words into voice data divided by gender, age, and intonation.

However, there is a problem that it is difficult to process speech recognition with respect to a voice spoken by a young child who has not yet learned language, a person with a strong dialect, or a person who has a bad pronunciation.

In addition, there are many difficulties in generating and applying learning data suitable for the characteristics of all speakers.

Accordingly, there is an increasing need for artificial intelligence devices capable of recognizing the voices of various users.

It is an object of the present invention to solve the above and other problems.

An object of the present invention is to provide an artificial intelligence device capable of recognizing voices of various users by an artificial intelligence device providing a speech recognition based service.

An object of the present invention is to provide an artificial intelligence device capable of acquiring and learning correction data for a voice command that is difficult to perform speech recognition, and performing speech recognition.

According to an embodiment of the present invention, when a database storing correction data replacing a predetermined voice command, a microphone receiving a first voice command from a first user, and an operation to be performed on the first voice command are not determined, And a processor for storing the first voice command in a database, obtaining correction data for replacing the first voice command from a second user, and mapping and storing the first voice command and correction data in the database. do.

According to an embodiment of the present invention, when a voice command having a similar pattern to the first voice command is retrieved from the database, and a voice command having a similar pattern to the first voice command is not retrieved, the first voice command is transmitted to the database. It provides an artificial intelligence device comprising a processor for storing.

According to an embodiment of the present invention, when the second voice command is obtained from the second user and the second user is determined to be a user who has a right to calibrate based on the second voice command, the second voice command is assigned to the first voice. An artificial intelligence device comprising a processor that obtains with correction data to replace instructions.

In addition, according to an embodiment of the present invention, when the second voice command is obtained from the second user and an operation to be performed on the second voice command is determined, the correction data is substituted for the first voice command. Provides an artificial intelligence device comprising a processor to obtain.

In addition, an embodiment of the present invention includes a processor that acquires text data from a second user and obtains the text data as correction data to replace the first voice command when it is determined that an operation to be performed on the text data is determined. To provide artificial intelligence devices.

In addition, an embodiment of the present invention obtains correction data for correcting previously stored correction data replacing a first voice command from a second user, and obtaining correction data as correction data for replacing the first voice command. An artificial intelligence device including a processor is provided.

In addition, an embodiment of the present invention obtains correction data replacing the third voice command from the microphone and the database receiving the third voice command from the first user, and performs the correction data replacing the third voice command. The present invention provides an artificial intelligence device including a processor configured to determine an operation to perform speech recognition.

According to an embodiment of the present invention, a voice command having a similar pattern to a third voice command is searched from a database, and correction data for replacing a voice command having a found similar pattern is used as correction data for replacing the third voice command. It provides an artificial intelligence device including a processor to obtain.

In addition, an embodiment of the present invention is artificial, including a communication unit for transmitting the correction data to replace the third voice command to the NLP server performing the intention analysis and a processor for performing the speech recognition by obtaining the intention analysis information from the NLP server Provide intelligent devices.

Also, an embodiment of the present disclosure may include receiving a first voice command from a first user, storing the first voice command in a database if the operation to be performed on the first voice command is not determined. A method of recognizing a speech may be provided, comprising: acquiring correction data replacing a first voice command from a user, and storing the first voice command and the acquired correction data in a database.

Also, an embodiment of the present invention provides a method of retrieving a voice command having a similar pattern to a first voice command from a database, and if a voice command having a similar pattern to the first voice command is not retrieved, the first voice command is stored in a database. It provides a speech recognition method comprising the step of storing in.

According to an embodiment of the present disclosure, when the second voice command is determined as a user having a right to calibrate based on the second voice command, the second voice command may be acquired by the first voice command. It provides a speech recognition method comprising the step of obtaining with correction data to replace the voice command.

In addition, an embodiment of the present invention is to correct the second voice command to replace the first voice command when the step of obtaining the second voice command from the second user and the operation to be performed for the second voice command is determined. It provides a speech recognition method comprising the step of acquiring with data.

According to an embodiment of the present disclosure, when the text data is obtained from the second user and the operation to be performed on the text data is determined, the text data may be obtained as correction data replacing the first voice command. It provides a voice recognition method comprising.

In addition, an embodiment of the present invention is to obtain the correction data for correcting the previously stored correction data to replace the first voice command from the second user and to obtain the correction data for correction as the correction data to replace the first voice command It provides a speech recognition method comprising the step of.

In addition, an embodiment of the present invention comprises the steps of receiving a third voice command from the first user, obtaining a correction data to replace the third voice command from the database; It provides a speech recognition method comprising the step of performing the speech recognition by determining the operation to be performed on the correction data to replace the third speech command.

Also, an embodiment of the present invention provides a method of retrieving a voice command having a similar pattern to a third voice command from a database, and correcting data to replace a voice command having a retrieved similar pattern. It provides a speech recognition method comprising the step of obtaining.

In addition, an embodiment of the present invention includes the steps of transmitting correction data replacing the third voice command to the NLP server performing the intention analysis, and obtaining the intention analysis information from the NLP server to perform the speech recognition Provide a recognition method.

In addition, an embodiment of the present invention, a database for storing correction data to replace a predetermined voice command, An artificial intelligence device including a microphone receiving a voice command from a user, a processor configured to obtain correction data to replace the voice command from a database, and to perform voice recognition by determining an operation to be performed on the correction data to replace the voice command To provide.

According to an embodiment of the present invention, a speech recognition rate of a young child, a person with a bad dialect or a user who has a bad pronunciation can be increased.

In addition, according to an embodiment of the present invention, it is possible to generate and apply voice learning data suitable for the characteristics of all speakers.

In addition, according to an embodiment of the present invention, it is possible to perform a voice correction learning by a third party to provide an optimized speech recognition performance to a specific user.

