公开(公告)号：WO2023004223A1

公开(公告)日：2023-01-26

申请号：PCT/US2022/073104

申请日：2022-06-23

Applicant: QUALCOMM INCORPORATED

Inventor： MONTAZERI, Vahid ,  NGUYEN, Van ,  PESSENTHEINER, Hannes ,  KIM, Lae-Hoon ,  VISSER, Erik ,  ALVES, Rogerio Guedes

IPC: G10L21/0208 ,  G06N3/04 ,  G10L21/0216 ,  G10L15/08

Abstract: A device includes a memory configured to store instructions and one or more processors configured to execute the instructions. The one or more processors are configured to execute the instructions to receive audio data including a first audio frame corresponding to a first output of a first microphone and a second audio frame corresponding to a second output of a second microphone. The one or more processors are also configured to execute the instructions to provide the audio data to a first noisesuppression network and a second noise-suppression network. The first noisesuppression network is configured to generate a first noise-suppressed audio frame and the second noise-suppression network is configured to generate a second noisesuppressed audio frame. The one or more processors are further configured to execute the instructions to provide the noise-suppressed audio frames to an attention-pooling network. The attention-pooling network is configured to generate an output noisesuppressed audio frame.

公开(公告)号：WO2022204630A1

公开(公告)日：2022-09-29

申请号：PCT/US2022/070526

申请日：2022-02-04

Applicant: QUALCOMM INCORPORATED

Inventor： BYUN, Kyungguen ,  ZHANG, Shuhua ,  KIM, Lae-Hoon ,  VISSER, Erik ,  MOON, Sunkuk ,  MONTAZERI, Vahid

IPC: G10L21/02 ,  G10L25/30

Abstract: A device to perform speech enhancement includes one or more processors configured to obtain input spectral data based on an input signal. The input signal represents sound that includes speech. The one or more processors are also configured to process, using a multi-encoder transformer, the input spectral data and context data to generate output spectral data that represents a speech enhanced version of the input signal.

公开(公告)号：WO2022159256A1

公开(公告)日：2022-07-28

申请号：PCT/US2021/072800

申请日：2021-12-08

Applicant: QUALCOMM INCORPORATED

Inventor： BYUN, Kyungguen ,  MOON, Sunkuk ,  ZHANG, Shuhua ,  MONTAZERI, Vahid ,  KIM, Lae-Hoon ,  VISSER, Erik

IPC: G10L13/033 ,  G10L21/007 ,  G10L21/013

Abstract: A device for speech generation includes one or more processors configured to receive one or more control parameters indicating target speech characteristics. The one or more processors are also configured to process, using a multi-encoder, an input representation of speech based on the one or more control parameters to generate encoded data corresponding to an audio signal that represents a version of the speech based on the target speech characteristics.