Patents by Inventor Tae-gyoon KANG
Tae-gyoon KANG 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).
-
Patent number: 11776529Abstract: A method, the method includes determining a target segment partially overlapping a preceding segment from a speech signal, determining a target character sequence corresponding to the target segment by decoding the target segment, identifying a first overlapping portion between the target character sequence and a preceding character sequence based on an edit distance, and merging the target character sequence and the preceding character sequence based on the first overlapping portion. A cost applied to the edit distance is determined based on any one or any combination of any two or more of a type of operation performed at the edit distance, whether characters to be operated are located in the first overlapping portion, and whether the characters to be operated match. A portion overlapping the preceding segment in the target segment is greater than or equal to 8.3% of the target segment.Type: GrantFiled: July 7, 2021Date of Patent: October 3, 2023Assignee: Samsung Electronics Co., Ltd.Inventor: Tae Gyoon Kang
-
Publication number: 20230306961Abstract: A decoding method and apparatus in an artificial neural network for speech recognition. The decoding method in the artificial neural network for speech recognition includes performing a first decoding task of decoding a feature including speech information and at least one token recognized up to current time, using a shared decoding layer included in the artificial neural network, performing a second decoding task of decoding the at least one token, using the shared decoding layer, and determining an output token to be recognized subsequent to the at least one token based on a result of the first decoding task and a result of the second decoding task.Type: ApplicationFiled: May 23, 2023Publication date: September 28, 2023Applicant: Samsung Electronics Co., Ltd.Inventors: Min-Joong LEE, Tae Gyoon KANG
-
Patent number: 11721323Abstract: A method, the method includes determining a target segment from a speech signal, determining a target character sequence corresponding to the target segment by decoding the target segment, identifying a first overlapping portion between the target character sequence and a preceding character sequence based on an edit distance, and merging the target character sequence and the preceding character sequence based on the first overlapping portion. A cost applied to the edit distance is determined based on any one or any combination of any two or more of a type of operation performed at the edit distance, whether characters to be operated are located in the first overlapping portion, and whether the characters to be operated match.Type: GrantFiled: October 29, 2020Date of Patent: August 8, 2023Assignee: Samsung Electronics Co., Ltd.Inventor: Tae Gyoon Kang
-
Patent number: 11694677Abstract: A decoding method and apparatus in an artificial neural network for speech recognition. The decoding method in the artificial neural network for speech recognition includes performing a first decoding task of decoding a feature including speech information and at least one token recognized up to current time, using a shared decoding layer included in the artificial neural network, performing a second decoding task of decoding the at least one token, using the shared decoding layer, and determining an output token to be recognized subsequent to the at least one token based on a result of the first decoding task and a result of the second decoding task.Type: GrantFiled: April 9, 2020Date of Patent: July 4, 2023Assignee: Samsung Electronics Co., Ltd.Inventors: Min-Joong Lee, Tae Gyoon Kang
-
Patent number: 11670290Abstract: A speech signal processing method and apparatus is disclosed. The speech signal processing method includes receiving an input token that is based on a speech signal, calculating first probability values respectively corresponding to candidate output tokens based on the input token, adjusting at least one of the first probability values based on a priority of each of the first probability values, and processing the speech signal based on an adjusted probability value obtained by the adjusting.Type: GrantFiled: November 30, 2020Date of Patent: June 6, 2023Assignee: Samsung Electronics Co., Ltd.Inventor: Tae Gyoon Kang
-
Patent number: 11249756Abstract: A processor implemented natural language processing method and apparatus are provided. The natural language processing method includes converting a natural language phrase into a token vector, calculating a repetition count of the token vector, and generating an input vector by encoding the token vector based on the calculated repetition count and a position of the token vector.Type: GrantFiled: March 9, 2020Date of Patent: February 15, 2022Assignee: Samsung Electronics Co., Ltd.Inventors: Tae Gyoon Kang, Min-Joong Lee
-
Publication number: 20220020362Abstract: A speech signal processing method and apparatus is disclosed. The speech signal processing method includes receiving an input token that is based on a speech signal, calculating first probability values respectively corresponding to candidate output tokens based on the input token, adjusting at least one of the first probability values based on a priority of each of the first probability values, and processing the speech signal based on an adjusted probability value obtained by the adjusting.Type: ApplicationFiled: November 30, 2020Publication date: January 20, 2022Applicant: Samsung Electronics Co., Ltd.Inventor: Tae Gyoon KANG
-
Publication number: 20210335341Abstract: A method, the method includes determining a target segment partially overlapping a preceding segment from a speech signal, determining a target character sequence corresponding to the target segment by decoding the target segment, identifying a first overlapping portion between the target character sequence and a preceding character sequence based on an edit distance, and merging the target character sequence and the preceding character sequence based on the first overlapping portion. A cost applied to the edit distance is determined based on any one or any combination of any two or more of a type of operation performed at the edit distance, whether characters to be operated are located in the first overlapping portion, and whether the characters to be operated match. A portion overlapping the preceding segment in the target segment is greater than or equal to 8.3% of the target segment.Type: ApplicationFiled: July 7, 2021Publication date: October 28, 2021Applicant: Samsung Electronics Co., Ltd.Inventor: Tae Gyoon Kang
