-
公开(公告)号：US20230197096A1
公开(公告)日：2023-06-22
申请号：US17812784
申请日：2022-07-15
Inventor： Wenkai ZHANG , Ce ZHANG , Zheng LI , Lei JIA
IPC: G10L21/0224 , G10L15/22 , G10L25/30 , G10L15/06
CPC classification number: G10L21/0224 , G10L15/22 , G10L15/063 , G10L25/30 , G10L2015/223 , G10L2021/02082
Abstract: Provided are an audio signal processing method, a training method, an apparatus and a storage medium, relating to the field of data processing, in particular to, the field of voice. The audio signal processing method includes: eliminating at least part of a linear echo signal from a mixed voice signal, to obtain an intermediate processing signal, where the mixed voice signal is obtained by mixing a target voice signal with an echo signal, and the echo signal is generated in an environment where the target voice signal is located and includes the linear echo signal and a nonlinear echo signal; and removing the nonlinear echo signal and a residual part of the linear echo signal from the intermediate processing signal, by using a target full convolution neural network model, to obtain an approximate target voice signal, the target full convolution neural network model including at least two convolution layers.
-
公开(公告)号：US20230196716A1
公开(公告)日：2023-06-22
申请号：US18173689
申请日：2023-02-23
Inventor： Yuan FENG , Zhun SUN , Honghui ZHENG , Ying XIN , Bin ZHANG , Chao LI , Yunhao WANG , Shumin HAN
IPC: G06V10/44 , G06V10/774 , G06V10/764
CPC classification number: G06V10/443 , G06V10/774 , G06V10/764
Abstract: A method for training a multi-target image-text matching model and an image-text retrieval method are provided. The method for training the multi-target image-text matching model includes: obtaining a plurality of training samples that include sample pairs each including a sample image and a sample text, the sample image including a plurality of targets; obtaining, for each of the plurality of training samples, a heat map corresponding to the sample text in the training sample, the heat map representing a region of the target in the sample image that corresponds to the sample text; and training an image-text matching model based on a plurality of the sample texts and corresponding heat maps to obtain the multi-target image-text matching model.
-
413.发明公开公开(公告)号：US20230195998A1
公开(公告)日：2023-06-22
申请号：US17952556
申请日：2022-09-26
Inventor： Yunze GAO , Xiaoping WANG , Penghao RAO , Fenfen SHENG , Mingxin LIANG
IPC: G06F40/129 , G06F40/123 , G06N5/02
CPC classification number: G06F40/129 , G06F40/123 , G06N5/022
Abstract: Disclosed are a sample generation method, a model training method, a trajectory recognition method, a device, and a medium. The method is: determining a code result of a training Chinese character according to a preset code library, where the preset code library is generated based on code characters in a five-stroke code corpus; taking the code result as a training label of the training Chinese character; and generating a training sample according to both a writing trajectory and the training label of the training Chinese character. The amount of information carried in the training sample is enriched.
-
公开(公告)号：US20230195940A1
公开(公告)日：2023-06-22
申请号：US18082356
申请日：2022-12-15
Inventor： Bo Jing
IPC: G06F21/64
CPC classification number: G06F21/64
Abstract: Provided are a blockchain-based data processing method and apparatus, a device, and a storage medium, which relate to the field of blockchain technology and can be used for cloud computing and cloud services. The specific implementation is: in response to a data usage request initiated by a data user, acquiring a signature result from an entrusted signer associated with to-be-used data after the entrusted signer audits the data user; calling a lease smart contract according to the data usage request to determine a signature verification key of the entrusted signer associated with the to-be-used data; performing verification on the signature result according to the signature verification key; and in a case where the verification passes, feeding back the to-be-used data to the data user. Therefore, the usage security of data can be improved.
-
公开(公告)号：US20230195849A1
公开(公告)日：2023-06-22
申请号：US18169806
申请日：2023-02-15
Inventor： Shuo LI , Hanchenxi XU , Juyan ZHANG , Hongda YUE , Haiyang XU
Abstract: A data processing method is provided. The method includes: obtaining a sample data set for modeling; selecting a first sample data from the sample data set; generating, in response to determining that a similarity between a first semantic vector corresponding to a first feature dimension and a second semantic vector corresponding, to a second feature dimension meets a preset condition, a second sample data based on the first sample data; and adding the second sample data to the sample data set.
