Abstract: An acoustic model training method, a speech recognition method, an apparatus, a device and a medium. The acoustic model training method comprises: performing feature extraction on a training speech signal to obtain an audio feature sequence; training the audio feature sequence by a phoneme mixed Gaussian Model-Hidden Markov Model to obtain a phoneme feature sequence; and training the phoneme feature sequence by a Deep Neural Net-Hidden Markov Model-sequence training model to obtain a target acoustic model. The acoustic model training method can effectively save time required for an acoustic model training, improve the training efficiency, and ensure the recognition efficiency.

Abstract: A method, a device, a terminal and a storage medium for acquiring slant value of slant image are provided. The method for acquiring slant value of a slant image comprises: analyzing the slant image and acquiring coordinate information of a plurality of boundary lines of the slant image; acquiring first slant values of the boundary lines by analysing and calculating the coordinate information; acquiring a correction value; calculating difference values between the first slant values and the correction value respectively; determining the first slant value corresponding to the minimum difference value as the slant value of the slant image. The technical solution of the present disclosure can uniquely determine a slant value of slant image.

Abstract: Disclosed is a method for identifying a user interest, including: obtaining training samples and test samples, the training samples being obtained by manually labeling after the corresponding topic models have been trained based on text data; extracting characteristics of the training samples and of the test samples, and computing optimal model parameters of a logistic regression model by an iterative algorithm based on the characteristics of the training samples; evaluating the logistic regression model based on the characteristics of the test samples and an area AUC under an ROC curve to train and obtain a first theme classifier; determining a theme to which the text data belongs using the first theme classifier, computing a score of the theme to which the text data belongs based on the logistic regression model, and computing a confidence score of the user being interested in the theme according to a second preset algorithm.

Abstract: An electronic device for identity verification includes a memory and a processor; the system of identity verification is stored in the memory, and executed by the processor to implement: after receiving current voice data of a target user, carrying out framing processing on the current voice data according to preset framing parameters to obtain multiple voice frames; extracting preset types of acoustic features in all the voice frames by using a predetermined filter, and generating multiple observed feature units corresponding to the current voice data according to the extracted acoustic features; pairwise coupling all the observed feature units with pre-stored observed feature units respectively to obtain multiple groups of coupled observed feature units; inputting the multiple groups of coupled observed feature units into a preset type of identity verification model generated by pre-training to carry out the identity verification on the target user.

Abstract: Disclosed are a car damage picture angle correction method, an electronic device, and a readable storage medium. The method includes: after receiving a car damage picture to be classified and identified, identifying a rotation category corresponding to the received car damage picture by using a pre-trained picture rotation category identification model; determining a rotation control parameter corresponding to the identified rotation category according to a pre-determined mapping relation between rotation categories and rotation control parameters, the rotation control parameter including a rotation angle and a rotation direction; and rotating the received car damage picture according to the determined rotation control parameter, so as to generate an angle-normal car damage picture.

Abstract: Disclosed are a speech recognition method, apparatus, computer device and storage medium. The method includes: performing a framing and an acoustic feature extraction of a speech-information-to-be-tested according to a default rule to obtain a frame-level speech feature sequence; dividing the frame-level speech feature sequence into n blocks sequentially; inputting all blocks into a preset bidirectional LSTM-RNN model parallelly to obtain an output result of the corresponding neuron in an output layer of the preset bidirectional LSTM-RNN model corresponding to the forward recognition result and backward recognition result of each block to obtain a speech recognition result of the speech-information-to-be-tested. The present application can improve the speech recognition effect significantly and reduce the time delay of the speech decoding effectively.

Abstract: The preset application is applied to the field of information processing technologies, and a method and a device for generating a medical report are provided. The method includes: receiving a medical image to be recognized; importing the medical image into a preset visual geometry group VGG neural network to acquire a visual feature vector and a keyword sequence of the medical image; importing the visual feature vector and the keyword sequence into a preset diagnostic item recognition model to determine diagnostic items corresponding to the medical image; constructing a paragraph for describing each of the diagnostic items respectively based on a diagnostic item extension model; generating a medical report for the medical image based on the paragraph, the keyword sequence and the diagnostic items.

