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: 20210217434
    Abstract: A target speech signal extraction method for robust speech recognition includes: initializing a steering vector for a target speech source and an adaptive vector, setting a real output channel of the target speech source as an output by the adaptive vector, initializing adaptive vectors for a noise and setting a dummy channel as an output by the adaptive vectors for the noise; setting a cost function for minimizing dependency between a real output for the target speech source and a dummy output for the noise; setting an auxiliary function to the cost function, and updating the adaptive vector for the target speech source and the adaptive vectors for the noise by using the auxiliary function and the steering vector; estimating the target speech signal by using the adaptive vector thereby extracting the target speech signal from the input signals; and updating the steering vector for the target speech source.
    Type: Application
    Filed: March 29, 2021
    Publication date: July 15, 2021
    Inventors: Hyung Min PARK, Uihyeop SHIN
  • Publication number: 20210167717
    Abstract: A motor drive system with a correction function of a temperature deviation of an IGBT module is provided. The system may include: a gate board configured to detect a plurality of sensing temperature information by sensing the IGBT module, acquire a difference value between maximum temperature information among the plurality of sensing temperature information and at least one sensing temperature information, and correct and output the at least one sensing temperature information by using the acquired difference value.
    Type: Application
    Filed: November 30, 2020
    Publication date: June 3, 2021
    Applicant: HYUNDAI AUTRON CO., LTD.
    Inventors: Hyung Min PARK, Dong On JANG, Na Yeon KIM
  • Patent number: 10994718
    Abstract: A multi-master system includes a first master, a second master, and an integrated control circuit controlled by each of the first and second masters. The integrated control circuit includes a first dedicated block configured to provide a first function to the first master, a second dedicated block configured to provide a second function to the second master, and a global using block configured to provide a common function to each of the first and second masters.
    Type: Grant
    Filed: June 27, 2018
    Date of Patent: May 4, 2021
    Assignee: HYUNDAI AUTRON CO., LTD.
    Inventors: Hyung Min Park, Ji Haeng Lee, Dong On Jang, Won Hee Jo
  • Patent number: 10991362
    Abstract: Provided is a target speech signal extraction method for robust speech recognition including: receiving information on a direction of arrival of the target speech source with respect to the microphones; 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; setting a real output of the target speech source using an adaptive vector as a first channel and setting a dummy output by the nullformer as a remaining channel; 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) or independent vector analysis (IVA); setting an auxiliary function to the cost function; and estimating the target speech signal by using the cost function and the auxiliary function.
    Type: Grant
    Filed: April 15, 2020
    Date of Patent: April 27, 2021
    Assignee: INDUSTRY-UNIVERSITY COOPERATION FOUNDATION SOGANG UNIVERSITY
    Inventors: Hyung Min Park, Seoyoung Lee, Seung-Yun Kim, Byung Joon Cho, Uihyeop Shin
  • Patent number: 10962936
    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: Grant
    Filed: September 11, 2018
    Date of Patent: March 30, 2021
    Assignee: INDUSTRY-UNIVERSITY COOPERATION FOUNDATION SOGANG UNIVERSITY
    Inventors: Jaechan Lim, Hyung Min Park
  • Patent number: 10916239
    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) obtained by removing the noise from the input signal satisfies a complex generalized Guassian 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) coverages, and finally acquiring a final filter (wk).
    Type: Grant
    Filed: December 18, 2018
    Date of Patent: February 9, 2021
    Assignee: INDUSTRY-UNIVERSITY COOPERATION FOUNDATION SOGANG UNIVERSITY
    Inventor: Hyung Min Park
  • Patent number: 10872594
    Abstract: According to an embodiment, a noise cancellation method comprises updating a first far-end channel filter according to a first variance yielded based on an input signal and a first far-end signal included in the input signal, providing a first output signal obtained by removing a first far-end noise signal from the input signal through the first far-end channel filter, updating a second far-end channel filter according to a second variance yielded based on the first output signal and a second far-end signal included in the input signal, and providing a second output signal obtained by removing a second far-end noise signal from the first output signal through the second far-end channel filter.
