Samsung Electronics Co., Ltd.

Korea Advanced Institute of Science and Technology

Yonghoon Lee

Hangil Moon

Beakkwon Son

Chulmin Choi

Jeock Lee

Jinwoo Park

Jonghwan Kim

Hochul Hwang

Jiyun Seol

Jeongho Park

Gangyoul Kim

Kyoungho Bang

Jinyong Kim

Gunwoo Lee

Jaemo Yang

Kiho Cho

Seongkwan Yang

SungJin Kim

Namil Lee

Soonho Baek

Yangsu Kim

Gunhyuk Yoon

Seungyoon Heo

Jaeha Park

Keunwon Jang

Minhyun Kim

Jongmo Keum

Changtaek Kang

Byeongmin Lee

Myoungho Lee

Gabriel Nicolae

Sindhu Vijaya-Raghavan

Uitae Hwang

George Brancovici

Hiep Luong

A wearable device outputting a sound for an object of interest and a method for controlling the same are disclosed. In an embodiment, a wearable device may comprise at least one microphone, at least one speaker, and at least one processor. The at least one processor may be configured to identify an object of interest of a user wearing the wearable device, obtain a sound signal generated from the identified object of interest using the at least one microphone, and output the sound signal generated from the object of interest through the at least one speaker or output a sound related to the object of interest through the at least one speaker, based on a sensitivity of the obtained sound signal.

Wearable device outputting sound for object of interest and method for controlling the same

A wearable device is provided and includes a plurality of speakers including a first speaker, a second speaker, and an Nspeaker, a plurality of digital to analog converter (DAC)s including a first DAC connected to the first speaker, a second DAC connected to the second speaker, and an NDAC connected to the Nspeaker, an audio signal processing module including N DAC output paths configured to filter an audio signal according to each frequency band and output the audio signal, a memory; and a processor electrically connected to the plurality of DACs, the audio signal processing module, and the memory, wherein the memory includes instructions causing the processor to, when the audio signal is reproduced, analyze a frequency component included in the audio signal, activate the N DAC output paths when the frequency component included in the audio signal has a full band range, activate only a DAC output path for processing a specific frequency band among the N DAC output paths when the frequency component included in the audio signal has only the specific frequency band, and output the audio signal through a speaker connected to the activated DAC output path.

Wearable device and method for controlling audio output using multi digital to analog converter path

According to an embodiment, an electronic device may include a memory configured to store a noise removal neural network model and data utilized in the noise removal neural network model and a processor electrically connected to the memory wherein the memory may store instructions that, when executed, enable the processor to: output a first channel signal using a first beamformer for a multi-channel audio signal; output a second channel signal using a second beamformer; generate a third channel signal that compensates for a difference in noise levels between the first channel signal and the second channel signal; and train the noise removal neural network model by using the third channel signal in which the difference in noise levels is compensated for and the first channel signal as input values.

Method for processing multi-channel audio signal on basis of neural network and electronic device

An audio processing method and an electronic device for supporting the same are provided. The audio signal processing method includes checking property information of an audio signal in response to a request for playing the audio signal; processing, when property information fulfills a first condition, the audio signal using the first method and, when the property information fulfills a second condition, the audio signal using the second method; and outputting the audio signal processed using one of the first and second methods through a speaker.

Audio signal processing method and electronic device for supporting the same

A system includes a storage device configured to store a plurality of named entities collected from a plurality of sources, tokenized, and associated with a label. The system includes a tagging apparatus configured to receive textual communications, identify each of the textual communications, tokenize the textual communications, match the textual tokens with the named entities tokens stored in the storage device in order to assign the textual tokens to the labels associated with the named entity tokens, tag the textual communications based on the matching between the textual tokens and the named entity tokens in order to identify the intended meaning of each of the textual communications, and identify the intended meaning of the textual communications based on applying the tags to the textual communications. A method capable of disambiguating named entities using a common sense reasoning approach is also disclosed.

Method and system for robust tagging of named entities in the presence of source or translation errors

A method and apparatus configures a beamforming coefficient based on the signal strength information without collecting channel information by adjusting the phase of the antennas through random perturbation. An antenna control method of a base station in a wireless communication system using a beamforming technique includes measuring nreceived signal strength at nphase of at least one receive antenna, measuring (n+1)received signal strength at (n+1)phase shifted randomly from the nphase in one of forward and backward directions, and configuring a beamforming coefficient with the phase at which the received signal strength is greatest through comparison of received signal strengths. The random perturbation-based beamforming method and apparatus of the present disclosure is capable of configuring the beamforming coefficient appropriate for the normal cellular environment using a plurality analog array antenna without channel estimation overhead.

Random perturbation-based beamforming method and apparatus for use in mobile communication system

Growing community of inventors

Gyeonggi-do, South Korea

Yonghoon Lee