公开(公告)号：US09355646B2

公开(公告)日：2016-05-31

申请号：US14020006

申请日：2013-09-06

Applicant: SAMSUNG Electronics Co., Ltd.

Inventor： Eun Mi Oh ,  Jung Hoe Kim ,  Ki-Hyun Choo ,  Ho Sang Sung ,  Mi Young Kim

IPC: G10L19/00 ,  G10L19/04 ,  G10L19/008 ,  G10L19/02 ,  G10L19/16

CPC classification number: G10L19/03 ,  G10L19/008 ,  G10L19/0204 ,  G10L19/0212 ,  G10L19/04 ,  G10L19/12 ,  G10L19/167 ,  G10L19/20

Abstract: A method and apparatus to encode and decode an audio/speech signal is provided. An inputted audio signal or speech signal may be transformed into at least one of a high frequency resolution signal and a high temporal resolution signal. The signal may be encoded by determining an appropriate resolution, the encoded signal may be decoded, and thus the audio signal, the speech signal, and a mixed signal of the audio signal and the speech signal may be processed.

公开(公告)号：US10373624B2

公开(公告)日：2019-08-06

申请号：US15033834

申请日：2014-11-03

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  INDUSTRY-UNIVERSITY COOPERATION FOUNDATION HANYANG UNIVERSITY ERICA CAMPUS

Inventor： Ki-Hyun Choo ,  Sang-won Kang ,  Ho-sang Sung ,  Eun-mi Oh ,  Jong-geun Jeon ,  Yaxing Li

IPC: G10L19/00 ,  G10L19/09 ,  G10L19/16 ,  G10L19/087 ,  G10L21/038

Abstract: A method of generating a wideband signal may include estimating a high-band spectrum parameter from a reconstructed narrowband signal based on a combination of at least two mapping schemes; estimating a high-band excitation signal based on the reconstructed narrowband signal; generating a high-band signal based on the estimated high-band spectrum parameter and the estimated high-band excitation signal; and generating a wideband signal by synthesizing the reconstructed narrowband signal with the high-band signal.

公开(公告)号：US11282535B2

公开(公告)日：2022-03-22

申请号：US16757070

申请日：2018-07-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ki-Hyun Choo ,  Anton Porov ,  Jong-Hoon Jeong ,  Ho-Sang Sung ,  Eun-Mi Oh ,  Jong-Youb Ryu

IPC: G10L15/25 ,  G10L25/30 ,  G10L21/02

Abstract: Disclosed is an electronic apparatus. The electronic apparatus includes a storage for storing a plurality of filters trained in a plurality of convolutional neural networks (CNNs) respectively and a processor configured to acquire a first spectrogram corresponding to a damaged audio signal, input the first spectrogram to a CNN corresponding to each frequency band to apply the plurality of filters trained in the plurality of CNNs respectively, acquire a second spectrogram by merging output values of the CNNs to which the plurality of filters are applied, and acquire an audio signal reconstructed based on the second spectrogram.