Abstract: Disclosed is a method for identifying a user interest, including: obtaining training samples and test samples, the training samples being obtained by manually labeling after the corresponding topic models have been trained based on text data; extracting characteristics of the training samples and of the test samples, and computing optimal model parameters of a logistic regression model by an iterative algorithm based on the characteristics of the training samples; evaluating the logistic regression model based on the characteristics of the test samples and an area AUC under an ROC curve to train and obtain a first theme classifier; determining a theme to which the text data belongs using the first theme classifier, computing a score of the theme to which the text data belongs based on the logistic regression model, and computing a confidence score of the user being interested in the theme according to a second preset algorithm.

Abstract: A method for data distribution includes: receiving a request for data distribution sent from a terminal; searching for raw association network data, wherein the raw association network data includes a set of nodes and a set of edges existing between the nodes; searching for a corresponding user grade according to a user identifier carried in the request for data distribution, and determining a privacy budget parameter corresponding to the user grade; determining the distributing probability distribution corresponding to the raw association network data to be distributed according to a pre-constructed Laplace Model and the determined privacy budget parameter; selecting an arbitrary value within the distributing probability distribution as a distributing probability for each network edge of the set of edges, generating a random number between 0 to 1 for each network edge, comparing the random number to the distributing probability, and distributing the corresponding network edge when the distributing probabilit

Abstract: The disclosure relates to a data source-based service customizing device, method and system, and a computer readable storage medium. The data source-based service customizing device includes: a memory, a processor and the data source-based service customizing system stored on the memory and operated on the processor.

Abstract: A method and apparatus for establishing a voiceprint model, a computer device, and a storage medium are described herein. The method includes: collecting speech acoustic features in a speech signal to form a plurality of cluster structures; calculating an average value and a standard deviation of the plurality of cluster structures and then performing coordinate transformation and activation function calculation to obtain a feature vector; and obtaining a voiceprint model based on the feature vector.

Abstract: A method and apparatus for training a semantic segmentation model, a computer device, and a storage medium are described herein. The method includes: constructing a training sample set; inputting the training sample set into a deep network model for training; inputting the training sample set into a weight transfer function for training to obtain a bounding box prediction mask parameter; and constructing a semantic segmentation model.

Abstract: The present application provides a method and device for vehicle identification, the method comprises: obtaining a first vehicle image and a second vehicle image, wherein the first vehicle image comprises a first vehicle, and the second vehicle image comprises a second vehicle; extracting a first color feature and a first vehicle type feature of the first vehicle, and extracting a second color feature and a second vehicle type feature of the second vehicle based on a convolutional neural network model; combining the first color feature and the first vehicle type feature into a first vehicle feature, and combining the second color feature and the second vehicle type feature into a second vehicle feature; calculating a similarity parameter between the first vehicle feature and the second vehicle feature; and determining whether the first vehicle is the same one as the second vehicle according to the similarity parameter.

Abstract: A speaker acquires audio data and performing processing. Audio features of the audio data are extracted. The audio features are inputted into a preset neural network model for training to obtain vector features. A first similarity value between a first vector feature and a second vector feature of a first speaker and a second similarity value between the first vector feature and a third vector feature of a second speaker are calculated. A loss function value is calculated and when is less than or equal to a preset loss function threshold, a training process of the speaker separation model is ended and parameters are updated. A two-speaker separation method, a terminal, and a storage medium are disclosed. Feature extraction capabilities of the model are enhanced, and accuracy of separation between speakers is improved, especially in long meetings and conversations.