-
Publication number: 20210335339Abstract: A method, the method includes determining a target segment from a speech signal, determining a target character sequence corresponding to the target segment by decoding the target segment, identifying a first overlapping portion between the target character sequence and a preceding character sequence based on an edit distance, and merging the target character sequence and the preceding character sequence based on the first overlapping portion. A cost applied to the edit distance is determined based on any one or any combination of any two or more of a type of operation performed at the edit distance, whether characters to be operated are located in the first overlapping portion, and whether the characters to be operated match.Type: ApplicationFiled: October 29, 2020Publication date: October 28, 2021Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventor: TAE GYOON KANG
-
Publication number: 20210109752Abstract: A processor implemented natural language processing method and apparatus are provided. The natural language processing method includes converting a natural language phrase into a token vector, calculating a repetition count of the token vector, and generating an input vector by encoding the token vector based on the calculated repetition count and a position of the token vector.Type: ApplicationFiled: March 9, 2020Publication date: April 15, 2021Applicant: Samsung Electronics Co., Ltd.Inventors: Tae Gyoon KANG, Min-Joong LEE
-
Publication number: 20210035562Abstract: A decoding method and apparatus in an artificial neural network for speech recognition. The decoding method in the artificial neural network for speech recognition includes performing a first decoding task of decoding a feature including speech information and at least one token recognized up to current time, using a shared decoding layer included in the artificial neural network, performing a second decoding task of decoding the at least one token, using the shared decoding layer, and determining an output token to be recognized subsequent to the at least one token based on a result of the first decoding task and a result of the second decoding task.Type: ApplicationFiled: April 9, 2020Publication date: February 4, 2021Applicant: Samsung Electronics Co., Ltd.Inventors: Min-Joong LEE, Tae Gyoon KANG
-
Patent number: 10509864Abstract: A language model training method and an apparatus using the language model training method are disclosed. The language model training method includes assigning a context vector to a target translation vector, obtaining feature vectors based on the target translation vector and the context vector, generating a representative vector representing the target translation vector using an attention mechanism for the feature vectors, and training a language model based on the target translation vector, the context vector, and the representative vector.Type: GrantFiled: April 9, 2018Date of Patent: December 17, 2019Assignee: Samsung Electronics Co., Ltd.Inventors: Tae Gyoon Kang, Hodong Lee
-
Publication number: 20190163747Abstract: A language model training method and an apparatus using the language model training method are disclosed. The language model training method includes assigning a context vector to a target translation vector, obtaining feature vectors based on the target translation vector and the context vector, generating a representative vector representing the target translation vector using an attention mechanism for the feature vectors, and training a language model based on the target translation vector, the context vector, and the representative vector.Type: ApplicationFiled: April 9, 2018Publication date: May 30, 2019Applicant: Samsung Electronics Co., Ltd.Inventors: Tae Gyoon KANG, Hodong LEE
-
Patent number: 8892436Abstract: A method of recognizing speech is provided. The method includes the operations of (a) dividing first speech that is input to a speech recognizing apparatus into frames; (b) converting the frames of the first speech into frames of second speech by applying conversion rules to the divided frames, respectively; and (c) recognizing, by the speech recognizing apparatus, the frames of the second speech, wherein (b) comprises converting the frames of the first speech into the frames of the second speech by reflecting at least one frame from among the frames that are previously positioned with respect to a frame of the first speech.Type: GrantFiled: October 19, 2011Date of Patent: November 18, 2014Assignees: Samsung Electronics Co., Ltd., Seoul National University Industry FoundationInventors: Ki-wan Eom, Chang-woo Han, Tae-gyoon Kang, Nam-soo Kim, Doo-hwa Hong, Jae-won Lee, Hyung-joon Lim
-
Publication number: 20120095762Abstract: A method of recognizing speech is provided. The method includes the operations of (a) dividing first speech that is input to a speech recognizing apparatus into frames; (b) converting the frames of the first speech into frames of second speech by applying conversion rules to the divided frames, respectively; and (c) recognizing, by the speech recognizing apparatus, the frames of the second speech, wherein (b) comprises converting the frames of the first speech into the frames of the second speech by reflecting at least one frame from among the frames that are previously positioned with respect to a frame of the first speech.Type: ApplicationFiled: October 19, 2011Publication date: April 19, 2012Applicants: SEOUL NATIONAL UNIVERSITY INDUSTRY FOUNDATION, SAMSUNG ELECTRONICS CO., LTD.Inventors: Ki-wan EOM, Chang-woo HAN, Tae-gyoon KANG, Nam-soo KIM, Doo-hwa HONG, Jae-won LEE, Hyung-joon LIM