Beijing Baidu Netcom Science Technology Co., Ltd

Microsoft Technology Licensing, LLC

Canon Kabushiki Kaisha

Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing University of Civil Engineering and Architecture

Shenzhen Common Technology Ltd

Yulin Li

Junyu Han

Xiameng Qin

Ju Huang

Sheng Zhao

Qunyi Xie

Jie Wang

Lei He

Hongsheng Zhao

Shifeng Pan

Chunling Ma

Haifeng Wang

Errui Ding

Tian Wu

Minghao Liu

Chengquan Zhang

Yu Cheng

Duohao Qin

Haiyan Li

Yanqing Liu

Xiangkai Huang

Qiaoyi Li

Zhaoying Liu

Chaohong Tan

Shengxian Zhu

Jinzhu Li

Guangyu Wu

Yuqi Pan

Zhengxing Liu

Jiayuan Xu

Systems and methods are provided for generating a lightweight, high-quality streaming text-to-speech (TTS) system. For example, some disclosed systems are configured to obtain a first model comprising one or more layers of a convolutional neural network. Each layer of the convolutional neural network is configured to generate a new output from a previous input. The systems also obtain a second model comprising a recurrent neural network. Subsequent to obtaining the first model and the second model, the systems are configured to compile the one or more layers of the convolutional neural network and the recurrent neural network in a parallel architecture to generate a machine learning module such that each model of the machine learning module is configured to receive input simultaneously.

Streaming, lightweight and high-quality device neural TTS system

The present disclosure provides an intelligent low-carbon treatment and reuse system for stormwater and wastewater, including: a bioretention module for collecting stormwater and treating it to obtain treated stormwater; a numerically controlled drainage module for collecting oxidation-reduction potential data and pH data of the treated stormwater and transmitting them to a control module as environmental data, and discharging treated stormwater for a preset time period based on a first control signal sent by the control module; a stormwater and wastewater collection module for storing the discharged treated stormwater and maintaining water storage volume within a preset range; an irrigation module; and the control module. Stable, efficient and low-carbon treatment and reuse of stormwater and wastewater are achieved.

Intelligent low-carbon treatment and reuse system for stormwater and wastewater

Embodiments of the present disclosure provide a method and apparatus for performing a structured extraction on a text, a device and a storage medium. The method may include: performing a text detection on an entity text image to obtain a position and content of a text line of the entity text image; extracting multivariate information of the text line based on the position and the content of the text line; performing a feature fusion on the multivariate information of the text line to obtain a multimodal fusion feature of the text line; performing category and relationship reasoning based on the multimodal fusion feature of the text line to obtain a category and a relationship probability matrix of the text line; and constructing structured information of the entity text image based on the category and the relationship probability matrix of the text line.

Method and apparatus for performing structured extraction on text, device and storage medium

A method, apparatus, device and storage medium for recognizing a bill image may include: performing text detection on a bill image, and determining an attribute information set and a relationship information set of each text box of at least two text boxes in the bill image; determining a type of the text box and an associated text box that has a structural relationship with the text box based on the attribute information set and the relationship information set of the text box; and extracting structured bill data of the bill image, based on the type of the text box and the associated text box that has the structural relationship with the text box.

Method, apparatus, device and storage medium for recognizing bill image

A method for visual question answering, a computer device implementing the method and a medium for storing instructions on performing the method are provided. The method includes: acquiring an input image and an input question; constructing a visual graph based on the input image, wherein the visual graph comprises a first node feature and a first edge feature; constructing a question graph based on the input question, wherein the question graph comprises a second node feature and a second edge feature; performing a multimodal fusion on the visual graph and the question graph to obtain an updated visual graph and an updated question graph; determining a question feature based on the input question; determining a fusion feature based on the updated visual graph, the updated question graph and the question feature; and generating a predicted answer for the input image and the input question.

Method and apparatus for visual question answering, computer device and medium

The present disclosure provides a method for visual question answering, which relates to a field of computer vision and natural language processing. The method includes: acquiring an input image and an input question; constructing a Visual Graph based on the input image, wherein the Visual Graph comprises a Node Feature and an Edge Feature; updating the Node Feature by using the Node Feature and the Edge Feature to obtain an updated Visual Graph; determining a question feature based on the input question; fusing the updated Visual Graph and the question feature to obtain a fused feature; and generating a predicted answer for the input image and the input question based on the fused feature. The present disclosure further provides an apparatus for visual question answering, a computer device and a non-transitory computer-readable storage medium.

Method and device for visual question answering, computer apparatus and medium

Embodiments of the present disclosure provide a method and apparatus for correcting a distorted document image, where the method for correcting a distorted document image includes: obtaining a distorted document image; and inputting the distorted document image into a correction model, and obtaining a corrected image corresponding to the distorted document image; where the correction model is a model obtained by training with a set of image samples as inputs and a corrected image corresponding to each image sample in the set of image samples as an output, and the image samples are distorted. By inputting the distorted document image to be corrected into the correction model, the corrected image corresponding to the distorted document image can be obtained through the correction model, which realizes document image correction end-to-end, improves accuracy of the document image correction, and extends application scenarios of the document image correction.

Method and apparatus for correcting distorted document image

Disclosed are a method, apparatus and electronic device for annotating information of a structured document. A specific implementation is: obtaining a template image of a structured document and at least one piece of annotation information of a field to be filled in the template image, where the annotation information includes attribute value and historical content of the field to be filled, and historical position of the field to be filled in the template image; generating, according to the attribute value of the field to be filled, the historical content of the field to be filled and the historical position of the field to be filled in the template image, target filling information of the field to be filled; obtaining, according to the target filling information of the field to be filled, an image of an annotated structured document.

Method, apparatus and electronic device for annotating information of structured document

Systems are configured for generating spectrogram data characterized by a voice timbre of a target speaker and a prosody style of source speaker by converting a waveform of source speaker data to phonetic posterior gram (PPG) data, extracting additional prosody features from the source speaker data, and generating a spectrogram based on the PPG data and the extracted prosody features. The systems are configured to utilize/train a machine learning model for generating spectrogram data and for training a neural text-to-speech model with the generated spectrogram data.

System and method for cross-speaker style transfer in text-to-speech and training data generation

The present invention provides a unique method, apparatus, system and storage medium for image binarization process, wherein an image to be processed is divided into a plurality of sub-images and an binarization threshold for each of the sub-images is determined based on the gray-levels of the edge pixels detected in respective sub-image. The image processing method of the present invention comprises: calculating a gray-level statistical distribution of pixels of an image, detecting edge pixels in an image based on an edge criterion corresponding to the gray-level statistical distribution, dividing the image into a plurality of sub-images; determining a binarization threshold for each of the sub-images based on the gray-levels of edge pixels detected in the sub-image; and performing binarization process for each of the sub-images based on the binarization threshold of the sub-image.

Image processing method and apparatus using self-adaptive binarization

A method for detecting edges in an image is disclosed along with corresponding apparatus and system for accurately extracting edges in the image. The edge detecting apparatus comprises a reading means, an image gray-level statistical means, an image classification means, a segmenting threshold generating means, an edge criterion determining means, and an image edge extracting means. The present invention realizes a reliable and accurate method for detecting edges in an image so as to extract edges in various file images.

Image processing method, apparatus and system

Growing community of inventors

Beijing, China

Yulin Li