Patents by Inventor Hyung Min Park

Hyung Min Park has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20190189114
    Abstract: Provided is a method for beamforming by using maximum likelihood estimation in a speech recognition apparatus, including: (a) receiving an input signal (Xn,k) at a time frame n and a frequency k where noise is mixed: (b) determining a probability density function for a target signal (Yn,k) under an assumption that the target signal (Yn,k) obtained by removing the noise from the input signal satisfies a complex generalized Gaussian distribution or a complex gamma distribution where an average value is zero in a time-frequency domain; (c) estimating a variance (?n,k) of the target signal so as to maximize log likelihood for the probability density function; (d) estimating a filter (wk) maximizing a cost function so as to maximize the log likelihood for the probability density function; and (e) repeatedly performing the estimation of the steps (c) and (d) until the filter (wk) converges, and finally acquiring a final filter (wk).
    Type: Application
    Filed: December 18, 2018
    Publication date: June 20, 2019
    Inventor: Hyung Min PARK
  • Publication number: 20190079466
    Abstract: Provided are a prediction value correction method and apparatus. The prediction value correction method includes steps of: (a) determining a prediction condition to be predicted; (b) receiving past prediction values and past measurement values according to the determined prediction condition; (c) filtering the past prediction values and the past measurement values by using an H-infinity filter to obtain an output value for a final time point; (d) estimating a future bias for a date and time point to be predicted by using the output value of the H-infinity filter; and (e) correcting a future prediction value for the date and time point to be predicted by using the estimated future bias to obtain a corrected future prediction value for the date and time point to be predicted.
    Type: Application
    Filed: September 11, 2018
    Publication date: March 14, 2019
    Inventors: Jaechan Lim, Hyung Min PARK
  • Publication number: 20190074000
    Abstract: Provided is a target speech signal extraction method for robust speech recognition including: (a) receiving information on a direction of arrival of the target speech source with respect to the microphones; (b) generating a nullformer by using the information on the direction of arrival of the target speech source to remove the target speech signal from the input signals and to estimate noise; (c) setting a real output of the target speech source using an adaptive vector w(k) as a first channel and setting a dummy output by the nullformer as a remaining channel; (d) setting a cost function for minimizing dependency between the real output of the target speech source and the dummy output using the nullformer by performing independent component analysis (ICA); and (e) estimating the target speech signal by using the cost function, thereby extracting the target speech signal from the input signals.
    Type: Application
    Filed: November 6, 2018
    Publication date: March 7, 2019
    Inventors: Hyung-Min PARK, Minook KIM
  • Publication number: 20190017814
    Abstract: The present disclosure relates to a method for generating a monochrome permutation structured-light pattern and a structured-light system using the method, and the method for generating a monochrome structured-light pattern that is represented with two or more luminous intensities of a single color includes selecting two different luminous intensities of a single color, generating a stripe for each selected luminous intensity, apart from the two luminous intensities selected previously, generating at least one combination stripe by combining regions of two or more different luminous intensities that are identical to or different from the previously selected two luminous intensities, generating permutations using the generated stripes as elements, setting each permutation as a subpattern, and introducing permutation overlapping into the set subpatterns to generate a monochrome structured-light pattern in which each subpattern is connected in sequential overlapping manner.
    Type: Application
    Filed: July 16, 2018
    Publication date: January 17, 2019
    Applicant: SOGANG UNIVERSITY RESEARCH FOUNDATION
    Inventors: Changsoo JE, Hyung-Min PARK
  • Publication number: 20190005655
    Abstract: Provided are an object tracking method and an object tracking system. The object tracking method uses a particle filter configured by combining a Minimax estimation technique with a Monte Carlo sampling method. In the object tracking method, for each of the particles, a feature having a maximum cost among measurement values of at least two or more features is selected, a weight for the particle is calculated by using the measurement value of the selected feature, and a position of the target, object in the frame is estimated by using the weight of each of the candidate particles.