1 illustrates an AI device 100 according to an embodiment of the present invention.
2 illustrates an AI server 200 according to an embodiment of the present invention.
3 shows an AI system 1 according to an embodiment of the present invention.
4 is a diagram illustrating a voice system according to an exemplary embodiment.
FIG. 5 is a diagram for describing a method of collecting training data optimized for user characteristics by storing correction data for a voice command according to an exemplary embodiment.
6 is a flowchart illustrating a method of storing correction data for a voice command according to an embodiment of the present invention.
7 is a flowchart illustrating a method of performing speech recognition using correction data for a voice command according to an embodiment of the present invention.
8 through 10 are diagrams for explaining a process of collecting, by an artificial intelligence device, correction data for a voice command and performing voice recognition using the correction data.
FIG. 11 is a diagram for describing a process of adding or editing correction data for a voice command stored in an artificial intelligence device according to an embodiment of the present invention.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings, and the same or similar components are denoted by the same reference numerals regardless of the reference numerals, and redundant description thereof will be omitted. The suffixes "module" and "unit" for components used in the following description are given or used in consideration of ease of specification, and do not have distinct meanings or roles from each other. In addition, in describing the embodiments disclosed herein, when it is determined that the detailed description of the related known technology may obscure the gist of the embodiments disclosed herein, the detailed description thereof will be omitted. In addition, the accompanying drawings are intended to facilitate understanding of the embodiments disclosed herein, but are not limited to the technical spirit disclosed herein by the accompanying drawings, all changes included in the spirit and scope of the present invention. It should be understood to include equivalents and substitutes.

Terms including ordinal numbers such as first and second may be used to describe various components, but the components are not limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

When a component is referred to as being "connected" or "connected" to another component, it may be directly connected to or connected to that other component, but it may be understood that other components may be present in between. Should be. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it should be understood that there is no other component in between.

Artificial Intelligence (AI)

Artificial intelligence refers to the field of researching artificial intelligence or the methodology that can produce it, and machine learning refers to the field of researching methodologies that define and solve various problems in the field of artificial intelligence. do. Machine learning is defined as an algorithm that improves the performance of a task through a consistent experience with a task.

Artificial Neural Network (ANN) is a model used in machine learning, and may refer to an overall problem-solving model composed of artificial neurons (nodes) formed by a combination of synapses. The artificial neural network may be defined by a connection pattern between neurons of different layers, a learning process of updating model parameters, and an activation function generating an output value.

The artificial neural network may include an input layer, an output layer, and optionally one or more hidden layers. Each layer includes one or more neurons, and the artificial neural network may include synapses that connect neurons to neurons. In an artificial neural network, each neuron may output a function value of an active function for input signals, weights, and deflections input through a synapse.

The model parameter refers to a parameter determined through learning and includes weights of synaptic connections and deflection of neurons. In addition, the hyperparameter means a parameter to be set before learning in the machine learning algorithm, and includes a learning rate, the number of iterations, a mini batch size, and an initialization function.

The purpose of learning artificial neural networks can be seen as determining model parameters that minimize the loss function. The loss function can be used as an index for determining optimal model parameters in the learning process of artificial neural networks.

Machine learning can be categorized into supervised learning, unsupervised learning, and reinforcement learning.

Supervised learning refers to a method of learning artificial neural networks with a given label for training data, and a label indicates a correct answer (or result value) that the artificial neural network should infer when the training data is input to the artificial neural network. Can mean. Unsupervised learning may refer to a method of training artificial neural networks in a state where a label for training data is not given. Reinforcement learning can mean a learning method that allows an agent defined in an environment to learn to choose an action or sequence of actions that maximizes cumulative reward in each state.

Machine learning, which is implemented as a deep neural network (DNN) including a plurality of hidden layers among artificial neural networks, is called deep learning (Deep Learning), which is part of machine learning. In the following, machine learning is used to mean deep learning.

<Robot>

A robot can mean a machine that automatically handles or operates a given task by its own ability. In particular, a robot having a function of recognizing the environment, judging itself, and performing an operation may be referred to as an intelligent robot.

Robots can be classified into industrial, medical, household, military, etc. according to the purpose or field of use.

The robot may include a driving unit including an actuator or a motor to perform various physical operations such as moving a robot joint. In addition, the movable robot includes a wheel, a brake, a propeller, and the like in the driving unit, and can travel on the ground or fly in the air through the driving unit.

<Self-Driving>

Autonomous driving means a technology that drives by itself, and autonomous vehicle means a vehicle that runs without a user's manipulation or with minimal manipulation of a user.

For example, for autonomous driving, the technology of maintaining a driving lane, the technology of automatically adjusting speed such as adaptive cruise control, the technology of automatically driving along a predetermined route, the technology of automatically setting a route when a destination is set, etc. All of these may be included.

The vehicle includes a vehicle having only an internal combustion engine, a hybrid vehicle having an internal combustion engine and an electric motor together, and an electric vehicle having only an electric motor, and may include not only automobiles but also trains and motorcycles.

In this case, the autonomous vehicle may be viewed as a robot having an autonomous driving function.

EXtended Reality (XR)

Extended reality collectively refers to Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR). VR technology provides real world objects or backgrounds only in CG images, AR technology provides virtual CG images on real objects images, and MR technology mixes and combines virtual objects in the real world. Graphic technology.

MR technology is similar to AR technology in that it shows both real and virtual objects. However, in AR technology, the virtual object is used as a complementary form to the real object, whereas in the MR technology, the virtual object and the real object are used in the same nature.

XR technology can be applied to HMD (Head-Mount Display), HUD (Head-Up Display), mobile phone, tablet PC, laptop, desktop, TV, digital signage, etc. It can be called.

1 illustrates an AI device 100 according to an embodiment of the present invention.

The AI device 100 is a TV, a projector, a mobile phone, a smartphone, a desktop computer, a notebook, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation device, a tablet PC, a wearable device, and a set-top box (STB). ), A DMB receiver, a radio, a washing machine, a refrigerator, a desktop computer, a digital signage, a robot, a vehicle, or the like.

Referring to FIG. 1, the terminal 100 includes a communication unit 110, an input unit 120, a running processor 130, a sensing unit 140, an output unit 150, a memory 170, a processor 180, and the like. It may include.

The communicator 110 may transmit / receive data to / from external devices such as the other AI devices 100a to 100e or the AI server 200 using wired or wireless communication technology. For example, the communicator 110 may transmit / receive sensor information, a user input, a learning model, a control signal, and the like with external devices.

In this case, the communication technology used by the communication unit 110 includes Global System for Mobile communication (GSM), Code Division Multi Access (CDMA), Long Term Evolution (LTE), 5G, Wireless LAN (WLAN), and Wireless-Fidelity (Wi-Fi). ), Bluetooth ™, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), ZigBee, and Near Field Communication (NFC).

