Patents by Inventor Eunmi Oh

Eunmi Oh 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: 20220180872
    Abstract: An electronic apparatus, based on a text sentence being input, obtains prosody information of the text sentence, segments the text sentence into a plurality of sentence elements, obtains a speech in which prosody information is reflected to each of the plurality of sentence elements in parallel by inputting the plurality of sentence elements and the prosody information of the text sentence to a text to speech (TTS) module, and merges the speech for the plurality of sentence elements that are obtained in parallel to output speech for the text sentence.
    Type: Application
    Filed: February 24, 2022
    Publication date: June 9, 2022
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jonghoon JEONG, Hosang SUNG, Doohwa HONG, Kyoungbo MIN, Eunmi OH, Kihyun CHOO
  • Patent number: 11335325
    Abstract: An electronic device and a controlling method of the electronic device are provided. The electronic device acquires text to respond on a received user's speech, acquires a plurality of pieces of parameter information for determining a style of an output speech corresponding to the text based on information on a type of a plurality of text-to-speech (TTS) databases and the received user's speech, identifies a TTS database corresponding to the plurality of pieces of parameter information among the plurality of TTS databases, identifies a weight set corresponding to the plurality of pieces of parameter information among a plurality of weight sets acquired through a trained artificial intelligence model, adjusts information on the output speech stored in the TTS database based on the weight set, synthesizes the output speech based on the adjusted information on the output speech, and outputs the output speech corresponding to the text.
    Type: Grant
    Filed: January 22, 2020
    Date of Patent: May 17, 2022
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Hosang Sung, Seonho Hwang, Doohwa Hong, Eunmi Oh, Kyoungbo Min, Jonghoon Jeong, Kihyun Choo
  • Patent number: 11289083
    Abstract: An electronic apparatus, based on a text sentence being input, obtains prosody information of the text sentence, segments the text sentence into a plurality of sentence elements, obtains a speech in which prosody information is reflected to each of the plurality of sentence elements in parallel by inputting the plurality of sentence elements and the prosody information of the text sentence to a text to speech (TTS) module, and merges the speech for the plurality of sentence elements that are obtained in parallel to output speech for the text sentence.
    Type: Grant
    Filed: November 14, 2019
    Date of Patent: March 29, 2022
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jonghoon Jeong, Hosang Sung, Doohwa Hong, Kyoungbo Min, Eunmi Oh, Kihyun Choo
  • Publication number: 20200279551
    Abstract: An electronic apparatus which acquires input data to be input into a TTS module for outputting a voice through the TTS module, acquires a voice signal corresponding to the input data through the TTS module, detects an error in the acquired voice signal based on the input data, corrects the input data based on the detection result, and acquires a corrected voice signal corresponding to the corrected input data through the TTS module.
    Type: Application
    Filed: February 12, 2020
    Publication date: September 3, 2020
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Hosang Sung, Kyoungbo Min, Seonho Hwang, Doohwa Hong, Eunmi Oh, Jonghoon Jeong, Kihyun Choo
  • Publication number: 20200234693
    Abstract: An electronic device and a controlling method of the electronic device are provided. The electronic device acquires text to respond on a received user's speech, acquires a plurality of pieces of parameter information for determining a style of an output speech corresponding to the text based on information on a type of a plurality of text-to-speech (TTS) databases and the received user's speech, identifies a TTS database corresponding to the plurality of pieces of parameter information among the plurality of TTS databases, identifies a weight set corresponding to the plurality of pieces of parameter information among a plurality of weight sets acquired through a trained artificial intelligence model, adjusts information on the output speech stored in the TTS database based on the weight set, synthesizes the output speech based on the adjusted information on the output speech, and outputs the output speech corresponding to the text.
    Type: Application
    Filed: January 22, 2020
    Publication date: July 23, 2020
    Inventors: Hosang SUNG, Seonho HWANG, Doohwa HONG, Eunmi OH, Kyoungbo MIN, Jonghoon JEONG, Kihyun CHOO
  • Publication number: 20200152194
    Abstract: An electronic apparatus, based on a text sentence being input, obtains prosody information of the text sentence, segments the text sentence into a plurality of sentence elements, obtains a speech in which prosody information is reflected to each of the plurality of sentence elements in parallel by inputting the plurality of sentence elements and the prosody information of the text sentence to a text to speech (TTS) module, and merges the speech for the plurality of sentence elements that are obtained in parallel to output speech for the text sentence.