-
Patent Agency Ranking
416.发明授权公开(公告)号：US11681444B2
公开(公告)日：2023-06-20
申请号：US17020967
申请日：2020-09-15
IPC: G06F3/06
CPC classification number: G06F3/062 , G06F3/0643 , G06F3/0644 , G06F3/0676
Abstract: The present application discloses a magnetic disk management method, an apparatus and an electronic device by providing an engine layer including a plurality of space files and an encapsulation layer including a file directory tree of a space file structure; where the engine layer responds to a data management operation performed for a target space file of the file directory tree output by the engine layer, and a target magnetic disk space corresponding to the target space files is determined through the address association list of the encapsulation layer, and data management is performed on the data in the target magnetic disk space. Thereby, different data can be isolated by different space files when entering through the engine layer, which ensures that security issues such as leakage of the data in the magnetic disk will not occur.
-
公开(公告)号：US20230186943A1
公开(公告)日：2023-06-15
申请号：US17893895
申请日：2022-08-23
Inventor： Guochang ZHANG , Libiao YU , Jianqiang WEI
CPC classification number: G10L25/78 , G10L25/93 , G10L2025/937
Abstract: Provided are a voice activity detection method and apparatus, an electronic device and a storage medium, which relate to the technical field of voice processing, for example, to the technical field of artificial intelligence and deep learning. The specific implementation solution is described below. A first audio signal is acquired, and a frequency domain feature of the first audio signal is extracted; and the frequency domain feature of the first audio signal is input into a voice activity detection model, and a voice presence detection result output by the voice activity detection model is obtained, where the voice activity detection model is configured to detect whether voice is present in the first audio signal.
-
418.发明公开公开(公告)号：US20230186933A1
公开(公告)日：2023-06-15
申请号：US18077307
申请日：2022-12-08
Inventor： Chunliang WANG , Jianqiang WEI , Guochang ZHANG , Libiao YU
IPC: G10L21/0216 , G10L25/18
CPC classification number: G10L21/0216 , G10L25/18
Abstract: Provided are a voice noise reduction method, an electronic device, and a non-transitory computer-readable storage medium. The specific implementation scheme includes determining a to-be-denoised voice spectrum of a to-be-denoised voice signal; performing feature extraction on the to-be-denoised voice spectrum to obtain a local voice spectral feature of the to-be-denoised voice spectrum; determining a global voice spectral feature of the to-be-denoised voice spectrum according to the local voice spectral feature of the to-be-denoised voice spectrum; and determining a masking matrix of an original voice signal in the to-be-denoised voice signal according to the local voice spectral feature and the global voice spectral feature, and determining the original voice signal according to the to-be-denoised voice spectrum and the masking matrix.
-
公开(公告)号：US20230186930A1
公开(公告)日：2023-06-15
申请号：US17890638
申请日：2022-08-18
Inventor： Guangzheng LI , Guochang ZHANG , Libiao YU , Jianqiang WEI
IPC: G10L21/0208 , G10L25/30
CPC classification number: G10L21/0208 , G10L25/30
Abstract: A speech enhancement method includes steps as follows. Subband decomposition processing is performed on at least two paths of target speech to obtain amplitude spectrums and phase spectrums of the at least two paths of target speech, where the at least two paths of target speech include: target mixed speech and target interference speech; a prediction probability of the target mixed speech including target clean speech in a feature domain is determined according to the amplitude spectrums of the at least two paths of target speech; and subband synthesis processing is performed according to the prediction probability and the amplitude spectrums and the phase spectrums of the at least two paths of target speech to obtain the target clean speech in the target mixed speech.
-
公开(公告)号：US20230186137A1
公开(公告)日：2023-06-15
申请号：US18164334
申请日：2023-02-03
Inventor： Xin WANG , Lijing JIN , Zhan YU , Chenghong ZHU , Xuanqiang ZHAO
Abstract: The present disclosure provides a quantum circuit processing method and a quantum circuit processing device on a quantum chip, and an electronic device, and it relates to the field of quantum computing technology, in particular to the field of quantum circuit technology. The method includes: obtaining a first swap fidelity for measuring connectivity of the quantum chip, the first swap fidelity being determined in accordance with first information, the first information being used to represent a topological structure of the quantum chip, the topological structure indicating that the quantum chip includes at least two physical quantum bits, the first swap fidelity being used to represent an average state maintenance level of logic quantum bits obtained through analog exchanging quantum states of any two of the physical quantum bits; and performing quantum circuit processing on the quantum chip in accordance with the first swap fidelity.
-
-
-
-
-
-
-
-
-
Search Results
1522
records
(took 0.041 seconds)