The input unit 120 may acquire various types of data.

In this case, the input unit 120 may include a camera for inputting an image signal, a microphone for receiving an audio signal, a user input unit for receiving information from a user, and the like. Here, the signal obtained from the camera or microphone may be referred to as sensing data or sensor information by treating the camera or microphone as a sensor.

The input unit 120 may acquire input data to be used when acquiring an output using training data and a training model for model training. The input unit 120 may obtain raw input data, and in this case, the processor 180 or the running processor 130 may extract input feature points as preprocessing on the input data.

The running processor 130 may train a model composed of artificial neural networks using the training data. Here, the learned artificial neural network may be referred to as a learning model. The learning model may be used to infer result values for new input data other than the training data, and the inferred values may be used as a basis for judgment to perform an operation.

In this case, the running processor 130 may perform AI processing together with the running processor 240 of the AI server 200.

In this case, the running processor 130 may include a memory integrated with or implemented in the AI device 100. Alternatively, the running processor 130 may be implemented using a memory 170, an external memory directly coupled to the AI device 100, or a memory held in the external device.

The sensing unit 140 may acquire at least one of internal information of the AI device 100, surrounding environment information of the AI device 100, and user information using various sensors.

In this case, the sensors included in the sensing unit 140 include a proximity sensor, an illumination sensor, an acceleration sensor, a magnetic sensor, a gyro sensor, an inertial sensor, an RGB sensor, an IR sensor, a fingerprint sensor, an ultrasonic sensor, an optical sensor, a microphone, and a li. , Radar, etc.

The output unit 150 may generate an output related to sight, hearing, or touch.

In this case, the output unit 150 may include a display unit for outputting visual information, a speaker for outputting auditory information, and a haptic module for outputting tactile information.

The memory 170 may store data supporting various functions of the AI device 100. For example, the memory 170 may store input data, training data, training model, training history, and the like acquired by the input unit 120.

The processor 180 may determine at least one executable operation of the AI device 100 based on the information determined or generated using the data analysis algorithm or the machine learning algorithm. In addition, the processor 180 may control the components of the AI device 100 to perform the determined operation.

To this end, the processor 180 may request, search, receive, or utilize data of the running processor 130 or the memory 170, and may perform an operation predicted or determined to be preferable among the at least one executable operation. The components of the AI device 100 may be controlled to execute.

In this case, when the external device needs to be linked to perform the determined operation, the processor 180 may generate a control signal for controlling the corresponding external device and transmit the generated control signal to the corresponding external device.

The processor 180 may obtain intention information about the user input, and determine the user's requirements based on the obtained intention information.

In this case, the processor 180 uses at least one of a speech to text (STT) engine for converting a voice input into a string or a natural language processing (NLP) engine for obtaining intention information of a natural language. Intent information corresponding to the input can be obtained.

In this case, at least one or more of the STT engine or the NLP engine may be configured as an artificial neural network, at least partly learned according to a machine learning algorithm. At least one of the STT engine or the NLP engine may be learned by the running processor 130, may be learned by the running processor 240 of the AI server 200, or may be learned by distributed processing thereof. It may be.

The processor 180 collects history information including operation contents of the AI device 100 or feedback of a user about the operation, and stores the information in the memory 170 or the running processor 130, or the AI server 200. Can transmit to external device. The collected historical information can be used to update the learning model.

The processor 180 may control at least some of the components of the AI device 100 to drive an application program stored in the memory 170. In addition, the processor 180 may operate two or more of the components included in the AI device 100 in combination with each other to drive the application program.

2 illustrates an AI server 200 according to an embodiment of the present invention.

Referring to FIG. 2, the AI server 200 may refer to an apparatus for learning an artificial neural network using a machine learning algorithm or using an learned artificial neural network. Here, the AI server 200 may be composed of a plurality of servers to perform distributed processing, or may be defined as a 5G network. In this case, the AI server 200 may be included as a part of the AI device 100 to perform at least some of the AI processing together.

The AI server 200 may include a communication unit 210, a memory 230, a running processor 240, a processor 260, and the like.

The communication unit 210 may transmit / receive data with an external device such as the AI device 100.

The memory 230 may include a model storage unit 231. The model storage unit 231 may store a model being trained or learned (or an artificial neural network 231a) through the running processor 240.

The running processor 240 may train the artificial neural network 231a using the training data. The learning model may be used while mounted in the AI server 200 of the artificial neural network, or may be mounted and used in an external device such as the AI device 100.

The learning model can be implemented in hardware, software or a combination of hardware and software. When some or all of the learning model is implemented in software, one or more instructions constituting the learning model may be stored in the memory 230.

The processor 260 may infer a result value with respect to the new input data using the learning model, and generate a response or control command based on the inferred result value.

3 shows an AI system 1 according to an embodiment of the present invention.

Referring to FIG. 3, the AI system 1 may include at least one of an AI server 200, a robot 100a, an autonomous vehicle 100b, an XR device 100c, a smartphone 100d, or a home appliance 100e. This cloud network 10 is connected. Here, the robot 100a to which the AI technology is applied, the autonomous vehicle 100b, the XR device 100c, the smartphone 100d or the home appliance 100e may be referred to as the AI devices 100a to 100e.

The cloud network 10 may refer to a network that forms part of or exists within a cloud computing infrastructure. Here, the cloud network 10 may be configured using a 3G network, 4G or Long Term Evolution (LTE) network or a 5G network.

That is, the devices 100a to 100e and 200 constituting the AI system 1 may be connected to each other through the cloud network 10. In particular, although the devices 100a to 100e and 200 may communicate with each other through the base station, they may also communicate with each other directly without passing through the base station.

The AI server 200 may include a server that performs AI processing and a server that performs operations on big data.

The AI server 200 includes at least one or more of the AI devices constituting the AI system 1, such as a robot 100a, an autonomous vehicle 100b, an XR device 100c, a smartphone 100d, or a home appliance 100e. Connected via the cloud network 10, the AI processing of the connected AI devices 100a to 100e may help at least a part.

In this case, the AI server 200 may train the artificial neural network according to the machine learning algorithm on behalf of the AI devices 100a to 100e and directly store the learning model or transmit the training model to the AI devices 100a to 100e.

