-
公开(公告)号：USRE49762E1
公开(公告)日：2023-12-19
申请号：US17487437
申请日：2021-09-28
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Chi-youn Park , Il-hwan Kim , Kyung-min Lee , Nam-hoon Kim , Jae-won Lee
IPC: G10L15/22 , G10L15/187 , G10L15/14 , G10L15/197 , G10L15/06 , G10L15/02
CPC classification number: G10L15/063 , G10L15/02 , G10L15/14 , G10L15/187 , G10L15/197 , G10L2015/025 , G10L2015/0633 , G10L2015/0635
Abstract: A method of updating speech recognition data including a language model used for speech recognition, the method including obtaining language data including at least one word; detecting a word that does not exist in the language model from among the at least one word; obtaining at least one phoneme sequence regarding the detected word; obtaining components constituting the at least one phoneme sequence by dividing the at least one phoneme sequence into predetermined unit components; determining information regarding probabilities that the respective components constituting each of the at least one phoneme sequence appear during speech recognition; and updating the language model based on the determined probability information.
-
公开(公告)号：US11264008B2
公开(公告)日：2022-03-01
申请号：US16163789
申请日：2018-10-18
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Ji-sang Yu , Sang-ha Kim , Jong-youb Ryu , Yoon-jung Choi , Eun-kyoung Kim , Jae-won Lee
Abstract: A method and an electronic device for translating a speech signal between a first language and a second language with minimized translation delay by translating fewer than all words of the speech signal according to a level of understanding of the second language by a user that receives the translation.
-
公开(公告)号：US10964310B2
公开(公告)日：2021-03-30
申请号：US16820353
申请日：2020-03-16
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Chi-youn Park , Il-hwan Kim , Kyung-min Lee , Nam-hoon Kim , Jae-won Lee
IPC: G10L15/22 , G10L15/06 , G10L15/197 , G10L15/02 , G10L15/14 , G10L15/187
Abstract: A method of updating speech recognition data including a language model used for speech recognition, the method including obtaining language data including at least one word; detecting a word that does not exist in the language model from among the at least one word; obtaining at least one phoneme sequence regarding the detected word; obtaining components constituting the at least one phoneme sequence by dividing the at least one phoneme sequence into predetermined unit components; determining information regarding probabilities that the respective components constituting each of the at least one phoneme sequence appear during speech recognition; and updating the language model based on the determined probability information.
-
公开(公告)号：US10665224B2
公开(公告)日：2020-05-26
申请号：US16523263
申请日：2019-07-26
Applicant: Samsung Electronics Co., Ltd.
Inventor： Chi-youn Park , Il-hwan Kim , Kyung-min Lee , Nam-hoon Kim , Jae-won Lee
IPC: G10L15/22 , G10L15/30 , G06F3/00 , G10L15/06 , G10L15/197 , G10L15/02 , G10L15/14 , G10L15/187
Abstract: A method of updating speech recognition data including a language model used for speech recognition, the method including obtaining language data including at least one word; detecting a word that does not exist in the language model from among the at least one word; obtaining at least one phoneme sequence regarding the detected word; obtaining components constituting the at least one phoneme sequence by dividing the at least one phoneme sequence into predetermined unit components; determining information regarding probabilities that the respective components constituting each of the at least one phoneme sequence appear during speech recognition; and updating the language model based on the determined probability information.
-
公开(公告)号：US10410638B2
公开(公告)日：2019-09-10
申请号：US15553819
申请日：2015-02-27
Inventor： Hanseok Ko , Sung-soo Kim , Jinsang Rho , Suwon Shon , Jae-won Lee
Abstract: A method of converting a feature vector includes extracting a feature sequence from an audio signal including utterance of a user; extracting a feature vector from the feature sequence; acquiring a conversion matrix for reducing a dimension of the feature vector, based on a probability value acquired based on different covariance values; and converting the feature vector by using the conversion matrix.
-
Patent Agency Ranking
公开(公告)号：US10055406B2
公开(公告)日：2018-08-21
申请号：US15012206
申请日：2016-02-01
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Ji-sang Yu , Jin-sik Lee , Sang-ha Kim , Eun-kyoung Kim , Dong-hyeon Lee , Jae-won Lee
CPC classification number: G06F17/289 , G06F17/241
Abstract: A server, a user terminal, and a method for controlling the server and the user terminal are provided. The server controlling method includes receiving a text from a user terminal, translating the received text to generate a translated text, extracting at least one core word from the translated text, obtaining image information corresponding to the at least one core word with respect to each of the at least one core word, and transmitting the translated text and the extracted image information to the user terminal.
-
27.发明授权公开(公告)号：US11687319B2
公开(公告)日：2023-06-27
申请号：US17215409
申请日：2021-03-29
Applicant: Samsung Electronics Co., Ltd.
Inventor： Sung-ja Choi , Eun-kyoung Kim , Ji-sang Yu , Ji-yeon Hong , Jong-youb Ryu , Jae-won Lee
CPC classification number: G06F3/167 , G06N20/00 , G10L15/08 , G10L15/22 , G10L15/26 , G10L15/30 , G10L17/24 , G10L2015/228
Abstract: A speech recognition method and apparatus for performing speech recognition in response to an activation word determined based on a situation are provided. The speech recognition method and apparatus include an artificial intelligence (AI) system and its application, which simulates functions such as recognition and judgment of a human brain using a machine learning algorithm such as deep learning.
-
公开(公告)号：US20220148567A1
公开(公告)日：2022-05-12
申请号：US17585019
申请日：2022-01-26
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Ji-sang YU , Sang-ha Kim , Jong-youb Ryu , Yoon-jung Choi , Eun-kyoung Kim , Jae-won Lee
Abstract: A method and an electronic device for translating a speech signal between a first language and a second language with minimized translation delay by translating fewer than all words of the speech signal according to a level of understanding of the second language by a user that receives the translation.
-
29.发明授权公开(公告)号：US11003417B2
公开(公告)日：2021-05-11
申请号：US15783476
申请日：2017-10-13
Applicant: Samsung Electronics Co., Ltd.
Inventor： Sung-ja Choi , Eun-kyoung Kim , Ji-sang Yu , Ji-yeon Hong , Jong-youb Ryu , Jae-won Lee
Abstract: A speech recognition method and apparatus for performing speech recognition in response to an activation word determined based on a situation are provided. The speech recognition method and apparatus include an artificial intelligence (AI) system and its application, which simulates functions such as recognition and judgment of a human brain using a machine learning algorithm such as deep learning.
-
公开(公告)号：US10923126B2
公开(公告)日：2021-02-16
申请号：US15557378
申请日：2015-03-19
Inventor： Hanseok Ko , Sung-soo Kim , Taeyup Song , Kyungsun Lee , Jae-won Lee
Abstract: Provided is a method of detecting a voice section, including detecting from at least one image an area where lips exist, obtaining a feature value of movement of the lips in the detected area based on a difference between pixel values of pixels included in the detected area, and detecting the voice section from the at least one image based on the feature value.
-
-
-
-
-
-
-
-
-
Search Results
38
records
(took 0.025 seconds)