    Type: Application
    Filed: November 14, 2019
    Publication date: May 14, 2020
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jonghoon JEONG, Hosang SUNG, Doohwa HONG, Kyoungbo MIN, Eunmi OH, Kihyun CHOO
  • Patent number: 9934789
    Abstract: A method, medium, and apparatus with scalable channel decoding. The method includes recognizing the configuration of channels or speakers, calculating the respective number of same path decoding levels for each multi-channel signal using the recognized configuration of the channels or speakers, and performing decoding and up-mixing according to the calculated respective number of decoding levels.
    Type: Grant
    Filed: January 11, 2007
    Date of Patent: April 3, 2018
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe Kim, Eunmi Oh, Kihyun Choo, Miao Lei
  • Patent number: 9848180
    Abstract: Surround audio decoding for selectively generating an audio signal from a multi-channel signal. In the surround audio decoding, a down-mixed signal, e.g., as down-mixed by an encoding terminal, is selectively up-mixed to a stereo signal or a multi-channel signal, by generating spatial information for generating the stereo signal, using spatial information for up-mixing the down-mixed signal to the multi-channel signal.
    Type: Grant
    Filed: July 8, 2015
    Date of Patent: December 19, 2017
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe Kim, Eunmi Oh, Kihyun Choo, Miao Lei
  • Patent number: 9706325
    Abstract: A method, medium, and system decoding and/or encoding multiple channels. Accordingly, down-mixed multiple channels can be decoded/up-mixed to a left channel and a right channel during a first stage, thereby enabling a high quality sound output even in scalable channel decoding.
    Type: Grant
    Filed: June 13, 2016
    Date of Patent: July 11, 2017
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe Kim, Eunmi Oh, Kihyun Choo, Miao Lei
  • Patent number: 9667270
    Abstract: An system, method, and method of encoding/decoding a multi-channel audio signal, including a decoding level generation unit producing decoding-level information that helps a bitstream including a number of audio channel signals and space information to be decoded into a number of audio channel signals, wherein the space information includes information about magnitude differences and/or similarities between channels, and an audio decoder decoding the bitstream according to the decoding-level information. Accordingly, even a single input bitstream can be decoded into a suitable number of channels depending on the type of a speaker configuration used. Scalable channel decoding can be achieved by partially decoding an input bitstream. In the scalable channel decoding, a decoder may set decoding levels and outputs audio channel signals according to the decoding levels, thereby reducing decoding complexity.
    Type: Grant
    Filed: July 21, 2015
    Date of Patent: May 30, 2017
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe Kim, Miao Lei, Eunmi Oh
  • Patent number: 9552820
    Abstract: An apparatus for and a method of processing a multi-channel audio signal using space information. The apparatus includes: a main coding unit down mixing a multi-channel audio signal by applying space information to surround components included in the multi-channel audio signal, generating side information using the multi-channel audio signal or a stereo signal of a down-mixed result, coding the stereo signal and the side information, and transmitting the coded result as a coding signal; and a main decoding unit receiving the coding signal, decoding the stereo signal and the side information using the received coding signal, up mixing the decoded stereo signal using the decoded side information, and restoring the multi-channel audio signal.
    Type: Grant
    Filed: December 11, 2015
    Date of Patent: January 24, 2017
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe Kim, Sangchul Ko, Shihwa Lee, Eunmi Oh, Miao Lei
  • Patent number: 9479871
    Abstract: A method, medium, and system generating a 3-dimensional (3D) stereo signal in a decoder by using a surround data stream. According to such a method, medium, and system, a head related transfer function (HRTF) is applied in a quadrature mirror filter (QMF) domain, thereby generating a 3D stereo signal by using a surround data stream.
    Type: Grant
    Filed: December 19, 2013
    Date of Patent: October 25, 2016
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe Kim, Eunmi Oh, Kihyun Choo, Miao Lei
  • Publication number: 20160302021
    Abstract: A method, medium, and system decoding and/or encoding multiple channels. Accordingly, down-mixed multiple channels can be decoded/up-mixed to a left channel and a right channel during a first stage, thereby enabling a high quality sound output even in scalable channel decoding.