    Type: Application
    Filed: June 27, 2018
    Publication date: January 3, 2019
    Inventors: Jaechan LIM, Hyung Min PARK
  • Publication number: 20180357118
    Abstract: Provided is an operating method of a monitoring device configured to monitor a microcontroller unit including a plurality of cores. The operating method includes: transmitting a question message to a first core among the plurality of cores; receiving an answer message from a second core among the plurality of cores; determining whether an operation of the microcontroller unit is abnormal, by using the answer message; receiving answer messages from cores, except for the second core, among the plurality of cores when the operation of the microcontroller unit is abnormal; and detecting an error of each of the plurality of cores by using the received answer messages.
    Type: Application
    Filed: June 5, 2018
    Publication date: December 13, 2018
    Applicant: Hyundai Autron Co., Ltd.
    Inventors: Dong On JANG, Hyung Min PARK, Yeon Ho KIM, Jae Hyuck WOO, Ji Haeng LEE, Won Hee JO
  • Publication number: 20180357536
    Abstract: A beating pattern recognition system includes: a preprocessor preprocessing an input signal; a deep neural network learning processor including a plurality of deep neural networks and performing learning to classify an input type of the input signal; and a classification processor classifying the input type of the preprocessed input signal using the learned deep neural network.
    Type: Application
    Filed: November 22, 2017
    Publication date: December 13, 2018
    Inventors: Hui Sung LEE, Hyung Min PARK, Young Man KIM
  • Publication number: 20180153878
    Abstract: An oral solid formulation includes irinotecan or a pharmaceutically acceptable salt thereof as an active ingredient, and an acidifying agent.
    Type: Application
    Filed: June 20, 2016
    Publication date: June 7, 2018
    Applicant: HANMI PHARM. CO., LTD.
    Inventors: Caleb Hyung Min PARK, Myeong Ki JUNG, Jin Cheul KIM, Yong Il KIM, Jae Hyun PARK, Jong Soo WOO
  • Patent number: 9929328
    Abstract: Provided is a lighting device, comprising: a light source module comprising: at least one light source disposed on a printed circuit board; and a resin layer disposed on the printed circuit board so that the light source is embedded; a light reflection member formed on at least any one of one side surface and another side surface of the resin layer; and a diffusion plate having an upper surface which is in contact with an upper part of the light source module, and a side wall which is integrally formed with the upper surface and formed to extend in a lower side direction and which is adhered to the light reflection member, whereby flexibility of the product itself can be secured, and durability and reliability of the product can be also improved.
    Type: Grant
    Filed: June 27, 2013
    Date of Patent: March 27, 2018
    Assignee: LG INNOTEK CO., LTD.
    Inventors: Kwang Ho Park, Moo Ryong Park, Ki Beom Kim, Jin Hee Kim, Chul Hong Kim, Hyung Min Park, Hyun Hee Chae, Jun Chul Hyun
  • Patent number: 9747922
    Abstract: A sound signal processing method, the sound signal processing apparatus and the vehicle equipped with the apparatus, in which the sound signal processing apparatus includes a spatial filtering unit configured to obtain a filtered signal including a target signal by a spatial filtering by applying a spatial filter to an input signal, and a mask application unit configured to obtain an output signal by applying a mask to the filtered signal. The mask may be obtained by using a spatial selectivity between the target signal and noise of the target signal.
    Type: Grant
    Filed: December 22, 2014
    Date of Patent: August 29, 2017
    Assignees: HYUNDAI MOTOR COMPANY, KIA MOTORS CORPORATION, SOGANG UNIVERSITY RESEARCH FOUNDATION
    Inventors: Yunil Hwang, Biho Kim, Hyung Min Park
  • Patent number: 9625642
    Abstract: A light unit is provided. The light unit includes a PCB mounted with a plurality of LEDs, and a light guide member having a plurality of reception grooves piercing therethrough and receiving the LEDs, wherein the light guide member includes one surface and the other surface opposite to the one surface, and the one surface of the light guide member is further coated with the resin material. The reception grooves are formed in the light guide member and are filled with a fluid resin material, thus preventing the damage to the LED caused by the difference between the thermal expansion rates of the components such as the light guide member, the reflection film and the PCB.
