Abstract: According to a method of an embodiment of the present disclosure, a method for correcting a beamforming pattern of a base station by an analysis server of a base station management network may comprise the steps of: when network management information is received from a first base station, identifying whether or not the network management information indicates the occurrence of a failure in an antenna element of the first base station; when the network management information indicates the occurrence of the failure in the antenna element of the first base station, analyzing an effect of a beamforming pattern of the first base station and analyzing a change in a cell coverage; on the basis of the result of the analysis, determining a first beamforming pattern for compensating for the failure in the antenna element; and transmitting, to the first base station, information about the first beamforming pattern by including the information in management control information.

Abstract: An electronic device is provided. The electronic device includes a first power management integrated circuit (PMIC) with a first fault controller connected to a first node and a first interface circuit connected to a second node; a second PMIC with a second fault controller connected to the first node and a second interface circuit connected to the second node; and a third PMIC with a third fault controller connected to the first node and a third interface circuit connected to the second node. The first fault controller is configured to, during a power on sequence or a power off sequence, detect a change in a voltage level of the first node. The first interface circuit is configured to communicate with any one or any combination of the second interface circuit and communication and the third interface circuit based on the change in the voltage level of the first node.

Abstract: An electronic device is provided. The electronic device includes a first power management integrated circuit (PMIC) with a first fault controller connected to a first node and a first interface circuit connected to a second node; a second PMIC with a second fault controller connected to the first node and a second interface circuit connected to the second node; and a third PMIC with a third fault controller connected to the first node and a third interface circuit connected to the second node. The first fault controller is configured to, during a power on sequence or a power off sequence, detect a change in a voltage level of the first node. The first interface circuit is configured to communicate with any one or any combination of the second interface circuit and communication and the third interface circuit based on the change in the voltage level of the first node.

Abstract: A method for generating an acoustic model is disclosed. The method can generate the acoustic model with high accuracy through learning data including various dialects by training the acoustic model using text data, to which regional information is tagged, and changing a parameter of the acoustic model based on the tagged regional information. The acoustic model can be associated with an artificial intelligence module, an unmanned aerial vehicle (UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, devices related to 5G services, and the like.

Abstract: Disclosed is an artificial intelligence (AI) apparatus for training an acoustic model, and more particularly, an AI apparatus for training an acoustic model including a shared network and a branch network connected to the shared network using speech data and phonemes corresponding to the speech data.

Abstract: A learning system and method for updating recognition performance by assigning weights according to a confidence level of data are discussed. The unsupervised learning system includes a memory configured to store speech data received from a server that performs speech recognition; and a processor configured to measure confidence levels of pieces of learnable data stored in the memory and classify the pieces of learnable data into learning data and adaptation data, generate a learning model by performing unsupervised learning on the learning data, generate an adaption model using the adaptation data, and evaluate speech recognition performance for the learning model and the adaptation model, wherein the processor is configured to assign weights by applying the measured confidence levels to the learning model and the adaptation model and update recognition performance with the learning model and the adaptation model to which the weights are applied.

Abstract: Disclosed is an artificial intelligence (AI) apparatus for training an acoustic model, and more particularly, an AI apparatus for training an acoustic model including a shared network and a branch network connected to the shared network using speech data and phonemes corresponding to the speech data.

Abstract: A method for generating an acoustic model is disclosed. The method can generate the acoustic model with high accuracy through learning data including various dialects by training the acoustic model using text data, to which regional information is tagged, and changing a parameter of the acoustic model based on the tagged regional information. The acoustic model can be associated with an artificial intelligence module, an unmanned aerial vehicle (UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, devices related to 5G services, and the like.

Abstract: A terminal includes a memory configured to store voice data and a processor configured to measure reliability of learnable data stored in the memory, to classify the learnable data into learning data or adaptive data according to the measured reliability, to generate a learning model by performing unsupervised learning with respect to the learning data, to generate an adaptive model using the adaptive data, and to evaluate recognition performance of each of the learning model and the adaptive model.

Abstract: A terminal includes a memory configured to store voice data and a processor configured to measure reliability of learnable data stored in the memory, to classify the learnable data into learning data or adaptive data according to the measured reliability, to generate a learning model by performing unsupervised learning with respect to the learning data, to generate an adaptive model using the adaptive data, and to evaluate recognition performance of each of the learning model and the adaptive model.

Abstract: A learning system and method for updating recognition performance by assigning weights according to a confidence level of data are discussed. The unsupervised learning system includes a memory configured to store speech data received from a server that performs speech recognition; and a processor configured to measure confidence levels of pieces of learnable data stored in the memory and classify the pieces of learnable data into learning data and adaptation data, generate a learning model by performing unsupervised learning on the learning data, generate an adaption model using the adaptation data, and evaluate speech recognition performance for the learning model and the adaptation model, wherein the processor is configured to assign weights by applying the measured confidence levels to the learning model and the adaptation model and update recognition performance with the learning model and the adaptation model to which the weights are applied.