公开(公告)号：US20240331378A1

公开(公告)日：2024-10-03

申请号：US18618134

申请日：2024-03-27

Applicant: Fujitsu Limited

Inventor： Ziqiang SHI ,  Liu LIU ,  Zhongling LIU ,  Rujie LIU

IPC: G06V20/40 ,  G06T7/12 ,  G06T7/13 ,  G06T7/246 ,  G06T7/277 ,  G06V10/26 ,  G06V10/44 ,  G06V10/75

CPC classification number: G06V20/41 ,  G06T7/12 ,  G06T7/13 ,  G06T7/248 ,  G06T7/277 ,  G06V10/26 ,  G06V10/44 ,  G06V10/751 ,  G06V20/49 ,  G06T2207/10016 ,  G06T2207/20132

Abstract: The embodiments of the present disclosure provide an apparatus for identifying items, a method for identifying items and an electronic device. The apparatus includes: a detector configured to detect one or more items in a reference area in one or more image frames in video data; a tracker configured to track an item detected in multiple image frames, wherein multi-hierarchy decision is performed on the item in the multiple image frames by using different time windows; and a classifier configured to identify the item according to a decision result of the tracker. Thereby, even if an item is moved briefly in some scenarios, the item will not be identified as two different items, which can reduce a situation in which the item is identified repeatedly and improve accuracy and robustness of item detection.

公开(公告)号：US20180336438A1

公开(公告)日：2018-11-22

申请号：US15971549

申请日：2018-05-04

Applicant: FUJITSU LIMITED

Inventor： Ziqiang SHI ,  Liu LIU ,  Rujie LIU

IPC: G06K9/62 ,  G06K9/48

CPC classification number: G06K9/6277 ,  G06K9/481 ,  G06K9/6215 ,  G06K9/6256 ,  G06K9/6262 ,  G10L17/00

Abstract: A multi-view vector processing method and a multi-view vector processing device are provided. A multi-view vector x represents an object containing information on at least two non-discrete views. A model of the multi-view vector, where the model includes at least components of: a population mean μ of the multi-view vector, view component of each view of the multi-view vector and noise is established. The population mean μ, parameters of each view component and parameters of the noise , are obtained by using training data of the multi-view vector x. The device includes a processor and a storage medium storing program codes, and the program codes implements the aforementioned method when being executed by the processor.

公开(公告)号：US20180197547A1

公开(公告)日：2018-07-12

申请号：US15866079

申请日：2018-01-09

Applicant: Fujitsu Limited

Inventor： Ziqiang SHI ,  Liu LIU ,  Rujie LIU

IPC: G10L17/18 ,  G10L25/30 ,  G10L17/06 ,  G06F17/17

CPC classification number: G10L17/18 ,  G06F17/17 ,  G10L17/04 ,  G10L17/06 ,  G10L25/30

Abstract: An identity verification method and an identity verification apparatus based on a voiceprint are provided. The identity verification method based on a voiceprint includes: receiving an unknown voice; extracting a voiceprint of the unknown voice using a neural network-based voiceprint extractor which is obtained through pre-training; concatenating the extracted voiceprint with a pre-stored voiceprint to obtain a concatenated voiceprint; and performing judgment on the concatenated voiceprint using a pre-trained classification model, to verify whether the extracted voiceprint and the pre-stored voiceprint are from a same person. With the identity verification method and the identity verification apparatus, a holographic voiceprint of the speaker can be extracted from a short voice segment, such that the verification result is more robust.

公开(公告)号：US20210073591A1

公开(公告)日：2021-03-11

申请号：US17012357

申请日：2020-09-04

Applicant: FUJITSU LIMITED

Inventor： Chaoliang ZHONG ,  Ziqiang SHI ,  Wensheng XIA ,  Jun SUN

IPC: G06K9/62 ,  G06N3/08

Abstract: A robustness estimation method, a data processing method, and an information processing apparatus are provided. The method for estimating robustness a classification model obtained in advance through training based on a training data set, includes: for each training sample in the training data set, determining a target sample in a target data set that has a sample similarity with a respective training sample that is within a predetermined threshold range, and calculating a classification similarity between a classification result of the classification model with respect to the respective training sample and a classification result of the classification model with respect to the determined respective target sample; and determining, based on classification similarities between classification results of respective training samples in the training data set and classification results of corresponding target samples in the target data set, classification robustness of the classification model with respect to the target data set.

公开(公告)号：US20170294191A1

公开(公告)日：2017-10-12

申请号：US15477687

申请日：2017-04-03

Applicant: FUJITSU LIMITED

Inventor： Ziqiang SHI ,  Liu LIU ,  Rujie Liu

IPC: G10L17/02 ,  G10L15/30 ,  G10L17/10 ,  G10L15/22 ,  G10L15/20 ,  G10L17/04

CPC classification number: G10L17/02 ,  G10L15/20 ,  G10L15/22 ,  G10L15/30 ,  G10L17/04 ,  G10L17/10 ,  G10L2015/227

Abstract: The present invention discloses a method for speaker recognition and an apparatus for speaker recognition. The method for speaker recognition comprises: extracting, from a speaker-to-be-recognized corpus, voice characteristics of a speaker to be recognized: obtaining a speaker-to-be-recognized model based on the extracted voice characteristics of the speaker to be recognized, a universal background model UBM reflecting distribution of the voice characteristics in a characteristic space, a gradient universal speaker model GUSM reflecting statistic values of changes of the distribution of the voice characterizes in the characteristic space and a total change matrix reflecting environmental changes; and comparing the speaker-to-be-recognized model with known speaker models, to determine whether or not the speaker to be recognized is one of known speakers.