    Type: Application
    Filed: June 13, 2016
    Publication date: October 13, 2016
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe KIM, Eunmi OH, Kihyun CHOO, Miao LEI
  • Patent number: 9384743
    Abstract: An apparatus and method for encoding/decoding a multi-channel signal may be provided. The apparatus of encoding a multi-channel signal may insert information about whether to encode a phase parameter indicating phase information of a plurality of channels, included in the multi-channel signal, in a bitstream of the multi-channel signal. The apparatus of decoding a multi-channel signal may determine whether to up-mix a mono signal using the phase parameter based on the information about whether to encode.
    Type: Grant
    Filed: February 16, 2015
    Date of Patent: July 5, 2016
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jung Hoe Kim, Eunmi Oh, Mi Young Kim, Ki Hyun Choo
  • Patent number: 9369164
    Abstract: A method, medium, and system decoding and/or encoding multiple channels. Accordingly, down-mixed multiple channels can be decoded/up-mixed to a left channel and a right channel during a first stage, thereby enabling a high quality sound output even in scalable channel decoding.
    Type: Grant
    Filed: January 10, 2007
    Date of Patent: June 14, 2016
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe Kim, Eunmi Oh, Kihyun Choo, Miao Lei
  • Publication number: 20160099002
    Abstract: An apparatus for and a method of processing a multi-channel audio signal using space information. The apparatus includes: a main coding unit down mixing a multi-channel audio signal by applying space information to surround components included in the multi-channel audio signal, generating side information using the multi-channel audio signal or a stereo signal of a down-mixed result, coding the stereo signal and the side information, and transmitting the coded result as a coding signal; and a main decoding unit receiving the coding signal, decoding the stereo signal and the side information using the received coding signal, up mixing the decoded stereo signal using the decoded side information, and restoring the multi-channel audio signal.
    Type: Application
    Filed: December 11, 2015
    Publication date: April 7, 2016
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe KIM, Sangchul KO, Shihwa LEE, Eunmi OH, Miao LEI
  • Patent number: 9232334
    Abstract: An apparatus for and a method of processing a multi-channel audio signal using space information. The apparatus includes: a main coding unit down mixing a multi-channel audio signal by applying space information to surround components included in the multi-channel audio signal, generating side information using the multi-channel audio signal or a stereo signal of a down-mixed result, coding the stereo signal and the side information, and transmitting the coded result as a coding signal; and a main decoding unit receiving the coding signal, decoding the stereo signal and the side information using the received coding signal, up mixing the decoded stereo signal using the decoded side information, and restoring the multi-channel audio signal.
    Type: Grant
    Filed: September 1, 2014
    Date of Patent: January 5, 2016
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe Kim, Sangchul Ko, Shihwa Lee, Eunmi Oh, Miao Lei
  • Publication number: 20150348563
    Abstract: An encoder and decoder to encode one or more input signals into a scalable codec and to decode the scalable codec, and encoding and decoding methods using a bitstream with a layered structure in the scalable codec change a top coding bit rate to encode the input signals according to a network status, and the bitstream is decoded by analyzing the top coding bit rate included in the bitstream.
    Type: Application
    Filed: July 27, 2015
    Publication date: December 3, 2015
    Applicant: Samsung Electronics Co., Ltd.
    Inventors: Hosang SUNG, Eunmi OH, Junghoe KIM, Kangeun LEE
  • Patent number: RE46082
    Abstract: An apparatus and method of low bit rate encoding and reproducing. The method includes transforming input audio signals in a time domain into spectral signals in a frequency domain, extracting important-spectrum components from the spectral signals in the frequency domain, and quantizing the important-spectrum components, extracting residual-spectrum components other than the important-spectrum components from the spectral signals in the frequency domain, and calculating and quantizing a noise level of the residual-spectrum components, and encoding the quantized important-spectrum components and the quantized noise level losslessly, and outputting encoded bitstreams.
    Type: Grant
    Filed: November 15, 2012
    Date of Patent: July 26, 2016
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Junghoe Kim, Eunmi Oh, Boris Kudryashov, Konstantin Osipov
  • Patent number: D798836
    Type: Grant
    Filed: December 2, 2015
    Date of Patent: October 3, 2017
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Donghyun Jung, Wook Hyoung Lee, Yong Sun Cho, Jiho Chang, Dongkyu Park, Haekwang Park, Eunmi Oh, Yoonjae Lee, Donghyun Lim, Jaeyoun Cho