Emc IP Holding Company LLC

Dell Products Inc.

Wenbin Yang

Zhen Jia

Jiacheng Ni

Zijia Wang

Jinpeng Liu

Sanping Li

Mengze Liao

Jin Li

WuiChak Wong

Embodiments of the present disclosure relate to a method, a device, and a computer program product for text to speech. The method includes encoding a reference waveform of a first speaker to obtain an encoded style feature separated from a second speaker. The method further includes transferring the encoded style feature to a spectrogram obtained by encoding an input text, to obtain a style transferred spectrogram. The method further includes converting the style transferred spectrogram into a time-domain speech waveform. According to the method for text to speech in the present disclosure, a comparative learning framework can also flexibly and effectively synthesize speech with a style of a target speaker, thus realizing lightweight speech style transfer, making it possible to learn high-quality and recognizable features of speech synthesis, and realizing effective speaker feature learning. In addition, the model will be beneficial to other downstream tasks.

Method, device, and computer program product for text to speech

Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for analyzing samples. The method includes acquiring a set of feature representations associated with a set of samples. The set of samples illustratively have classification information for indicating classifications of the set of samples. The method further includes adjusting the set of feature representations so that distances between feature representations of samples corresponding to the same classification are less than a first distance threshold. The method further includes training a classification model based on the adjusted set of feature representations and the classification information. The classification model is illustratively configured to receive an input sample and determine a classification of the input sample. In this manner, a relatively accurate classification model can be trained using a small number of samples, thereby reducing computation time and required computation capacity.

Method, electronic device, and computer program product for analyzing samples

Embodiments disclosed herein include a method, an electronic device, and a computer program product for data processing. The method includes determining a first set of feature vectors representing samples in a data set. The method also includes generating a second set of feature vectors by performing a first transformation on the first set of feature vectors, wherein distribution skewness of the second set of feature vectors in a feature space is smaller than that of the first set of feature vectors. The method also includes generating a third set of feature vectors by performing a second transformation on the second set of feature vectors, wherein the third set of feature vectors and the second set of feature vectors have different distances between vectors. The method also includes selecting target samples as representatives from the samples based on a distribution of the third set of feature vectors in the feature space.

Method, electronic device, and computer program product for data processing

Embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a medium for detecting an abnormality in a network. The method for detecting an abnormality in a network includes acquiring a reference tensor and a target tensor representing traffic in the network, the reference tensor and the target tensor having at least dimensions of source, destination, and time of the traffic. The method further includes determining a target core tensor of the target tensor based on a reference decomposition factor of the reference tensor related to the dimensions of source and destination of the traffic. The method further includes determining that there is an abnormality in the network if a difference between the target core tensor of the target tensor and a reference core tensor of the reference tensor is greater than a preset value.

Method, apparatus, electronic device, and medium for detecting abnormality in network

Embodiments relate to a method, an electronic device, and a program product for training an encoder and processing data. The method includes inputting sample point cloud data for an object to an encoder to obtain encoded data for the object, and determining, by transforming the encoded data, a plurality of invariant portions for the object and a plurality of variable portions for the object, an invariant portion in the plurality of invariant portions indicating an invariant feature of the object and a variable portion in the plurality of variable portions indicating a variable feature of the object. The method further includes determining, based on the plurality of invariant portions and the plurality of variable portions, a similarity loss and a spatial loss for the sample point cloud data, and adjusting, based on the similarity loss and the spatial loss, a parameter of the encoder to obtain a trained encoder.

Method, electronic device, and program product for training encoder and processing data

Embodiments of the present disclosure relate to a method for distributing content, an electronic device, and a computer program product. The method for distributing content provided in embodiments of the present disclosure includes acquiring neighboring topological information of a plurality of nodes in a collaborative storage network, the plurality of nodes being used for collaboratively storing a plurality of contents requested by a client, the neighboring topological information at least indicating a one-hop relationship between directly connected one-hop node pairs among the plurality of nodes and a two-hop relationship between two-hop node pairs connected via an intermediate node among the plurality of nodes; determining a potential cost of transmitting a plurality of to-be-distributed contents among the plurality of nodes based on the neighboring topological information; and distributing a target content among the plurality of contents to a node among the plurality of nodes based on the potential cost.

Method for distributing content, electronic device, and computer program product

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for training a data classification model. The method includes generating a first training rule based on probabilities of classifying a plurality of sample data into corresponding classes by a data classification model. The method also includes generating a second training rule based on relevances of the plurality of sample data to the corresponding classes. In addition, the method also includes training the data classification model using the first training rule and the second training rule. With this method, a data classification model is trained, so that the data classification accuracy of the data classification model and the robustness to noise can be improved.

Method, electronic device, and computer program product for training data classification model

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for data augmentation. The method includes: generating a group of candidate images based on a target image by using a thermodynamic genetic algorithm (TDGA) model, the TDGA model being configured to apply one or more operations of a set of predetermined image processing operations during each evolution process; and determining multiple augmented images from the group of candidate images based on free energy of the group of candidate images, the multiple augmented images being determined as belonging to the same classification with the target image. In this way, data augmentation can be efficiently implemented by a thermodynamic genetic algorithm.

Method, device, and computer program product for data augmentation

A method for graph data processing comprises obtaining graph data which includes a plurality of nodes and data corresponding to the plurality of nodes respectively; classifying the plurality of nodes into at least one category of a plurality of categories, wherein the plurality of categories are associated with a plurality of node relationship patterns; determining, from a plurality of candidate parameter value sets of a graph convolutional network (GCN) model, parameter value subsets respectively matching at least one category, wherein the plurality of candidate parameter value sets are determined by training the GCN model respectively for the plurality of node relationship patterns; and using the parameter value subsets respectively matching the at least one category to respectively perform a graph convolution operation in the GCN model on data corresponding to the nodes classified into the at least one category to obtain a processing result for the graph data.

Graph data processing method, device, and computer program product

A method for determining a model compression rate comprises determining a near-zero importance value subset from an importance value set associated with a machine learning model, a corresponding importance value in the importance value set indicating an importance degree of a corresponding input of a processing layer of the machine learning model, importance values in the near-zero importance value subset being closer to zero than other importance values in the importance value set; determining a target importance value from the near-zero importance value subset, the target importance value corresponding to a turning point of a magnitude of the importance values in the near-zero importance value subset; determining a proportion of importance values less than the target importance value in the importance value set in the importance value set; and determining the compression rate for the machine learning model based on the determined proportion.

Method, device, and program product for determining model compression rate

Embodiments include a method, an electronic device, and a computer program product for storage management. According to one embodiment of the present disclosure, a method for storage management includes: determining at a kernel of a storage server whether a first system call related to a target file is initiated by a thread executed in the storage server, wherein the target file is a file targeted by an accessing operation executed by a client terminal with respect to a storage device; determining a first connection and a second connection that are associated with the target file if the first system call is initiated, wherein the first connection is a connection between the client terminal and the storage server, and the second connection is a connection between the storage server and the storage device; and causing the client terminal to access the target file via the first connection and the second connection.

Growing community of inventors

Shanghai, China

Wenbin Yang