At this time, the AI server 200 receives the input data from the AI device (100a to 100e), infers the result value with respect to the input data received using the training model, and generates a response or control command based on the inferred result value Can be generated and transmitted to the AI device (100a to 100e).

Alternatively, the AI devices 100a to 100e may infer a result value from input data using a direct learning model and generate a response or control command based on the inferred result value.

Hereinafter, various embodiments of the AI devices 100a to 100e to which the above-described technology is applied will be described. Here, the AI devices 100a to 100e illustrated in FIG. 3 may be viewed as specific embodiments of the AI device 100 illustrated in FIG. 1.

<AI + robot>

The robot 100a may be applied to an AI technology, and may be implemented as a guide robot, a transport robot, a cleaning robot, a wearable robot, an entertainment robot, a pet robot, an unmanned flying robot, or the like.

The robot 100a may include a robot control module for controlling an operation, and the robot control module may refer to a software module or a chip implemented in hardware.

The robot 100a acquires state information of the robot 100a by using sensor information obtained from various kinds of sensors, detects (recognizes) the surrounding environment and an object, generates map data, or moves a route and travels. You can decide on a plan, determine a response to a user interaction, or determine an action.

Here, the robot 100a may use sensor information acquired from at least one sensor among a rider, a radar, and a camera to determine a movement route and a travel plan.

The robot 100a may perform the above-described operations by using a learning model composed of at least one artificial neural network. For example, the robot 100a may recognize a surrounding environment and an object using a learning model, and determine an operation using the recognized surrounding environment information or object information. Here, the learning model may be directly learned by the robot 100a or may be learned by an external device such as the AI server 200.

In this case, the robot 100a may perform an operation by generating a result using a direct learning model, but transmits sensor information to an external device such as the AI server 200 and receives the result generated accordingly to perform an operation. You may.

The robot 100a determines a moving route and a traveling plan by using at least one of map data, object information detected from sensor information, or object information obtained from an external device, and controls the driving unit to determine the moving route and the traveling plan. Accordingly, the robot 100a may be driven.

The map data may include object identification information about various objects arranged in a space in which the robot 100a moves. For example, the map data may include object identification information about fixed objects such as walls and doors and movable objects such as flower pots and desks. The object identification information may include a name, type, distance, location, and the like.

In addition, the robot 100a may control the driving unit based on the control / interaction of the user, thereby performing an operation or driving. In this case, the robot 100a may acquire the intention information of the interaction according to the user's motion or speech, and determine a response based on the acquired intention information to perform the operation.

<AI + autonomous driving>

The autonomous vehicle 100b may be implemented by an AI technology and implemented as a mobile robot, a vehicle, an unmanned aerial vehicle, or the like.

The autonomous vehicle 100b may include an autonomous driving control module for controlling the autonomous driving function, and the autonomous driving control module may refer to a software module or a chip implemented in hardware. The autonomous driving control module may be included inside as a configuration of the autonomous driving vehicle 100b, but may be connected to the outside of the autonomous driving vehicle 100b as a separate hardware.

The autonomous vehicle 100b obtains state information of the autonomous vehicle 100b by using sensor information obtained from various types of sensors, detects (recognizes) the surrounding environment and an object, generates map data, A travel route and a travel plan can be determined, or an action can be determined.

Here, the autonomous vehicle 100b may use sensor information acquired from at least one sensor among a lidar, a radar, and a camera, similarly to the robot 100a, to determine a movement route and a travel plan.

In particular, the autonomous vehicle 100b may receive or recognize sensor information from external devices or receive information directly recognized from external devices. .

The autonomous vehicle 100b may perform the above operations by using a learning model composed of at least one artificial neural network. For example, the autonomous vehicle 100b may recognize a surrounding environment and an object using a learning model, and determine a driving line using the recognized surrounding environment information or object information. Here, the learning model may be learned directly from the autonomous vehicle 100b or may be learned from an external device such as the AI server 200.

In this case, the autonomous vehicle 100b may perform an operation by generating a result using a direct learning model, but transmits sensor information to an external device such as the AI server 200 and receives the result generated accordingly. You can also do

The autonomous vehicle 100b determines a moving route and a driving plan by using at least one of map data, object information detected from sensor information, or object information obtained from an external device, and controls the driving unit to determine the moving route and the driving plan. According to the plan, the autonomous vehicle 100b can be driven.

The map data may include object identification information for various objects arranged in a space (eg, a road) on which the autonomous vehicle 100b travels. For example, the map data may include object identification information about fixed objects such as street lights, rocks, buildings, and movable objects such as vehicles and pedestrians. The object identification information may include a name, type, distance, location, and the like.

In addition, the autonomous vehicle 100b may perform an operation or drive by controlling the driving unit based on the user's control / interaction. In this case, the autonomous vehicle 100b may acquire the intention information of the interaction according to the user's motion or voice utterance and determine the response based on the obtained intention information to perform the operation.

<AI + XR>

The XR device 100c is applied with AI technology, and includes a head-mount display (HMD), a head-up display (HUD) installed in a vehicle, a television, a mobile phone, a smartphone, a computer, a wearable device, a home appliance, and a digital signage. It may be implemented as a vehicle, a fixed robot or a mobile robot.

The XR apparatus 100c analyzes three-dimensional point cloud data or image data acquired through various sensors or from an external device to generate location data and attribute data for three-dimensional points, thereby providing information on the surrounding space or reality object. It can obtain and render XR object to output. For example, the XR apparatus 100c may output an XR object including additional information about the recognized object in correspondence with the recognized object.

The XR apparatus 100c may perform the above-described operations using a learning model composed of at least one artificial neural network. For example, the XR apparatus 100c may recognize a reality object in 3D point cloud data or image data using a learning model, and may provide information corresponding to the recognized reality object. Here, the learning model may be learned directly from the XR device 100c or learned from an external device such as the AI server 200.

In this case, the XR device 100c may perform an operation by generating a result using a direct learning model, but transmits sensor information to an external device such as the AI server 200 and receives the result generated accordingly. It can also be done.

<AI + Robot + Autonomous Driving>

The robot 100a may be applied to an AI technology and an autonomous driving technology, and may be implemented as a guide robot, a transport robot, a cleaning robot, a wearable robot, an entertainment robot, a pet robot, an unmanned flying robot, or the like.

The robot 100a to which the AI technology and the autonomous driving technology are applied may mean a robot itself having an autonomous driving function or a robot 100a interacting with the autonomous vehicle 100b.

