公开(公告)号：US11900959B2

公开(公告)日：2024-02-13

申请号：US17451061

申请日：2021-10-15

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yang Zhang ,  Oxana Verkholyak ,  Alexey Karpov ,  Li Qian

IPC: G10L25/63 ,  G10L25/30 ,  G10L19/038 ,  G10L15/04 ,  G10L15/16

CPC classification number: G10L25/63 ,  G10L15/16 ,  G10L15/04 ,  G10L19/038 ,  G10L25/30

Abstract: A plurality of pieces of emotional state information corresponding to a plurality of speech frames in a current utterance are obtained based on a first neural network model; statistical operation is performed on the plurality of pieces of emotional state information, to obtain a statistical result, and then the emotional state information corresponding to the current utterance is obtained based on a second neural network device, the statistical result corresponding to the current utterance, and statistical results corresponding to a plurality of utterances before the current utterance.

公开(公告)号：US20220036916A1

公开(公告)日：2022-02-03

申请号：US17451061

申请日：2021-10-15

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yang Zhang ,  Oxana Verkholyak ,  Alexey Karpov ,  Li Qian

IPC: G10L25/63 ,  G10L15/16

Abstract: A plurality of pieces of emotional state information corresponding to a plurality of speech frames in a current utterance are obtained based on a first neural network model; statistical operation is performed on the plurality of pieces of emotional state information, to obtain a statistical result, and then the emotional state information corresponding to the current utterance is obtained based on a second neural network device, the statistical result corresponding to the current utterance, and statistical results corresponding to a plurality of utterances before the current utterance.