Microsoft Technology Licensing, LLC

Petrochina Company Limited

National Institute of Biological Sciences, Beijing

Beijing Idriverplus Technology Co.

Beijing Idriverplus Information Technology Co., Ltd.

Bo Yan

Pei Zhao

Kaisheng N Yao

Max Leung

Cheng Xu

Xiao Wang

Yu Shi

Mei-Yuh Hwang

Fang Zhang

Jian Luan

Xiaofei Li

Dezhao Zhang

Shuhao Huo

Malone Ma

Lei Liu

Xiaodong Wang

Lei He

Fileno A Alleva

Zhiyuan Zhang

Sheng Zhao

Yiu-Ming Leung

Shaoqiang Huang

Huayi Wang

Jianguang Han

Huaqing Liu

Guangmin Hu

Zhong Hong

Zhi Huang

Weiye Cao

Changkuan Ni

Runlin He

Haichao Jiao

Qilin Chen

Zhe Geng

Xingmiao Yao

Shibin Zhu

Disclosed are a preprocessing method and device for distance transformation. The method includes: acquiring a first grid map; calculating a second parameter of a vehicle model; calculating a precision of a second grid map according to the second parameter of the vehicle model and a precision of the first grid map; calculating the numbers of rows and columns of the second grid map according to information on the first grid map, the precision of the second grid map and the second parameter of the vehicle model; determining for each cell of the second grid map a state value according to the numbers of obstacle cells within said each cell; and determining in the first grid map at least one cell requiring no processing, according to the state value. Therefore, during the distance transformation, the processing speed for determining the distance value of each cell is increased.

Preprocessing method and device for distance transformation

An example intent-recognition system comprises a processor and memory storing instructions. The instructions cause the processor to receive speech input comprising spoken words. The instructions cause the processor to generate text results based on the speech input and generate acoustic feature annotations based on the speech input. The instructions also cause the processor to apply an intent model to the text result and the acoustic feature annotations to recognize an intent based on the speech input. An example system for adapting an emotional text-to-speech model comprises a processor and memory. The memory stores instructions that cause the processor to receive training examples comprising speech input and receive labelling data comprising emotion information associated with the speech input. The instructions also cause the processor to extract audio signal vectors from the training examples and generate an emotion-adapted voice font model based on the audio signal vectors and the labelling data.

Intent recognition and emotional text-to-speech learning

The invention provides compounds that inhibit human MLKL, and pharmaceutically acceptable salts, hydrates and stereoisomers thereof. The compounds are employed in pharmaceutical compositions, and methods of making and use, including treating a person in need thereof with an effective amount of the compound or composition.

MLKL inhibitors

Disclosed is zero point compensation method and device for EPS. The method includes: acquiring a value of lateral distance when a vehicle travels along an ideal path and obtaining a smoothed lateral distance value, for each control cycle; calculating a longitudinal movement distance value of the vehicle for each control cycle; performing linear fitting to obtain a linear relationship between the longitudinal movement distance value and the smoothed lateral distance value; calculating a zero point compensation angle for the EPS based on a first parameter in the linear relationship and a preset steering wheel transmission ratio, and compensating a steering control angle; and determining that the zero point compensation angle passes verification when a minimum residual error is less than a preset acceptable deviation. In this way, the time required for calibration can be reduced, and the accuracy and effectiveness of the control algorithm can be improved.

Zero point compensation method and device for electric power steering

The present disclosure discloses a method for identifying a boundary of a sedimentary facies, a computer device and a computer readable storage medium. The method comprises: acquiring a preliminary marked result of the sedimentary facies in a seismic attribute map; acquiring a color-based K-means classification result of the seismic attribute map by using a maximal between-cluster variance and a K-means clustering; acquiring a super-pixel classification result of the seismic attribute map according to a SLIC super-pixel segmentation; and performing a region growing fusion on the super-pixel classification result by taking the preliminary marked result and the K-means classification result as constraints, to determine an identification result of the boundary of the sedimentary facies in the seismic attribute map.

Method for identifying boundary of sedimentary facies, computer device and computer readable storage medium

The technology relates to converting text to speech utilizing recurrent neural networks (RNNs). The recurrent neural networks may be implemented as multiple modules for determining properties of the text. In embodiments, a part-of-speech RNN module, letter-to-sound RNN module, a linguistic prosody tagger RNN module, and a context awareness and semantic mining RNN module may all be utilized. The properties from the RNN modules are processed by a hyper-structure RNN module that determine the phonetic properties of the input text based on the outputs of the other RNN modules. The hyper-structure RNN module may generate a generation sequence that is capable of being converting to audible speech by a speech synthesizer. The generation sequence may also be optimized by a global optimization module prior to being synthesized into audible speech.

Hyper-structure recurrent neural networks for text-to-speech

An example text-to-speech learning system performs a method for generating a pronunciation sequence conversion model. The method includes generating a first pronunciation sequence from a speech input of a training pair and generating a second pronunciation sequence from a text input of the training pair. The method also includes determining a pronunciation sequence difference between the first pronunciation sequence and the second pronunciation sequence; and generating a pronunciation sequence conversion model based on the pronunciation sequence difference. An example speech recognition learning system performs a method for generating a pronunciation sequence conversion model. The method includes extracting an audio signal vector from a speech input and applying an audio signal conversion model to the audio signal vector to generate a converted audio signal vector. The method also includes adapting an acoustic model based on the converted audio signal vector to generate an adapted acoustic model.

Speech recognition and text-to-speech learning system

Pronunciation issues for synthesized speech are automatically detected using human recordings as a reference within a Speech Recognition Assisted Evaluation (SRAE) framework including a Text-To-Speech flow and a Speech Recognition (SR) flow. A pronunciation issue detector evaluates results obtained at multiple levels of the TTS flow and the SR flow (e.g. phone, word, and signal level) by using the corresponding human recordings as the reference for the synthesized speech, and outputs possible pronunciation issues. A signal level may be used to determine similarities/differences between the recordings and the TTS output. A model level checker may provide results to the pronunciation issue detector to check the similarities of the TTS and the SR phone set including mapping relations. Results from a comparison of the SR output and the recordings may also be evaluation by the pronunciation issue detector. The pronunciation issue detector outputs a list that lists potential pronunciation issue candidates.

Speech recognition assisted evaluation on text-to-speech pronunciation issue detection

Growing community of inventors

Beijing, China

Bo Yan