The robot 100a having an autonomous driving function may collectively move devices by moving according to a given copper wire or determine the copper wire by itself without the user's control.

The robot 100a and the autonomous vehicle 100b having the autonomous driving function may use a common sensing method to determine one or more of a moving route or a driving plan. For example, the robot 100a and the autonomous vehicle 100b having the autonomous driving function may determine one or more of the movement route or the driving plan by using information sensed through the lidar, the radar, and the camera.

The robot 100a, which interacts with the autonomous vehicle 100b, is present separately from the autonomous vehicle 100b, and is linked to the autonomous driving function inside the autonomous vehicle 100b or is connected to the autonomous vehicle 100b. The operation associated with the boarding user may be performed.

At this time, the robot 100a interacting with the autonomous vehicle 100b acquires sensor information on behalf of the autonomous vehicle 100b and provides the sensor information to the autonomous vehicle 100b or obtains sensor information and displays the surrounding environment information or By generating object information and providing the object information to the autonomous vehicle 100b, the autonomous vehicle function of the autonomous vehicle 100b can be controlled or assisted.

Alternatively, the robot 100a interacting with the autonomous vehicle 100b may monitor a user in the autonomous vehicle 100b or control a function of the autonomous vehicle 100b through interaction with the user. . For example, when it is determined that the driver is in a drowsy state, the robot 100a may activate the autonomous driving function of the autonomous vehicle 100b or assist control of the driver of the autonomous vehicle 100b. Here, the function of the autonomous vehicle 100b controlled by the robot 100a may include not only an autonomous vehicle function but also a function provided by a navigation system or an audio system provided inside the autonomous vehicle 100b.

Alternatively, the robot 100a interacting with the autonomous vehicle 100b may provide information or assist a function to the autonomous vehicle 100b outside the autonomous vehicle 100b. For example, the robot 100a may provide traffic information including signal information to the autonomous vehicle 100b, such as a smart signal light, or may interact with the autonomous vehicle 100b, such as an automatic electric charger of an electric vehicle. You can also automatically connect an electric charger to the charging port.

<AI + robot + XR>

The robot 100a may be implemented with an AI technology and an XR technology, and may be implemented as a guide robot, a transport robot, a cleaning robot, a wearable robot, an entertainment robot, a pet robot, an unmanned flying robot, a drone, or the like.

The robot 100a to which the XR technology is applied may mean a robot that is the object of control / interaction in the XR image. In this case, the robot 100a may be distinguished from the XR apparatus 100c and interlocked with each other.

When the robot 100a that is the object of control / interaction in the XR image acquires sensor information from sensors including a camera, the robot 100a or the XR apparatus 100c generates an XR image based on the sensor information. In addition, the XR apparatus 100c may output the generated XR image. The robot 100a may operate based on a control signal input through the XR apparatus 100c or user interaction.

For example, the user may check an XR image corresponding to the viewpoint of the robot 100a that is remotely linked through an external device such as the XR device 100c, and may adjust the autonomous driving path of the robot 100a through interaction. You can control the movement or driving, or check the information of the surrounding objects.

<AI + Autonomous driving + XR>

The autonomous vehicle 100b may be implemented by an AI technology and an XR technology, such as a mobile robot, a vehicle, an unmanned aerial vehicle, and the like.

The autonomous vehicle 100b to which the XR technology is applied may mean an autonomous vehicle provided with means for providing an XR image, or an autonomous vehicle that is the object of control / interaction in the XR image. In particular, the autonomous vehicle 100b, which is the object of control / interaction in the XR image, is distinguished from the XR apparatus 100c and may be linked with each other.

The autonomous vehicle 100b having means for providing an XR image may acquire sensor information from sensors including a camera and output an XR image generated based on the acquired sensor information. For example, the autonomous vehicle 100b may provide an XR object corresponding to a real object or an object on the screen by providing an HR to output an XR image.

In this case, when the XR object is output to the HUD, at least a part of the XR object may be output to overlap the actual object to which the occupant's eyes are directed. On the other hand, when the XR object is output on the display provided inside the autonomous vehicle 100b, at least a part of the XR object may be output to overlap the object in the screen. For example, the autonomous vehicle 100b may output XR objects corresponding to objects such as a road, another vehicle, a traffic light, a traffic sign, a motorcycle, a pedestrian, a building, and the like.

When the autonomous vehicle 100b that is the object of control / interaction in the XR image acquires sensor information from sensors including a camera, the autonomous vehicle 100b or the XR apparatus 100c may be based on the sensor information. The XR image may be generated, and the XR apparatus 100c may output the generated XR image. In addition, the autonomous vehicle 100b may operate based on a user's interaction or a control signal input through an external device such as the XR apparatus 100c.

4 is a diagram illustrating a voice system according to an exemplary embodiment.

Referring to FIG. 4, the speech system 40 includes an artificial intelligence device 100, a speech to text (STT) server 41, a natural language processing (NLP) server 42, and speech synthesis. Server 43 may be included.

The artificial intelligence device 100 may transmit voice data to the STT server 41.

The STT server 40 may convert the voice data received from the artificial intelligence device 100 into text data.

The STT server 41 may increase the accuracy of the speech-to-text conversion using the language model.

The language model may mean a model that calculates a probability of a sentence or calculates a probability of a next word given a previous word.

For example, the language model may include probabilistic language models such as a unigram model, a bigram model, an N-gram model, and the like.

The unigram model assumes that all words are completely independent of each other. The unigram model calculates the probability of a word sequence as the product of the probability of each word.

The bigram model is a model that assumes that the utilization of a word depends only on the previous one word.

The N-gram model is a model that assumes that the utilization of words depends on the previous (n-1) words.

That is, the STT server 41 may determine whether the text data converted from the voice data is appropriately converted by using the language model, thereby increasing the accuracy of the conversion into text data.

The NLP server 42 may receive text data from the STT server 41. The NLP server 42 may perform intention analysis on the text data based on the received text data.

The NLP server 42 may transmit intention analysis information indicating the result of performing the intention analysis to the artificial intelligence device 100.

The NLP server 42 may sequentially perform the morphological analysis step, the syntax analysis step, the speech act analysis step, and the conversation processing step on the text data to generate intention analysis information.