    Type: Grant
    Filed: September 2, 2011
    Date of Patent: April 18, 2017
    Assignee: LG INNOTEK CO., LTD.
    Inventors: Jong Sun Kim, Sang Jun Park, Jae Hyuk Jang, Hyung Min Park, Kyoung Soo Ahn, Jeong Oh Lee, Yong In Lee
  • Patent number: 9627595
    Abstract: Provided is a lighting device, comprising: a light source module comprising: at least one light source disposed on a printed circuit board; and a resin layer disposed on the printed circuit board so that the light source is embedded; an indirect light emission unit which is formed in at least any one of one side and another side of the light source module and which reflects light irradiated from the light source; and a diffusion plate having an upper surface which is in contact with an upper part of the light source module, and a side wall which is integrally formed with the upper surface and formed to extend in a lower side direction and which is adhered onto an outer side surface of the indirect light emission unit, whereby flexibility of the product itself can be secured, and durability and reliability thereof can be also improved.
    Type: Grant
    Filed: June 27, 2013
    Date of Patent: April 18, 2017
    Assignee: LG INNOTEK CO., LTD.
    Inventors: Kwang Ho Park, Moo Ryong Park, Chul Hong Kim, Ki Beom Kim, Jin Hee Kim, Hyung Min Park, Hyun Hee Chae
  • Patent number: 9609431
    Abstract: Provided are an interested audio source cancellation method, a voice recognition method using the interested audio source cancellation method, computer-readable recording media recording programs for implementing the methods, and a voice recognition apparatus for performing voice recognition by using the interested audio source cancellation method. The interested audio source cancellation method includes steps of: receiving input mixed signals from two microphones and transforming the signals into a time-frequency domain through short-term Fourier transformation; setting an interested audio source cancellation vector for cancelling an interested audio source signal from the input mixed signals in the time-frequency domain; and generating a mixed noise signal by cancelling the interested audio source signal from the input mixed signals by using the interested audio source cancellation vector.
    Type: Grant
    Filed: December 17, 2012
    Date of Patent: March 28, 2017
    Assignee: INDUSTRY-UNIVERSITY COOPERATION FOUNDATION SOGANG UNIVERSITY
    Inventors: Hyung Min Park, Myung Woo Oh
  • Publication number: 20160275954
    Abstract: Provided is a target speech signal extraction method for robust speech recognition including: (a) receiving information on a direction of arrival of the target speech source with respect to the microphones; (b) generating a nullformer by using the information on the direction of arrival of the target speech source to remove the target speech signal from the input signals and to estimate noise; (c) setting a real output of the target speech source using an adaptive vector w(k) as a first channel and setting a dummy output by the nullformer as a remaining channel; (d) setting a cost function for minimizing dependency between the real output of the target speech source and the dummy output using the nullformer by performing independent component analysis (ICA); and (e) estimating the target speech signal by using the cost function, thereby extracting the target speech signal from the input signals.
    Type: Application
    Filed: March 16, 2016
    Publication date: September 22, 2016
    Inventors: Hyung- Min PARK, Minook KIM
  • Patent number: 9355641
    Abstract: A monitoring device is provided, which includes an inputter configured to receive an input of a plurality of images captured at separate positions and a plurality of sound sources heard at separate positions, a saliency map generator configured to generate a plurality of mono saliency maps for the plurality of images and to generate a dynamic saliency map using the plurality of mono saliency maps generated, a position determinator configured to determine the positions of the sound sources through analysis of the plurality of sound sources, a scan path recognizer configured to generate scan paths of the plurality of images based on the generated dynamic saliency map and the determined positions of the sound sources, and an outputter configured to output the generated scan paths.