    Type: Grant
    Filed: February 1, 2019
    Date of Patent: December 22, 2020
    Inventors: Hyung Min Park, Byung Joon Cho
  • Publication number: 20200294524
    Abstract: A method of noise cancellation comprises providing a first estimated output signal based on an input signal and a first prior far-end channel filter and a second prior far-end channel filter corresponding to a prior frame, updating a first current far-end channel filter corresponding to a current frame according to the first estimated output signal and the first prior far-end channel filter, providing a second estimated output signal based on the input signal, the first current far-end channel filter, and the second prior far-end channel filter, updating a second current far-end channel filter corresponding to the current frame according to the second estimated output signal and the second prior far-end channel filter, and providing a resultant signal based on the input signal, the first current far-end channel filter, and the second current far-end channel filter.
    Type: Application
    Filed: September 28, 2019
    Publication date: September 17, 2020
    Inventors: Hyung Min PARK, Byung Joon CHO
  • Publication number: 20200243072
    Abstract: Provided is a target speech signal extraction method for robust speech recognition including: receiving information on a direction of arrival of the target speech source with respect to the microphones; 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; setting a real output of the target speech source using an adaptive vector as a first channel and setting a dummy output by the nullformer as a remaining channel; 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) or independent vector analysis (IVA); setting an auxiliary function to the cost function; and estimating the target speech signal by using the cost function and the auxiliary function.
    Type: Application
    Filed: April 15, 2020
    Publication date: July 30, 2020
    Inventors: Hyung Min PARK, Seoyoung LEE, Seung-Yun KIM, Byung Joon CHO, Uihyeop SHIN
  • Patent number: 10684903
    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: Grant
    Filed: June 5, 2018
    Date of Patent: June 16, 2020
    Assignee: 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: 20200159282
    Abstract: A real time clock device for a vehicle may include: a register set provided with a first register, in which second time information is stored, and configured to store Real Time Clock (RTC) data including the time or date; and a data compensation circuit to block an input of a 1 second (1 s) tick to the first register and compensate for a delay time according to the block of the input of the 1 s tick to the first register by an RTC lock signal during a process of transmitting the RTC data to an external device or receiving setting data for the RTC data from the external device.
    Type: Application
    Filed: November 19, 2019
    Publication date: May 21, 2020
    Applicant: HYUNDAI AUTRON CO., LTD.
    Inventors: Dong On JANG, Young Suk KIM, Hyung Min PARK, Ji Haeng LEE, Doo Jin JANG, Won Hee JO
  • Patent number: 10657958
    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: Grant
    Filed: November 6, 2018
    Date of Patent: May 19, 2020
    Assignee: SOGANG UNIVERSITY RESEARCH FOUNDATION
    Inventors: Hyung-Min Park, Minook Kim
  • Patent number: 10648799
    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: Grant
    Filed: July 16, 2018
    Date of Patent: May 12, 2020
    Assignee: SOGANG UNIVERSITY RESEARCH FOUNDATION
    Inventors: Changsoo Je, Hyung-Min Park
  • Patent number: 10621734
    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: Grant
    Filed: June 27, 2018
    Date of Patent: April 14, 2020
    Assignee: SOGANG UNIVERSITY RESEARCH FOUNDATION
    Inventors: Jaechan Lim, Hyung Min Park
  • Patent number: 10593344
    Abstract: Provided is a sound source localization method including steps of: (a) receiving a mixed signal of a target sound source signal and noise and echo signals through multiple microphones including at least two microphones; (b) generating a binarized mask based on a diffuseness by using a coherence-to-diffuseness ratio CDR, which is information on the target sound source and the noise source, by using the input signal; (c) pre-processing an input signal to multiple microphones by using the generated binarized mask; and (d) performing a predetermined algorithm such as the GCC-PHAT or the SRP-PHAT on the pre-processed input signal to estimate a direction of the target sound source.