The morpheme analysis step is to classify text data corresponding to a voice spoken by a user into morpheme units, which are smallest units having meanings, and determine which parts of speech each classified morpheme has.

The parsing step is to classify text data into noun phrases, verb phrases, adjective phrases, etc., using the results of the morpheme analysis step, and determine what kind of relationship exists between the separated phrases.

Through the parsing step, the subject, object, and modifier of the voice spoken by the user may be determined.

The speech act analysis step is a step of analyzing the intention of the voice spoken by the user using the result of the syntax analysis step. Specifically, the act of speech analysis is a step of determining the intention of the sentence, such as whether the user asks a question, makes a request, or expresses a simple emotion.

The conversation processing step is a step of determining whether to answer the user's speech, to respond to the question, or to ask additional information by using the result of the speech act analysis step.

After the conversation processing step, the NLP server 42 may generate intention analysis information including one or more of a response to the intention spoken by the user, a response, and a query for additional information.

Meanwhile, the NLP server 42 may receive text data from the artificial intelligence device 100. For example, when the artificial intelligence device 100 supports the voice text conversion function, the artificial intelligence device 100 may convert the voice data into text data and transmit the converted text data to the NLP server 42. .

The speech synthesis server 43 may combine the pre-stored speech data to generate the synthesized speech.

The speech synthesis server 43 may record the voice of one person selected as a model and divide the recorded speech into syllables or words. The speech synthesis server 43 may store the divided speech in an internal or external database on a syllable or word basis.

The speech synthesis server 43 may search for a syllable or word corresponding to the given text data from the database, synthesize a combination of the found syllables or words, and generate a synthesized speech.

The speech synthesis server 43 may store a plurality of speech language groups corresponding to each of the plurality of languages.

For example, the speech synthesis server 43 may include a first voice language group recorded in Korean and a second voice language group recorded in English.

The speech synthesis server 43 may translate text data of the first language into text of the second language, and generate a synthesized speech corresponding to the text of the translated second language by using the second speech language group.

The speech synthesis server 43 may transmit the generated synthesized speech to the artificial intelligence device 100.

The speech synthesis server 43 may receive intention analysis information from the NLP server 42.

The speech synthesis server 43 may generate the synthesized speech reflecting the intention of the user based on the intention analysis information.

In one embodiment, the STT server 41, the NLP server 42 and the speech synthesis server 43 may be implemented as one server.

The functions of each of the above-described STT server 41, NLP server 42 and speech synthesis server 43 may also be performed in artificial intelligence device 100. To this end, the artificial intelligence device 100 may include a plurality of processors.

In addition, the functions of each of the above-described STT server 41, NLP server 42, and speech synthesis server 43 may be performed in artificial intelligence server 200. To this end, the artificial intelligence device 200 may include a plurality of processors.

5 and 6 are diagrams for describing a method of collecting training data optimized for user-specific characteristics by storing correction data for a voice command according to an exemplary embodiment.

An artificial intelligence device including a database 171 (see FIG. 8) that stores correction data that replaces a predetermined voice command may perform voice recognition.

The memory 170 of the artificial intelligence device 100 may include a database 171 that stores correction data that replaces a predetermined voice command. The database 171 may also be included in the memory 230 of the artificial intelligence server 200.

The database 171 may store correction data that replaces a predetermined voice command in the form of "index", "voice command data", and "correction data mapped to a voice mapping command."

Referring to FIG. 5, the input unit 120 of the artificial intelligence device 100 may receive a first voice command from a first user (S501).

The input unit 120 may include a microphone for receiving a voice command from a user. The microphone of the input unit 120 may receive a first voice command from the first user.

When the operation to be performed on the first voice command is not determined, the processor 180 may store the first voice command in a database (S502).

The case where the operation is not determined for the voice command may include a case in which the artificial intelligence device 100 does not perform an operation corresponding to the voice command.

For example, the processor 180 may obtain a voice command “high LG” from the user through the input unit 120.

The artificial intelligence device 100 may determine that it is necessary to perform an operation of entering a state of waiting for the next voice command while outputting a voice of “You have called”.

On the other hand, when there is a problem in which the pronunciation of the “high LG” voice command is unclear or the sound is low, the artificial intelligence device 100 may not determine an operation to be performed on the “high LG” voice command.

Referring to FIG. 6, when storing the first voice command in a database, the processor 180 may retrieve a voice command having a similar pattern to the first voice command from the database (S601).

In addition, the processor 180 may determine whether a voice command having a pattern similar to the first voice command has been searched for (S602).

When a voice command having a similar pattern to the first voice command is found, the processor 180 may store the voice command having a similar pattern as a voice command (S603).

Also, when a voice command having a pattern similar to the first voice command is found, the processor 180 may not store the first voice command. Therefore, the capacity of the database can be efficiently managed without storing the voice command redundantly.

In addition, when a voice command having a pattern similar to the first voice command is not found, the processor 180 may store the first voice command in a database (S604).

Referring back to FIG. 5, the processor 180 may obtain correction data that replaces the first voice command from the second user (S503).

The processor 180 acquires the correction data through the input unit 120 of the artificial intelligence device 100 or uses the wired / wireless communication technology through the communication unit 110 to transmit another artificial intelligence device 100a to 100e or the artificial intelligence server 200. Can be obtained from

The processor 180 may obtain a second voice command from the second user through the input unit 120.

The processor 180 may obtain text data from the second user through the input unit 120.

For example, if the first voice command input from the first user is a local dialect of "Weekend on weekends?", The processor 180 is correction data that replaces the first voice command from the second user. You can acquire the voice command "Warm on weekends?" Or the text data "Warm on weekends?"

In addition, when the artificial intelligence device 100 enters a learning mode for a voice command, the processor 180 may allow a second user to input correction data to replace the first voice command.

In addition, the processor 180 may determine whether the second user has a correction authority (S504).

The processor 180 may determine whether the second user has a correction authority based on the second voice command obtained from the second user.

For example, the processor 180 acquires at least one or more voice data from the second user and registers the second user as a user having correction authority, and stores the acquired voice data or feature information of the voice data. A user can be registered as a user with correction authority.

The processor 180 compares whether the voice is uttered from the same talker based on the second voice command obtained from the second user and the feature information of the pre-stored voice data or voice data of the user who has the right of correction. It is possible to determine whether the user has a right to calibrate.

