公开(公告)号：US20190115039A1

公开(公告)日：2019-04-18

申请号：US16158993

申请日：2018-10-12

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanbin DU ,  Zhihai ZHU ,  Meng LIAO ,  Weijun ZHENG ,  Weibin CHEN ,  Guangzhao BAO ,  Cunshou QIU

IPC: G10L21/02 ,  H04R1/22 ,  H04R3/00 ,  G10L21/0216

Abstract: A speech processing method and a terminal are provided. The method includes: receiving signals from a plurality of microphones; performing, by using a same sampling rate, analog-to-digital conversion on the plurality of paths of signals received from the plurality of microphones, to obtain a plurality of paths of time-domain digital signals; performing time-to-frequency-domain conversion on the plurality of paths of time-domain digital signals to obtain a plurality of paths of frequency-domain signals; and determining a signal type of the primary frequency-domain signal based on at least one of a sound pressure difference between the primary frequency-domain signal and each of N paths of secondary frequency-domain signals in the M paths of secondary frequency-domain signals, a phase difference between the primary frequency-domain signal and each of the N paths of secondary frequency-domain signals, and a frequency distribution characteristic of the primary frequency-domain signal.

公开(公告)号：US20220277752A1

公开(公告)日：2022-09-01

申请号：US17628115

申请日：2020-07-15

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Long ZHANG ,  Cunshou QIU ,  Yanxin WEN ,  Guangzhao BAO ,  Haibo MIAO

IPC: G10L17/22 ,  G10L17/06 ,  G10L17/04 ,  H04N5/232 ,  G06V20/50

Abstract: Embodiments of this application provide a voice interaction method. In the interaction method an electronic device receives a first voice signal, where the first voice signal includes a wake-up word. The electronic device switches from a standby state to a working state based on the wake-up word, and the electronic device outputs a second voice signal in a first tone, where the second voice signal is used to respond to the first voice signal. The first tone is obtained based on personal information associated with a voiceprint feature of the first voice signal, and the personal information includes personal information corresponding to a first registered voice signal. In a plurality of registered voice signals, a voiceprint feature of the first registered voice signal is most similar to the voiceprint feature of the first voice signal.

公开(公告)号：US20210319782A1

公开(公告)日：2021-10-14

申请号：US17270271

申请日：2018-10-12

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Shuqiang GONG ,  Jianyong GONG ,  Cunshou QIU

IPC: G10L15/08 ,  G06K9/00 ,  G06F21/32 ,  H04R5/033

Abstract: A wearable device collects a fingerprint pattern input by a user and speech input by the user. The wearable device sends the fingerprint pattern to an electronic device, to enable the electronic device to perform authentication on the fingerprint pattern input by a user. The wearable device sends the speech to the electronic device, and, upon a determination that the authentication succeeds, the electronic device is enabled to execute a function corresponding to the speech.

公开(公告)号：US20180156887A1

公开(公告)日：2018-06-07

申请号：US15557760

申请日：2016-03-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Cunshou QIU ,  Hua MA ,  Qing CHANG ,  Bo HAN

IPC: G01S3/802 ,  H04R1/32 ,  H04R1/40

CPC classification number: G01S3/802 ,  G01S5/18 ,  H04R1/326 ,  H04R1/406 ,  H04R3/005 ,  H04R2430/20 ,  H04R2499/11 ,  H04R2499/15

Abstract: A directional recording method includes: generating an initial sound pickup beam by using a beam forming algorithm, where the initial sound pickup beam points towards the target acoustic source; recording an initial pointing direction of the initial sound pickup beam; and detecting that a direction towards which the recording device faces changes, and adjusting, according to the change of the direction towards which the recording device faces, the initial sound pickup beam to obtain a target sound pickup beam, where the target sound pickup beam points towards the target acoustic source. Compared with the prior art, according to the directional recording method and apparatus, and the recording device provided in the embodiments of the present invention, a pointing direction of a sound pickup beam can be adjusted according to a change of a direction towards which the recording device faces.