    Type: Grant
    Filed: December 5, 2012
    Date of Patent: May 31, 2016
    Assignees: KYUNGPOOK NATIONAL UNIVERSITY INDUSTRY-ACADEMIC COOPERATION, INDUSTRY-UNIVERSITY COOPERATION FOUNDATION SOGANG UNIVERSITY
    Inventors: Minho Lee, Young-Min Jang, Sungmoon Jeong, Bumhwi Kim, Hyung-Min Park, Minook Kim
  • Publication number: 20160086602
    Abstract: A sound signal processing method, the sound signal processing apparatus and the vehicle equipped with the apparatus, in which the sound signal processing apparatus includes a spatial filtering unit configured to obtain a filtered signal including a target signal by a spatial filtering by applying a spatial filter to an input signal, and a mask application unit configured to obtain an output signal by applying a mask to the filtered signal. The mask may be obtained by using a spatial selectivity between the target signal and noise of the target signal.
    Type: Application
    Filed: December 22, 2014
    Publication date: March 24, 2016
    Inventors: Yunil HWANG, Biho KIM, Hyung Min PARK
  • Patent number: 9207382
    Abstract: Disclosed is a light unit. The light unit includes a printed circuit board formed thereon with a plurality of LEDs and a light guide member having receiving holes to receive the LEDs. At least one round part having a predetermined curvature is formed at an edge defined in an intersection between an upper surface and an inner surface of the receiving hole. Since the round part is formed at the edge in the receiving hole receiving the LED at the portion of the light guide member, the light distribution is improved so that the light efficiency is increased.
    Type: Grant
    Filed: November 10, 2011
    Date of Patent: December 8, 2015
    Assignee: LG INNOTEK CO., LTD.
    Inventors: Kyoung Soo Ahn, Jong Sun Kim, Sang Jun Park, Hyung Min Park, Jeong Oh Lee, Jae Hyuk Jang
  • Publication number: 20140355776
    Abstract: Provided are an interested audio source cancellation method, a voice recognition method using the interested audio source cancellation method, computer-readable recording media recording programs for implementing the methods, and a voice recognition apparatus for performing voice recognition by using the interested audio source cancellation method. The interested audio source cancellation method includes steps of: receiving input mixed signals from two microphones and transforming the signals into a time-frequency domain through short-term Fourier transformation; setting an interested audio source cancellation vector for cancelling an interested audio source signal from the input mixed signals in the time-frequency domain; and generating a mixed noise signal by cancelling the interested audio source signal from the input mixed signals by using the interested audio source cancellation vector.
    Type: Application
    Filed: December 17, 2012
    Publication date: December 4, 2014
    Inventors: Hyung Min Park, Myung Woo Oh
  • Publication number: 20140334682
    Abstract: A monitoring device is provided, which includes an inputter configured to receive an input of a plurality of images captured at separate positions and a plurality of sound sources heard at separate positions, a saliency map generator configured to generate a plurality of mono saliency maps for the plurality of images and to generate a dynamic saliency map using the plurality of mono saliency maps generated, a position determinator configured to determine the positions of the sound sources through analysis of the plurality of sound sources, a scan path recognizer configured to generate scan paths of the plurality of images based on the generated dynamic saliency map and the determined positions of the sound sources, and an outputter configured to output the generated scan paths.
    Type: Application
    Filed: December 5, 2012
    Publication date: November 13, 2014
    Applicants: KYUNGPOCK NATIONAL INDUSRTY ACADEMIC COOPERATION FOUNDATION, INDUSTRY-UNIVERSITY COOPERATION FOUNDATION SOGANG UNIVERSITY
    Inventors: Minho Lee, Young-Min Jang, Sungmoon Jeong, Bumhwi Kim, Hyung-Min Park, Minook Kim
  • Publication number: 20140222425
    Abstract: Provided are a speech recognition learning method using 3D geometric information and a speech recognition method by using 3D geometric information. The method performs learning by using 3D geometric information for learning or information derived from the 3D geometric information to generate a recognizer, and the speech recognition method performs speech recognition by applying 3D geometric information on a physical object correlated to or dependent on voice or information derived from the 3D geometric information to the recognizer.
    Type: Application
    Filed: February 7, 2014
    Publication date: August 7, 2014
    Applicant: SOGANG UNIVERSITY RESEARCH FOUNDATION
    Inventors: Hyung-Min PARK, Changsoo JE, Bi Ho KIM, Min Wook KIM