In addition, when it is determined that the second user is a user having correction authority, the processor 180 may determine whether an operation to be performed on the obtained correction data is determined (S505).

The processor 180 may obtain a second voice command from the second user, and when the operation to be performed on the second voice command is determined, the processor 180 may obtain the second voice command as correction data that replaces the first voice command. .

In addition, the processor 180 may acquire text data from the second user, and when the operation to be performed on the text data is determined, the processor 180 may obtain the text data as correction data that replaces the first voice command.

For example, the processor 180 may obtain a second voice command “high LG” from a second user as correction data to replace the first voice command “High LG” having an unpronounced or low sound problem. Can be. In this case, the processor 180 enters a state in which the artificial intelligence device 100 waits for the next voice command while outputting the voice “You have called” based on the voice command “High LG” obtained from the second user. It can be checked whether it is determined that the operation to be performed is performed. If the operation to be performed is determined, the processor 180 may obtain a voice command “high lg” obtained from the second user as correction data to replace the first voice command. Therefore, the quality of the correction data for the first voice command can be guaranteed.

Also, for example, the processor 180 may obtain text data “high LG” from a second user as correction data that replaces the first voice command “high LG” having an unpronounced or low sound problem. Can be. In this case, the processor 180 enters a state in which the artificial intelligence device 100 waits for the next voice command while outputting the voice “You have called” based on the text data “high LG” obtained from the second user. It can be checked whether it is determined that the operation to be performed is performed. If the operation to be performed is determined, the processor 180 may obtain text data of “high LG” obtained from the second user as correction data to replace the first voice command. Therefore, the quality of the correction data for the first voice command can be guaranteed.

The processor 180 may obtain correction data for correcting previously stored correction data that replaces the first voice command from the second user.

In addition, the processor 180 may obtain correction data for correcting previously stored correction data that replaces the first voice command as correction data that replaces the first voice command.

For example, if the pre-stored correction data that replaces the first voice command "Weekend weather again?" Is text data "Weekend weather warm?", The processor 180 reads "Weekend weather warm?" It is possible to obtain text data "Warm weather on weekends?", Which is correction data for correcting text data. In addition, the processor 180 may obtain the text data “Warm on weekends?” As correction data that replaces the first voice command “Wear on weekends again?” And store it in the database 171.

The processor 180 may map the first voice command and the obtained correction data and store the same in a database (S506).

The database 171 may be configured in the form of "index", "voice command data", and "correction data mapped to a voice mapping command."

For example, the processor 180 maps a first voice command called “high LG” and correction data obtained from a second user, whose pronunciation is inaccurate and speech recognition is not possible, and stores it in the database 171 based on the same index. Can be.

7 is a flowchart illustrating a method of performing speech recognition using correction data for a voice command according to an embodiment of the present invention.

The microphone of the input unit 120 may receive a third voice command from the first user (S701).

The processor 180 may perform voice recognition by acquiring correction data replacing the third voice command from the database and determining an operation to be performed on the correction data replacing the third voice command.

The processor 180 may obtain correction data that replaces the third voice command from the database.

The processor 180 may perform voice recognition by determining an operation to be performed on correction data that replaces the third voice command.

The processor 180 may search for a voice command having a pattern similar to the third voice command (S702).

The processor 180 may obtain correction data stored by being mapped with a voice command having the found similar pattern (S703).

The processor 180 may obtain correction data that replaces the voice command having the found similar pattern, as correction data that replaces the third voice command (S704).

The processor 180 may determine whether the obtained correction data is text data (S705).

When the correction data is text data, the processor 180 may transmit the correction data to the NLP server 42 performing intent analysis (S706).

The processor 180 may acquire intention analysis information from the NLP server 42 and perform speech recognition (S707).

 If the correction data is not text data, the processor 180 may perform voice recognition with the correction data (S708).

In addition, the processor 180 uses at least one of a Speech To Text (STT) engine for converting correction data into a string or a Natural Language Processing (NLP) engine for obtaining intent information of a natural language. Intent information corresponding to the data can be obtained.

8 through 10 are diagrams for explaining a process of collecting, by an artificial intelligence device, correction data for a voice command and performing voice recognition using the correction data.

8 to 10, the first user 801 may speak the pronunciation as a young child. The artificial intelligence device 100 may be an artificial intelligence speaker, but is not limited thereto, and may include a communication robot disposed in a home, and the like.

The processor 180 of the artificial intelligence device 100 may obtain, via the microphone of the input unit 120, a first voice command 803 of “Hi-LGE” having an incorrect pronunciation from the first user 801. have.

In addition, since the processor 180 of the artificial intelligence device 100 does not determine an operation to be performed on the first voice command 803, the processor 180 may output a message “Please make an accurate pronunciation”.

 In addition, since the processor 180 does not determine an operation to be performed on the first voice command 803, the processor 180 may store the first voice command 803 in the database 171.

The processor 180 may search the database 171 for a voice command having a pattern similar to that of the first voice command 803. In this case, since a voice command having a similar pattern to the first voice command 803 is not found in the database 171, the first voice command 803 may be stored, and the first voice command 803 may be replaced. The calibration data can be stored unmapped.

The processor 180 may obtain the second voice command 804 as correction data to replace the first voice command 803 from the second user 802.

Since the processor 180 determines that the message output operation “Do you call it?”, Which is an operation to be performed on the second voice command 804, is determined, the processor 180 replaces the second voice command 804 with the first voice command 803. The first voice command 803 and the correction data 804 may be mapped and stored in the database 171.

The processor 180 may receive a third voice command 805 from the first user 801 through the microphone of the input unit 120.

The processor 180 retrieves a voice command 803 having a similar pattern from the third voice command 805 from the database 171, and obtains correction data 804 that replaces the voice command 803 having the retrieved similar pattern. In this case, it is possible to obtain the correction data 804 to replace the third voice command 805. Accordingly, the processor 180 of the artificial intelligence device 100 determines voice output by determining an operation of “Do you call it?”, Which is an operation that should be performed on the correction data 804 that replaces the third voice command 805. Can be performed.

FIG. 11 is a diagram for describing a process of adding or editing correction data for a voice command stored in an artificial intelligence device according to an embodiment of the present invention.

The communication unit 110 of the artificial intelligence device 100 may transmit / receive data with the smartphone 100d using wired or wireless communication technology, and may transmit / receive data stored in the database 171 of the artificial intelligence device 100. .

