公开(公告)号：US20220180882A1

公开(公告)日：2022-06-09

申请号：US17682399

申请日：2022-02-28

Applicant: TENCENT TECHNOLOGY(SHENZHEN) COMPANY LIMITED

Inventor： Jun WANG ,  Wing Yip Lam ,  Dan Su ,  Dong Yu

IPC: G10L19/06 ,  G10L25/30 ,  G06N3/08 ,  G06N3/04

Abstract: A method of training an audio separation network is provided. The method includes obtaining a first separation sample set, the first separation sample set including at least two types of audio with dummy labels, obtaining a first sample set by performing interpolation on the first separation sample set based on perturbation data, obtaining a second separation sample set by separating the first sample set using an unsupervised network, determining losses of second separation samples in the second separation sample set, and adjusting network parameters of the unsupervised network based on the losses of the second separation samples, such that a first loss of a first separation result outputted by an adjusted unsupervised network meets a convergence condition.

公开(公告)号：US12223969B2

公开(公告)日：2025-02-11

申请号：US17682399

申请日：2022-02-28

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Jun Wang ,  Wing Yip Lam ,  Dan Su ,  Dong Yu

IPC: G10L19/06 ,  G06N3/045 ,  G06N3/088 ,  G10L25/30

Abstract: A method of training an audio separation network is provided. The method includes obtaining a first separation sample set, the first separation sample set including at least two types of audio with dummy labels, obtaining a first sample set by performing interpolation on the first separation sample set based on perturbation data, obtaining a second separation sample set by separating the first sample set using an unsupervised network, determining losses of second separation samples in the second separation sample set, and adjusting network parameters of the unsupervised network based on the losses of the second separation samples, such that a first loss of a first separation result outputted by an adjusted unsupervised network meets a convergence condition.

公开(公告)号：US12230250B2

公开(公告)日：2025-02-18

申请号：US17671548

申请日：2022-02-14

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Jun Wang ,  Wing Yip Lam

IPC: G10L15/00 ,  G10L15/02 ,  G10L15/06 ,  G10L15/183 ,  G10L15/22

Abstract: A speech recognition method includes: obtaining first sample speech data corresponding to a target user and a first reference speech recognition result corresponding to the first sample speech data; obtaining a pre-update target model; inputting the first sample speech data into the pre-update target model, and performing speech recognition by using a target speech extraction model, a target feature extraction model, and a target speech recognition model, to obtain a first model output result; obtaining a target model loss value corresponding to the target feature extraction model according to the first model output result and the first reference speech recognition result; and updating a model parameter of the target feature extraction model in the pre-update target model according to the target model loss value, to obtain a post-update target model.