公开(公告)号：US11361751B2

公开(公告)日：2022-06-14

申请号：US17225376

申请日：2021-04-08

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Liqun Deng ,  Jiansheng Wei ,  Wenhua Sun

IPC: G10L25/63 ,  G10L13/10 ,  G10L13/00 ,  G10L21/00 ,  G10L15/00 ,  G10L13/033 ,  G10L13/047

Abstract: In a speech synthesis method, an emotion intensity feature vector is set for a target synthesis text, an acoustic feature vector corresponding to an emotion intensity is generated based on the emotion intensity feature vector by using an acoustic model, and a speech corresponding to the emotion intensity is synthesized based on the acoustic feature vector. The emotion intensity feature vector is continuously adjustable, and emotion speeches of different intensities can be generated based on values of different emotion intensity feature vectors, so that emotion types of a synthesized speech are more diversified. This application may be applied to a human-computer interaction process in the artificial intelligence (AI) field, to perform intelligent emotion speech synthesis.

公开(公告)号：US20200050897A1

公开(公告)日：2020-02-13

申请号：US16657576

申请日：2019-10-18

Applicant: Huawei Technologies Co., Ltd.

Inventor： Mingjie Dong ,  Kangmin Huang ,  Wenhua Sun

IPC: G06K9/62 ,  G06F17/18 ,  G06K9/00 ,  G06N20/00

Abstract: A sentiment threshold determining method and an artificial intelligence device configured for determining, based on obtained monitoring information, that a sentiment status of a first user is a first sentiment state, obtaining N actions of a second user, determining a first action based on a Q-value table, updating a Q value that corresponds to the first sentiment state and the first action in the Q-value table, determining whether an updated Q value is greater than a preset threshold. Finally, determining the sentiment threshold based on the monitoring information, and when the updated Q value is greater than a preset threshold, updating the sentiment status, or repeating the foregoing steps until the sentiment threshold is determined when the updated Q value is not greater than the preset threshold.

公开(公告)号：US20210287657A1

公开(公告)日：2021-09-16

申请号：US17225376

申请日：2021-04-08

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Liqun Deng ,  Jiansheng Wei ,  Wenhua Sun

IPC: G10L13/10 ,  G10L25/63 ,  G10L13/033 ,  G10L13/047

Abstract: In a speech synthesis method, an emotion intensity feature vector is set for a target synthesis text, an acoustic feature vector corresponding to an emotion intensity is generated based on the emotion intensity feature vector by using an acoustic model, and a speech corresponding to the emotion intensity is synthesized based on the acoustic feature vector. The emotion intensity feature vector is continuously adjustable, and emotion speeches of different intensities can be generated based on values of different emotion intensity feature vectors, so that emotion types of a synthesized speech are more diversified. This application may be applied to a human-computer interaction process in the artificial intelligence (AI) field, to perform intelligent emotion speech synthesis.

公开(公告)号：US11858118B2

公开(公告)日：2024-01-02

申请号：US16457676

申请日：2019-06-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Wenhua Sun ,  Jiali Fu ,  Heng Liao ,  Huimin Zhang

IPC: B25J11/00 ,  G06N20/00 ,  G09B5/06 ,  G10L25/63 ,  G06V40/16

CPC classification number: B25J11/001 ,  G06N20/00 ,  G06V40/176 ,  G09B5/065 ,  G10L25/63

Abstract: Embodiments of the present invention provide a human-machine interaction method, including: detecting and collecting, by a robot, sensing information of a companion object of a target object and emotion information of the target object that is obtained when the target object interacts with the companion object; extracting, by the robot, an emotion feature quantity based on the emotion information, determining, based on the emotion feature quantity, an emotional pattern used by the target object to interact with the companion object, determining, based on the emotional pattern, a degree of interest of the target object in the companion object, extracting behavioral data of the companion object from the sensing information based on the degree of interest, and screening the behavioral data to obtain simulated object data; and simulating, by the robot, the companion object based on the simulated object data.

公开(公告)号：US11511436B2

公开(公告)日：2022-11-29

申请号：US16276576

申请日：2019-02-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Sixiao Yang ,  Heng Liao ,  Maosheng Huang ,  Jiansheng Wei ,  Dawei Huo ,  Wenhua Sun

IPC: G06F3/01 ,  B25J11/00 ,  G06N3/00 ,  G06V40/20 ,  G06N20/00

Abstract: The present invention provides a robot control method, and the method includes: collecting interaction information of a companion target, and obtaining digital person information of a companion person (101), where the interaction information includes interaction information of a sound or an action of the companion target toward the robot, and the digital person information includes a set of digitized information of the companion person; and determining, by using the interaction information and the digital person information, a manner of interacting with the companion target (103); generating, based on the digital person information of the companion person and by using a machine learning algorithm, an interaction content corresponding to the interaction manner (105); and generating a response action toward the companion target based on the interaction manner and the interaction content (107).

公开(公告)号：US11282498B2

公开(公告)日：2022-03-22

申请号：US16944863

申请日：2020-07-31

Applicant: Huawei Technologies Co., Ltd.

Inventor： Liqun Deng ,  Yuezhi Hu ,  Zhanlei Yang ,  Wenhua Sun

IPC: G10L15/22 ,  G10L13/10 ,  G10L13/047

Abstract: A speech synthesis method and a speech synthesis apparatus to synthesize speeches of different emotional intensities in the field of artificial intelligence, where the method includes obtaining a target emotional type and a target emotional intensity parameter that correspond to an input text, determining a corresponding target emotional acoustic model based on the target emotional type and the target emotional intensity parameter, inputting a text feature of the input text into the target emotional acoustic model to obtain an acoustic feature of the input text, and synthesizing a target emotional speech based on the acoustic feature of the input text.