In addition, the smartphone 100d may output data of the database 171 on the screen.

For example, the communication unit 110 of the artificial intelligence device 100 may transmit a voice command stored in the database 171 and correction data mapped to the voice command to the smartphone 100d. In this case, the artificial intelligence device 100 may check whether the smartphone 100d has a right to view data.

The smartphone 100d may output correction data mapped to the voice command and the voice correction command received from the artificial intelligence device 100.

In addition, the smartphone 100d may provide an interface through which an authorized second user may modify or delete correction data of the database 171.

For example, the smartphone 100d may output four voice commands received from the artificial intelligence device 100 and correction data mapped to each voice command through the display unit. The smartphone 100d may provide an interface for deleting or modifying correction data mapped to each voice command. In addition, when the correction data mapped to the voice command does not exist, the smartphone 100d may provide an interface that allows a second user having correction authority to input the correction data to learn the correction data to replace the voice command. Can be.

In addition, the artificial intelligence device 100d may receive correction data learned or modified in the smartphone 100d through the communication unit 110, and may update the database 171 with the received correction or correction data. have.

The present invention described above can be embodied as computer readable codes on a medium in which a program is recorded. The computer-readable medium includes all kinds of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable media include hard disk drives (HDDs), solid state disks (SSDs), silicon disk drives (SDDs), ROMs, RAMs, CD-ROMs, magnetic tapes, floppy disks, optical data storage devices, and the like. There is this. The computer may also include a processor 180 of the terminal.

Claims (19)

In an artificial intelligence device that performs speech recognition,
A database for storing correction data that replaces a predetermined voice command;
A microphone receiving a first voice command from a first user;
If the operation to be performed on the first voice command is not determined, the first voice command is stored in the database, and correction data for replacing the first voice command is obtained from a second user. And a processor configured to map a voice command and the correction data to the database.
Artificial intelligence devices. The method of claim 1,
The processor,
Retrieving a voice command having a similar pattern to the first voice command from the database, and storing the first voice command in the database if a voice command having a similar pattern to the first voice command is not retrieved.
Artificial intelligence devices. The method of claim 1,
The processor,
Acquiring a second voice command from the second user and replacing the second voice command with the first voice command when it is determined that the second user is a user with correction authority based on the second voice command. Obtained with correction data,
Artificial intelligence devices. The method of claim 1,
The processor,
Acquiring a second voice command from the second user and acquiring the second voice command as correction data that replaces the first voice command when it is determined that an operation to be performed on the second voice command is determined;
Artificial intelligence devices. The method of claim 1,
The processor,
Acquiring text data from the second user, and when the operation to be performed on the text data is determined, acquiring the text data as correction data that replaces the first voice command;
Artificial intelligence devices. The method of claim 1,
The processor,
Acquiring correction data for correcting previously stored correction data replacing the first voice command from the second user, and acquiring the corrected correction data as correction data for replacing the first voice command;
Artificial intelligence devices. The method of claim 1,
The microphone,
Receiving a third voice command from the first user,
The processor,
Acquiring correction data to replace the third voice command from the database, and determining an operation to be performed on the correction data to replace the third voice command, and performing voice recognition;
Artificial intelligence devices. The method of claim 7, wherein
The processor,
Retrieving a voice command having a similar pattern to the third voice command from the database, and obtaining correction data to replace the voice command having the retrieved similar pattern as correction data to replace the third voice command,
Artificial intelligence devices. The method of claim 7, wherein
Further comprising a communication unit for transmitting the correction data to replace the third voice command to the NLP server for performing intention analysis,
The processor,
Obtaining intention analysis information from the NLP server to perform speech recognition,
Artificial intelligence devices. A voice recognition method performed by an artificial intelligence device comprising a database storing correction data replacing a predetermined voice command,
Receiving a first voice command from a first user;
If the operation to be performed on the first voice command is not determined, storing the first voice command in the database;
Obtaining correction data that replaces the first voice command from a second user; And
And mapping the first voice command and the obtained correction data and storing the same in the database.
Speech recognition method. The method of claim 10,
The storing of the first voice command in the database may include:
Retrieving a voice command having a pattern similar to the first voice command from the database; And
If a voice command having a pattern similar to the first voice command is not retrieved, storing the first voice command in the database.
Speech recognition method. The method of claim 10,
Acquiring correction data to replace the first voice command,
Obtaining a second voice command from the second user; And
Acquiring the second voice command as correction data that replaces the first voice command when it is determined that the second user is a user having correction authority based on the second voice command.
Speech recognition method. The method of claim 10,
Acquiring correction data to replace the first voice command,
Obtaining a second voice command from the second user; And
When the operation to be performed on the second voice command is determined, acquiring the second voice command as correction data that replaces the first voice command.
Speech recognition method. The method of claim 10,
Acquiring correction data to replace the first voice command,
Obtaining text data from the second user; And
If the operation to be performed on the text data is determined, acquiring the text data as correction data that replaces the first voice command;
Speech recognition method. The method of claim 10,
Acquiring correction data to replace the first voice command,
Acquiring correction data for correcting previously stored correction data that replaces the first voice command from the second user; And
Acquiring the corrected correction data as correction data to replace the first voice command;
Speech recognition method. The method of claim 10,
Receiving a third voice command from the first user;
Obtaining correction data from the database to replace the third voice command; And
And performing voice recognition by determining an operation to be performed on correction data that replaces the third voice command.
Speech recognition method. The method of claim 16,
Obtaining correction data that replaces the third voice command from the database,
Retrieving a voice command having a pattern similar to the third voice command from the database; And
Acquiring correction data for substituting the voice command having the retrieved similar pattern as correction data for substituting the third voice command;
Speech recognition method. The method of claim 16,
Performing the speech recognition,
Transmitting correction data in place of the third voice command to an NLP server performing intent analysis; And
Acquiring intent analysis information from the NLP server to perform speech recognition;
Speech recognition method. In an artificial intelligence device that performs speech recognition,
A database for storing correction data that replaces a predetermined voice command;
A microphone for receiving a voice command from a user; And
And a processor for acquiring correction data that replaces the voice command from the database and determining an operation to be performed on the correction data that replaces the voice command to perform voice recognition.
Artificial intelligence devices.

Images