公开(公告)号：US10957340B2

公开(公告)日：2021-03-23

申请号：US16492911

申请日：2017-03-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ho-sang Sung ,  Eun-mi Oh ,  Holly Francois

IPC: G10L25/00 ,  G10L25/60 ,  G10L21/0208 ,  G10L25/03 ,  G10L25/78 ,  H04M3/22

Abstract: A voice signal processing method according to an embodiment of the present disclosure for overcoming the problem includes: acquiring a real-time near-end noise signal; acquiring a far-end voice signal according to an incoming call; measuring subjective speech quality and perceptual-objective speech quality of test signals generated based on a reference signal and the real-time near-end noise signal; selecting at least one speech quality enhancement method based on the subjective speech quality and the perceptual-objective speech quality, and determining parameters that are to be applied to the selected at least one speech quality enhancement method; and enhancing speech quality of the far-end voice signal by using the selected at least one speech quality enhancement method, based on the determined parameters, wherein the test signals are generated by mixing the acquired real-time near-end noise signal with the reference signal whose speech quality is enhanced by applying a combination of parameter values to speech quality enhancement methods.

公开(公告)号：US10803877B2

公开(公告)日：2020-10-13

申请号：US15757547

申请日：2016-09-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ho-sang Sung ,  Holly Francois ,  Ki-hyun Choo ,  Eun-mi Oh ,  Kyung-hun Jung ,  Yaodu Wei

IPC: G10L21/00 ,  G10L19/028 ,  G10L19/22 ,  G10L21/0208 ,  G10L21/02 ,  G10L19/26 ,  G10L21/038 ,  G10L19/00 ,  H04M3/22

Abstract: Provided are a signal processing method and apparatus for enhancing sound quality. The signal processing method performed by a signal transmitting apparatus includes determining, based on a plurality of parameters, a valid bandwidth so as to encode an input signal; performing pre-processing on the input signal, based on the valid bandwidth; and encoding the pre-processed input signal, based on the valid bandwidth, and the signal processing method performed by a signal receiving apparatus includes decoding a bitstream or a packet received via a transmission channel; determining a valid bandwidth, based on a plurality of parameters used in the decoding; and performing post-processing on a decoded signal, based on the valid bandwidth.

公开(公告)号：US20210225358A1

公开(公告)日：2021-07-22

申请号：US17037023

申请日：2020-09-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jesus MONGE ALVAREZ ,  Holly Francois ,  Hosang Sung ,  Seungdo Choi ,  Kihyun Choo ,  Sangjun Park

IPC: G10L13/027 ,  G10L13/047 ,  G10L13/06 ,  G10L15/06 ,  G10L15/187

Abstract: A system for synthesising expressive speech includes: an interface configured to receive an input text for conversion to speech; a memory; and at least one processor coupled to the memory. The processor is configured to generate, using an expressivity characterisation module, a plurality of expression vectors, wherein each expression vector is a representation of prosodic information in a reference audio style file, and synthesise expressive speech from the input text, using an expressive acoustic model comprising a deep convolutional neural network that is conditioned by at least one of the plurality of expression vectors.

公开(公告)号：US11830473B2

公开(公告)日：2023-11-28

申请号：US17037023

申请日：2020-09-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jesus Monge Alvarez ,  Holly Francois ,  Hosang Sung ,  Seungdo Choi ,  Kihyun Choo ,  Sangjun Park

IPC: G10L13/027 ,  G10L13/047 ,  G10L15/06 ,  G10L15/187 ,  G10L13/06

CPC classification number: G10L13/027 ,  G10L13/047 ,  G10L13/06 ,  G10L15/063 ,  G10L15/187 ,  G10L2015/0635

Abstract: A system for synthesising expressive speech includes: an interface configured to receive an input text for conversion to speech; a memory; and at least one processor coupled to the memory. The processor is configured to generate, using an expressivity characterisation module, a plurality of expression vectors, wherein each expression vector is a representation of prosodic information in a reference audio style file, and synthesise expressive speech from the input text, using an expressive acoustic model comprising a deep convolutional neural network that is conditioned by at least one of the plurality of expression vectors.

公开(公告)号：US11380338B2

公开(公告)日：2022-07-05

申请号：US17037128

申请日：2020-09-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ho-sang Sung ,  Holly Francois ,  Ki-hyun Choo ,  Eun-mi Oh ,  Kyung-hun Jung ,  Yaodu Wei

IPC: G10L19/028 ,  G10L19/22 ,  G10L21/0208 ,  G10L19/26 ,  G10L21/038 ,  G10L19/00 ,  H04M3/22

Abstract: Provided are a signal processing method and apparatus for enhancing sound quality. The signal processing method performed by a signal transmitting apparatus includes determining, based on a plurality of parameters, a valid bandwidth so as to encode an input signal; performing pre-processing on the input signal, based on the valid bandwidth; and encoding the pre-processed input signal, based on the valid bandwidth, and the signal processing method performed by a signal receiving apparatus includes decoding a bitstream or a packet received via a transmission channel; determining a valid bandwidth, based on a plurality of parameters used in the decoding; and performing post-processing on a decoded signal, based on the valid bandwidth.

公开(公告)号：US11037581B2

公开(公告)日：2021-06-15

申请号：US16312827

申请日：2017-06-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ki-hyun Choo ,  Holly Francois ,  Eun-mi Oh ,  Chang-yeong Kim ,  Ho-sang Sung ,  Kyung-hun Jung

IPC: G10L21/00 ,  G10L21/0232 ,  G10L15/20 ,  G10L21/0364

Abstract: Provided is a method for processing a signal adaptively to a noisy environment, the method including: determining a class related to enhancement of intelligibility, based on a noise spectrum of a reception side or a near-end device and a received voice spectrum; generating guide information for the enhancement of intelligibility based on the noise spectrum, the voice spectrum, and the determined class; and generating a changed voice spectrum by applying the guide information to the voice spectrum.