    Type: Grant
    Filed: January 23, 2019
    Date of Patent: March 17, 2020
    Assignee: SOGANG UNIVERSITY RESEARCH FOUNDATION
    Inventors: Hyung Min Park, Ran Lee
  • Publication number: 20200066248
    Abstract: A method of noise cancellation comprises providing a first estimated output signal based on an input signal and a first prior far-end channel filter and a second prior far-end channel filter corresponding to a prior frame, updating a first current far-end channel filter corresponding to a current frame according to the first estimated output signal and the first prior far-end channel filter, providing a second estimated output signal based on the input signal, the first current far-end channel filter, and the second prior far-end channel filter, updating a second current far-end channel filter corresponding to the current frame according to the second estimated output signal and the second prior far-end channel filter, and providing a resultant signal based on the input signal, the first current far-end channel filter, and the second current far-end channel filter.
    Type: Application
    Filed: March 15, 2019
    Publication date: February 27, 2020
    Inventors: Hyung Min PARK, Byung Joon Cho
  • Publication number: 20200058286
    Abstract: According to an embodiment, a noise cancellation method comprises updating a first far-end channel filter according to a first variance yielded based on an input signal and a first far-end signal included in the input signal, providing a first output signal obtained by removing a first far-end noise signal from the input signal through the first far-end channel filter, updating a second far-end channel filter according to a second variance yielded based on the first output signal and a second far-end signal included in the input signal, and providing a second output signal obtained by removing a second far-end noise signal from the first output signal through the second far-end channel filter.
    Type: Application
    Filed: February 1, 2019
    Publication date: February 20, 2020
    Inventors: Hyung Min PARK, Byung Joon CHO
  • Publication number: 20200001854
    Abstract: A multi-master system includes a first master, a second master, and an integrated control circuit controlled by each of the first and second masters. The integrated control circuit includes a first dedicated block configured to provide a first function to the first master, a second dedicated block configured to provide a second function to the second master, and a global using block configured to provide a common function to each of the first and second masters.
    Type: Application
    Filed: June 27, 2018
    Publication date: January 2, 2020
    Applicant: HYUNDAI AUTRON CO., LTD.
    Inventors: Hyung Min PARK, Ji Haeng Lee, Dong On Jang, Won Hee Jo
  • Publication number: 20190237066
    Abstract: Provided is a source localization in an apparatus for performing a source localization, a target sound source enhancement or speech recognition. The source localization method using input signals input from a plurality of microphones, comprising steps of: (a) obtaining a log likelihood function or an auxiliary function under the assumption that a target source signal mixed with noises satisfies a CGMM model; (b) obtaining an equation for estimating parameter values of the log likelihood function or the auxiliary function so that a value of the log likelihood function or the auxiliary function is maximized recursively in each time frame; (c) estimating a covariance matrix recursively in each time frame; and (d) estimating a steering vector recursively by using the estimated covariance matrix, wherein the steering vector of the target sound source is estimated from the input signals.
    Type: Application
    Filed: March 12, 2019
    Publication date: August 1, 2019
    Inventors: Hyung Min PARK, Seo Young LEE
  • Publication number: 20190228790
    Abstract: Provided is a sound source localization method including steps of: (a) receiving a mixed signal of a target sound source signal and noise and echo signals through multiple microphones including at least two microphones; (b) generating a binarized mask based on a diffuseness by using a coherence-to-diffuseness ratio CDR, which is information on the target sound source and the noise source, by using the input signal; (c) pre-processing an input signal to multiple microphones by using the generated binarized mask; and (d) performing a predetermined algorithm such as the GCC-PHAT or the SRP-PHAT on the pre-processed input signal to estimate a direction of the target sound source.
    Type: Application
    Filed: January 23, 2019
    Publication date: July 25, 2019
    Inventors: Hyung Min PARK, Ran LEE