Abstract: The present disclosure publishes a vulnerable plaque identification method. The method includes: receiving an angiocarpy image sent by a terminal device; transforming the angiocarpy image in an original Cartesian coordinate system into a polar coordinate system to form a polarization image; constructing a faster RCNN architecture and accomplishing a training; inputting the polarization image into the faster RCNN architecture accomplished the training to identify the polarization image, and outputting the image with the marked vulnerable plaques; feed backing the image with the marked vulnerable plaques to the terminal device. The present disclosure also publishes an application server and a computer readable medium. The vulnerable plaque identification method, the application server, and the computer readable medium can quickly and correctly conform the position of the vulnerable plaque.

Abstract: A method and system of detecting image tampering, an electronic device and a storage medium. The method includes: A. carrying out block segmentation on a to-be-detected image to segment the to-be-detected image into a plurality of image small fragments, and extracting initial tampering detection features from all the image small fragments; B. encoding the extracted initial tampering detection features with a predetermined encoder to generate complicated tampering features, and determining a tampering detection result corresponding to the to-be-detected image according to the generated complicated tampering features, wherein the tampering detection result includes an image-tampered result and an image-not-tampered result. The disclosure realizes accurate detection for different types and formats of image tampering.

Abstract: Provided is a method for training a topic classifier: obtaining a training sample and a test sample, wherein the training sample is obtained by manually labeling after a corresponding topic model having been trained based on text data; extracting features of the training sample and of the test sample respectively using a preset algorithm, computing optimal model parameters of a logistic regression model by an iterative algorithm based on the features of the training sample, to train and get a logistic regression model containing the optimal model parameters; and drawing a ROC curve based on the features of the test sample and the logistic regression model containing the optimal model parameters, evaluating the logistic regression model containing the optimal model parameters based on the area AUC under the ROC curve, to train and get a first topic classifier. It further discloses a device and computer-readable storage medium thereof.

Abstract: The present disclosure provides a video compressed sensing reconstruction method, including: step B, after receiving to-be-reconstructed compressed video frames, extracting frame fragments of the compressed video frames according to a predetermined extraction rule; step C, inputting the frame fragments into an input layer of a pre-trained video frame reconstruction model, performing feature abstraction to the frame fragments through multiple hidden layers of the video frame reconstruction model, and building a nonlinear mapping between each frame fragment and a corresponding frame fragment block; and step D, reconstructing the input frame fragments to frame fragment blocks by the hidden layers according to the nonlinear mapping, and outputting the frame fragment blocks by an output layer of the video frame reconstruction model, and generating a reconstructed video based on the reconstructed frame fragment blocks. The present disclosure can render and reconstruct video frames quickly with a high quality.

Abstract: The present invention provides a voiceprint recognition method, a device, a storage medium and a background server. The voiceprint recognition method comprises: collecting, by a client, and sending a voice recognition request to the background server, the voice recognition request comprises the user ID and the test voice; receiving the voice recognition request, and determining the voice recognition request to be processed with a message queue and an asynchronous mechanism; acquiring a target voiceprint feature which corresponds to the user ID of the voice recognition request to be processed, and acquiring a test voiceprint feature which corresponds to the test voice of the voice recognition request to be processed; judging whether the target voiceprint feature and the test voiceprint feature correspond to the same user, and outputting the result of the judging to the client; and receiving and displaying, by the client, the result of the judging.

Abstract: The present invention discloses a method, a system, an electronic device, and a medium for classifying license plates based on deep learning that are applied to an electronic device. The method includes: acquiring at least one photograph sent by a terminal device; preprocessing the acquired photograph such that the preprocessed photograph matches a plurality of input parameters of a pre-trained recognition model; and inputting the preprocessed photograph to the pre-trained recognition model to recognize corresponding vehicle use information of the photograph, and sending the corresponding vehicle use information of the photograph to the terminal device. Thus, with this disclosure, the use of a vehicle in a photograph can be automatically and accurately recognized and further the photographs can be accurately classified, thereby improving the accuracy as well as the efficiency.